Multica

Desktop OS: macOS

Typed value: Yes.

Web app, Desktop app (macOS, Windows, Linux) and a CLI exist; the iOS client is self-built from source, with no App Store or Android client. Release stage is not labelled and versions are pre-1.0. The browser issue view includes a composer layout specifically for phone-sized viewports.

• Desktop os: Desktop installers for macOS (Apple Silicon and Intel), Windows (x64 and ARM64) and Linux (x64 and ARM64; AppImage, deb, rpm). Minimum OS versions are not stated in the sources read.
• Browser: Web app at multica.ai with email-code or Google sign-in; same account and data as Desktop.

Checked

2026-11-07 · checked 1 week ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Self-built iOS client

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Download Multica

   Finding: Downloads show macOS Apple Silicon/Intel, Windows x64/ARM64 and Linux x64/ARM64 installers; current v0.8.1. Vendor-hosted runtime remains not live, waitlist-only. It is separate from connecting Qoder Cloud Agents.

   Locator

   Choose your platform; Prefer the CLI?; Cloud runtime (waitlist); Current version

   Retrieved

   2026-11-07

2. Desktop app

   Finding: Desktop Mac/Windows/Linux shares server data with web, manages separate daemon profiles, auto-updates with OS/architecture feeds and supports self-hosted apiUrl configuration. Terminal issue CLI installed separately.

   Locator

   Installation; Built-in daemon; Updating Desktop; Connecting to a self-hosted instance

   Retrieved

   2026-11-07

Desktop OS: Windows

Typed value: Yes.

Web app, Desktop app (macOS, Windows, Linux) and a CLI exist; the iOS client is self-built from source, with no App Store or Android client. Release stage is not labelled and versions are pre-1.0. The browser issue view includes a composer layout specifically for phone-sized viewports.

• Desktop os: Desktop installers for macOS (Apple Silicon and Intel), Windows (x64 and ARM64) and Linux (x64 and ARM64; AppImage, deb, rpm). Minimum OS versions are not stated in the sources read.
• Browser: Web app at multica.ai with email-code or Google sign-in; same account and data as Desktop.

Checked

2026-11-07 · checked 1 week ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Self-built iOS client

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Download Multica

   Finding: Downloads show macOS Apple Silicon/Intel, Windows x64/ARM64 and Linux x64/ARM64 installers; current v0.8.1. Vendor-hosted runtime remains not live, waitlist-only. It is separate from connecting Qoder Cloud Agents.

   Locator

   Choose your platform; Prefer the CLI?; Cloud runtime (waitlist); Current version

   Retrieved

   2026-11-07

2. Desktop app

   Finding: Desktop Mac/Windows/Linux shares server data with web, manages separate daemon profiles, auto-updates with OS/architecture feeds and supports self-hosted apiUrl configuration. Terminal issue CLI installed separately.

   Locator

   Installation; Built-in daemon; Updating Desktop; Connecting to a self-hosted instance

   Retrieved

   2026-11-07

Desktop OS: Linux

Typed value: Yes.

Web app, Desktop app (macOS, Windows, Linux) and a CLI exist; the iOS client is self-built from source, with no App Store or Android client. Release stage is not labelled and versions are pre-1.0. The browser issue view includes a composer layout specifically for phone-sized viewports.

• Desktop os: Desktop installers for macOS (Apple Silicon and Intel), Windows (x64 and ARM64) and Linux (x64 and ARM64; AppImage, deb, rpm). Minimum OS versions are not stated in the sources read.
• Browser: Web app at multica.ai with email-code or Google sign-in; same account and data as Desktop.

Checked

2026-11-07 · checked 1 week ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Self-built iOS client

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Download Multica

   Finding: Downloads show macOS Apple Silicon/Intel, Windows x64/ARM64 and Linux x64/ARM64 installers; current v0.8.1. Vendor-hosted runtime remains not live, waitlist-only. It is separate from connecting Qoder Cloud Agents.

   Locator

   Choose your platform; Prefer the CLI?; Cloud runtime (waitlist); Current version

   Retrieved

   2026-11-07

2. Desktop app

   Finding: Desktop Mac/Windows/Linux shares server data with web, manages separate daemon profiles, auto-updates with OS/architecture feeds and supports self-hosted apiUrl configuration. Terminal issue CLI installed separately.

   Locator

   Installation; Built-in daemon; Updating Desktop; Connecting to a self-hosted instance

   Retrieved

   2026-11-07

Web client

Typed value: Yes.

Web app, Desktop app (macOS, Windows, Linux) and a CLI exist; the iOS client is self-built from source, with no App Store or Android client. Release stage is not labelled and versions are pre-1.0. The browser issue view includes a composer layout specifically for phone-sized viewports.

• Desktop os: Desktop installers for macOS (Apple Silicon and Intel), Windows (x64 and ARM64) and Linux (x64 and ARM64; AppImage, deb, rpm). Minimum OS versions are not stated in the sources read.
• Browser: Web app at multica.ai with email-code or Google sign-in; same account and data as Desktop.

Checked

2026-11-07 · checked 1 week ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Self-built iOS client

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Desktop app

   Finding: Desktop Mac/Windows/Linux shares server data with web, manages separate daemon profiles, auto-updates with OS/architecture feeds and supports self-hosted apiUrl configuration. Terminal issue CLI installed separately.

   Locator

   Installation; Built-in daemon; Updating Desktop; Connecting to a self-hosted instance

   Retrieved

   2026-11-07

2. Quickstart

   Finding: Web/Desktop sign-in uses email code or Google. Desktop connects a computer automatically; other computers install CLI and run setup. At least one installed/authenticated coding tool required; no bundled model quota.

   Locator

   Steps 1-5; Common problems

   Retrieved

   2026-11-07

Phone access: Native iOS

Typed value: Yes.

Web app, Desktop app (macOS, Windows, Linux) and a CLI exist; the iOS client is self-built from source, with no App Store or Android client. Release stage is not labelled and versions are pre-1.0. The browser issue view includes a composer layout specifically for phone-sized viewports.

• Mobile apps: iOS only, built from source on a Mac with Xcode and installed over USB; not on the App Store; free-signing installs expire after 7 days; no Android client.
• Cross device continuity: Workspaces, issues, comments and run history live on the server, so the same work is visible from web, Desktop and the iOS app without manual sync.

Checked

2026-11-07 · checked 1 week ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Self-built iOS client

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Mobile app (iOS)

   Finding: Current mobile guide says source-built iPhone client, no App Store and no Android, seven-day free signing, server-owned workspace data. Native iPad support is separately documented in release notes; no device test.

   Locator

   Intro; Prerequisites; 7-day limit of free signing

   Retrieved

   2026-11-07

Phone access: Native Android

Typed value: No.

Web app, Desktop app (macOS, Windows, Linux) and a CLI exist; the iOS client is self-built from source, with no App Store or Android client. Release stage is not labelled and versions are pre-1.0. The browser issue view includes a composer layout specifically for phone-sized viewports.

• Mobile apps: iOS only, built from source on a Mac with Xcode and installed over USB; not on the App Store; free-signing installs expire after 7 days; no Android client.
• Cross device continuity: Workspaces, issues, comments and run history live on the server, so the same work is visible from web, Desktop and the iOS app without manual sync.

Checked

2026-11-10 · checked 5 days ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Self-built iOS client

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Mobile app (iOS)

   Finding: Current mobile guide says source-built iPhone client, no App Store and no Android, seven-day free signing, server-owned workspace data. Native iPad support is separately documented in release notes; no device test.

   Locator

   Intro; Prerequisites; 7-day limit of free signing

   Retrieved

   2026-11-07

Phone access: Phone browser

Typed value: Yes.

Web app, Desktop app (macOS, Windows, Linux) and a CLI exist; the iOS client is self-built from source, with no App Store or Android client. Release stage is not labelled and versions are pre-1.0. The browser issue view includes a composer layout specifically for phone-sized viewports.

• Mobile browser: The shared web issue composer explicitly adapts to phone-sized viewports.

Checked

2026-11-13 · checked 2 days ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Self-built iOS client

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Multica mobile browser issue composer

   Finding: The shared issue view explicitly adapts its comment composer to phone-sized browser viewports via useIsMobile. The application is exposed through the web app as well as desktop clients.

   Locator

   useStickyComposer; apps/web browser application

   Retrieved

   2026-11-13

CLI

Typed value: Yes.

Web app, Desktop app (macOS, Windows, Linux) and a CLI exist; the iOS client is self-built from source, with no App Store or Android client. Release stage is not labelled and versions are pre-1.0. The browser issue view includes a composer layout specifically for phone-sized viewports.

• Cli: multica CLI for macOS, Linux and Windows (install script or Homebrew) manages issues, agents, skills, runtimes and the daemon.
• Task actions: Web and Desktop: assign, comment or @-mention, stop and retry runs, view transcripts; CLI covers assign, status, comment, cancel-task and rerun. Which actions the iOS app offers is not documented in the sources read.

Checked

2026-11-07 · checked 1 week ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Self-built iOS client

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Using the CLI

   Finding: CLI manages workspaces, issues, agents, automations and runtimes. OAuth setup/PAT login, shared issue IDs, status/assignment/comments, run inspect/stop/retry documented; installed --help is authoritative for flags.

   Locator

   Installation; First connection; Common issue operations; Command reference

   Retrieved

   2026-11-07

Coding agents: Claude Code

Typed value: Yes.

The vendor website, the providers table and the install table each list 29 supported coding tools, including ZeroClaw, Muse Code, Devin CLI and ZCode. Multica launches and drives each tool CLI through a local daemon rather than embedding a harness. Custom runtime profiles must fit an existing protocol family. Multica v0.8.2 detects and invokes Antigravity through the installed agy binary, with optional binary-path and model overrides.

• Session integration: The daemon spawns each tool CLI as a child process and drives its structured protocol (Claude Code and Qwen Code stream-json, Codex app-server, ACP or stdio for others); it stores returned session IDs and resumes sessions where the tool supports it.
• Mixed harness operation: Vendor tutorial shows agents on different tools and models in one workspace and one issue (Reviewer on Codex reviewing work of another agent); not observed in a test here.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-10

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Pinned Multica source

Version

Live docs v0.8.1 (docs source at tag v0.8.1, commit b1ea927); protocol source at commit 8db6cfe Antigravity source pass: v0.8.2 (b7f8efcaae6c5f3273c0038252b5d10c81b41068).

• Documentation and source based; no run with two different tools was observed.
• Supported means Multica can invoke the CLI; the tool, its account and model access come from the user.
• Install docs set minimum versions for eleven tools (Antigravity 1.1.10, Claude Code 2.0.0, Codex 0.100.0, GitHub Copilot CLI 1.0.0, Grok 0.2.89, Qwen Code 0.20.0, MiniMax Code 0.1.2, OpenCode 1.1.54, Dim 0.3.10, Devin CLI 3000.3.22, ZeroClaw 0.8.0); Muse Code needs 1.4.10 or later. A tool below its minimum is not registered as a runtime.
• The user supplies the Antigravity CLI and account; the existing documented minimum CLI version remains applicable.

1. AI coding tools comparison

   Finding: Re-read 2026-10-09: Supported tools table (25 CLIs). Model lists come from each runtime. QwenPaw and MiniMax Code do not accept a model chosen in Multica. No full provider list. Session resumption continues for tools marked as supporting it; MiniMax Code starts a fresh session. MCP is not read for Antigravity, GitHub Copilot CLI, DevEco Code or Pi.

   Locator

   Supported tools table; Model sources; Session resumption; MCP configuration; Skill injection

   Retrieved

   2026-10-09

Coding agents: Codex

Typed value: Yes.

The vendor website, the providers table and the install table each list 29 supported coding tools, including ZeroClaw, Muse Code, Devin CLI and ZCode. Multica launches and drives each tool CLI through a local daemon rather than embedding a harness. Custom runtime profiles must fit an existing protocol family. Multica v0.8.2 detects and invokes Antigravity through the installed agy binary, with optional binary-path and model overrides.

• Session integration: The daemon spawns each tool CLI as a child process and drives its structured protocol (Claude Code and Qwen Code stream-json, Codex app-server, ACP or stdio for others); it stores returned session IDs and resumes sessions where the tool supports it.
• Mixed harness operation: Vendor tutorial shows agents on different tools and models in one workspace and one issue (Reviewer on Codex reviewing work of another agent); not observed in a test here.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-10

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Pinned Multica source

Version

Live docs v0.8.1 (docs source at tag v0.8.1, commit b1ea927); protocol source at commit 8db6cfe Antigravity source pass: v0.8.2 (b7f8efcaae6c5f3273c0038252b5d10c81b41068).

• Documentation and source based; no run with two different tools was observed.
• Supported means Multica can invoke the CLI; the tool, its account and model access come from the user.
• Install docs set minimum versions for eleven tools (Antigravity 1.1.10, Claude Code 2.0.0, Codex 0.100.0, GitHub Copilot CLI 1.0.0, Grok 0.2.89, Qwen Code 0.20.0, MiniMax Code 0.1.2, OpenCode 1.1.54, Dim 0.3.10, Devin CLI 3000.3.22, ZeroClaw 0.8.0); Muse Code needs 1.4.10 or later. A tool below its minimum is not registered as a runtime.
• The user supplies the Antigravity CLI and account; the existing documented minimum CLI version remains applicable.

1. AI coding tools comparison

   Finding: Re-read 2026-10-09: Supported tools table (25 CLIs). Model lists come from each runtime. QwenPaw and MiniMax Code do not accept a model chosen in Multica. No full provider list. Session resumption continues for tools marked as supporting it; MiniMax Code starts a fresh session. MCP is not read for Antigravity, GitHub Copilot CLI, DevEco Code or Pi.

   Locator

   Supported tools table; Model sources; Session resumption; MCP configuration; Skill injection

   Retrieved

   2026-10-09

Coding agents: Cursor Agent

Typed value: Yes.

The vendor website, the providers table and the install table each list 29 supported coding tools, including ZeroClaw, Muse Code, Devin CLI and ZCode. Multica launches and drives each tool CLI through a local daemon rather than embedding a harness. Custom runtime profiles must fit an existing protocol family. Multica v0.8.2 detects and invokes Antigravity through the installed agy binary, with optional binary-path and model overrides.

• Session integration: The daemon spawns each tool CLI as a child process and drives its structured protocol (Claude Code and Qwen Code stream-json, Codex app-server, ACP or stdio for others); it stores returned session IDs and resumes sessions where the tool supports it.
• Mixed harness operation: Vendor tutorial shows agents on different tools and models in one workspace and one issue (Reviewer on Codex reviewing work of another agent); not observed in a test here.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-10

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Pinned Multica source

Version

Live docs v0.8.1 (docs source at tag v0.8.1, commit b1ea927); protocol source at commit 8db6cfe Antigravity source pass: v0.8.2 (b7f8efcaae6c5f3273c0038252b5d10c81b41068).

• Documentation and source based; no run with two different tools was observed.
• Supported means Multica can invoke the CLI; the tool, its account and model access come from the user.
• Install docs set minimum versions for eleven tools (Antigravity 1.1.10, Claude Code 2.0.0, Codex 0.100.0, GitHub Copilot CLI 1.0.0, Grok 0.2.89, Qwen Code 0.20.0, MiniMax Code 0.1.2, OpenCode 1.1.54, Dim 0.3.10, Devin CLI 3000.3.22, ZeroClaw 0.8.0); Muse Code needs 1.4.10 or later. A tool below its minimum is not registered as a runtime.
• The user supplies the Antigravity CLI and account; the existing documented minimum CLI version remains applicable.

1. AI coding tools comparison

   Finding: Re-read 2026-10-09: Supported tools table (25 CLIs). Model lists come from each runtime. QwenPaw and MiniMax Code do not accept a model chosen in Multica. No full provider list. Session resumption continues for tools marked as supporting it; MiniMax Code starts a fresh session. MCP is not read for Antigravity, GitHub Copilot CLI, DevEco Code or Pi.

   Locator

   Supported tools table; Model sources; Session resumption; MCP configuration; Skill injection

   Retrieved

   2026-10-09

Coding agents: OpenCode

Typed value: Yes.

The vendor website, the providers table and the install table each list 29 supported coding tools, including ZeroClaw, Muse Code, Devin CLI and ZCode. Multica launches and drives each tool CLI through a local daemon rather than embedding a harness. Custom runtime profiles must fit an existing protocol family. Multica v0.8.2 detects and invokes Antigravity through the installed agy binary, with optional binary-path and model overrides.

• Session integration: The daemon spawns each tool CLI as a child process and drives its structured protocol (Claude Code and Qwen Code stream-json, Codex app-server, ACP or stdio for others); it stores returned session IDs and resumes sessions where the tool supports it.
• Mixed harness operation: Vendor tutorial shows agents on different tools and models in one workspace and one issue (Reviewer on Codex reviewing work of another agent); not observed in a test here.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-10

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Pinned Multica source

Version

Live docs v0.8.1 (docs source at tag v0.8.1, commit b1ea927); protocol source at commit 8db6cfe Antigravity source pass: v0.8.2 (b7f8efcaae6c5f3273c0038252b5d10c81b41068).

• Documentation and source based; no run with two different tools was observed.
• Supported means Multica can invoke the CLI; the tool, its account and model access come from the user.
• Install docs set minimum versions for eleven tools (Antigravity 1.1.10, Claude Code 2.0.0, Codex 0.100.0, GitHub Copilot CLI 1.0.0, Grok 0.2.89, Qwen Code 0.20.0, MiniMax Code 0.1.2, OpenCode 1.1.54, Dim 0.3.10, Devin CLI 3000.3.22, ZeroClaw 0.8.0); Muse Code needs 1.4.10 or later. A tool below its minimum is not registered as a runtime.
• The user supplies the Antigravity CLI and account; the existing documented minimum CLI version remains applicable.

1. AI coding tools comparison

   Finding: Re-read 2026-10-09: Supported tools table (25 CLIs). Model lists come from each runtime. QwenPaw and MiniMax Code do not accept a model chosen in Multica. No full provider list. Session resumption continues for tools marked as supporting it; MiniMax Code starts a fresh session. MCP is not read for Antigravity, GitHub Copilot CLI, DevEco Code or Pi.

   Locator

   Supported tools table; Model sources; Session resumption; MCP configuration; Skill injection

   Retrieved

   2026-10-09

Coding agents: Pi

Typed value: Yes.

The vendor website, the providers table and the install table each list 29 supported coding tools, including ZeroClaw, Muse Code, Devin CLI and ZCode. Multica launches and drives each tool CLI through a local daemon rather than embedding a harness. Custom runtime profiles must fit an existing protocol family. Multica v0.8.2 detects and invokes Antigravity through the installed agy binary, with optional binary-path and model overrides.

• Session integration: The daemon spawns each tool CLI as a child process and drives its structured protocol (Claude Code and Qwen Code stream-json, Codex app-server, ACP or stdio for others); it stores returned session IDs and resumes sessions where the tool supports it.
• Mixed harness operation: Vendor tutorial shows agents on different tools and models in one workspace and one issue (Reviewer on Codex reviewing work of another agent); not observed in a test here.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-10

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Pinned Multica source

Version

Live docs v0.8.1 (docs source at tag v0.8.1, commit b1ea927); protocol source at commit 8db6cfe Antigravity source pass: v0.8.2 (b7f8efcaae6c5f3273c0038252b5d10c81b41068).

• Documentation and source based; no run with two different tools was observed.
• Supported means Multica can invoke the CLI; the tool, its account and model access come from the user.
• Install docs set minimum versions for eleven tools (Antigravity 1.1.10, Claude Code 2.0.0, Codex 0.100.0, GitHub Copilot CLI 1.0.0, Grok 0.2.89, Qwen Code 0.20.0, MiniMax Code 0.1.2, OpenCode 1.1.54, Dim 0.3.10, Devin CLI 3000.3.22, ZeroClaw 0.8.0); Muse Code needs 1.4.10 or later. A tool below its minimum is not registered as a runtime.
• The user supplies the Antigravity CLI and account; the existing documented minimum CLI version remains applicable.

1. AI coding tools comparison

   Finding: Re-read 2026-10-09: Supported tools table (25 CLIs). Model lists come from each runtime. QwenPaw and MiniMax Code do not accept a model chosen in Multica. No full provider list. Session resumption continues for tools marked as supporting it; MiniMax Code starts a fresh session. MCP is not read for Antigravity, GitHub Copilot CLI, DevEco Code or Pi.

   Locator

   Supported tools table; Model sources; Session resumption; MCP configuration; Skill injection

   Retrieved

   2026-10-09

Coding agents: Grok

Typed value: Yes.

The vendor website, the providers table and the install table each list 29 supported coding tools, including ZeroClaw, Muse Code, Devin CLI and ZCode. Multica launches and drives each tool CLI through a local daemon rather than embedding a harness. Custom runtime profiles must fit an existing protocol family. Multica v0.8.2 detects and invokes Antigravity through the installed agy binary, with optional binary-path and model overrides.

• Session integration: The daemon spawns each tool CLI as a child process and drives its structured protocol (Claude Code and Qwen Code stream-json, Codex app-server, ACP or stdio for others); it stores returned session IDs and resumes sessions where the tool supports it.
• Mixed harness operation: Vendor tutorial shows agents on different tools and models in one workspace and one issue (Reviewer on Codex reviewing work of another agent); not observed in a test here.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-10

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Pinned Multica source

Version

Live docs v0.8.1 (docs source at tag v0.8.1, commit b1ea927); protocol source at commit 8db6cfe Antigravity source pass: v0.8.2 (b7f8efcaae6c5f3273c0038252b5d10c81b41068).

• Documentation and source based; no run with two different tools was observed.
• Supported means Multica can invoke the CLI; the tool, its account and model access come from the user.
• Install docs set minimum versions for eleven tools (Antigravity 1.1.10, Claude Code 2.0.0, Codex 0.100.0, GitHub Copilot CLI 1.0.0, Grok 0.2.89, Qwen Code 0.20.0, MiniMax Code 0.1.2, OpenCode 1.1.54, Dim 0.3.10, Devin CLI 3000.3.22, ZeroClaw 0.8.0); Muse Code needs 1.4.10 or later. A tool below its minimum is not registered as a runtime.
• The user supplies the Antigravity CLI and account; the existing documented minimum CLI version remains applicable.

1. AI coding tools comparison

   Finding: Re-read 2026-10-09: Supported tools table (25 CLIs). Model lists come from each runtime. QwenPaw and MiniMax Code do not accept a model chosen in Multica. No full provider list. Session resumption continues for tools marked as supporting it; MiniMax Code starts a fresh session. MCP is not read for Antigravity, GitHub Copilot CLI, DevEco Code or Pi.

   Locator

   Supported tools table; Model sources; Session resumption; MCP configuration; Skill injection

   Retrieved

   2026-10-09

Coding agents: Antigravity

Typed value: Yes.

The vendor website, the providers table and the install table each list 29 supported coding tools, including ZeroClaw, Muse Code, Devin CLI and ZCode. Multica launches and drives each tool CLI through a local daemon rather than embedding a harness. Custom runtime profiles must fit an existing protocol family. Multica v0.8.2 detects and invokes Antigravity through the installed agy binary, with optional binary-path and model overrides.

• Harnesses: Website, providers table and install table name the same 29 tools: Antigravity, Claude Code, CodeBuddy, CodeArts, Codex, GitHub Copilot CLI, Cursor Agent, DeepSeek Harness, DevEco Code, Devin CLI, Dim, Grok, Hermes, Kimi, Kiro CLI, MiniMax Code, Muse Code, Oh-My-Pi, OpenClaw, OpenCode, Pi, Qoder, Qoder CN, Qwen Code, QwenPaw, Reasonix, Trae CLI, ZeroClaw and ZCode. ZeroClaw first shipped as a native ACP runtime in v0.4.33 (2026-08-24). Supported means Multica can invoke the CLI; the tool and its account come from the user. Multica v0.8.2 detects and invokes Antigravity through the installed agy binary, with optional binary-path and model overrides.

Checked

2026-11-13 · checked 2 days ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Pinned Multica source

Version

Live docs v0.8.1 (docs source at tag v0.8.1, commit b1ea927); protocol source at commit 8db6cfe Antigravity source pass: v0.8.2 (b7f8efcaae6c5f3273c0038252b5d10c81b41068).

• Documentation and source based; no run with two different tools was observed.
• Supported means Multica can invoke the CLI; the tool, its account and model access come from the user.
• Install docs set minimum versions for eleven tools (Antigravity 1.1.10, Claude Code 2.0.0, Codex 0.100.0, GitHub Copilot CLI 1.0.0, Grok 0.2.89, Qwen Code 0.20.0, MiniMax Code 0.1.2, OpenCode 1.1.54, Dim 0.3.10, Devin CLI 3000.3.22, ZeroClaw 0.8.0); Muse Code needs 1.4.10 or later. A tool below its minimum is not registered as a runtime.
• The user supplies the Antigravity CLI and account; the existing documented minimum CLI version remains applicable.

1. Multica Antigravity support at v0.8.2

   Finding: Multica v0.8.2 detects and invokes Antigravity through the installed agy binary, with optional binary-path and model overrides.

   Locator

   server/internal/daemon/agents_probe.go lines 260-272, v0.8.2, commit b7f8efcaae6c5f3273c0038252b5d10c81b41068

   Retrieved

   2026-11-10

   Source date

   2026-11-10

2. Multica Antigravity support at v0.8.2

   Finding: Multica v0.8.2 detects and invokes Antigravity through the installed agy binary, with optional binary-path and model overrides.

   Locator

   CLI_AND_DAEMON.md lines 268-280, v0.8.2, commit b7f8efcaae6c5f3273c0038252b5d10c81b41068

   Retrieved

   2026-11-10

   Source date

   2026-11-10

Use my subscription

Typed value: Yes.

Multica does not provide model access in the sources read: each coding tool uses the account, subscription or API key configured for that tool on the user's machine. Multica Cloud requires a Multica account (email code or Google); a self-hosted server has its own email-code sign-in and needs no Multica Cloud account.

• Agent subscriptions: Tools sign in on the user's machine and Multica never receives their login tokens, so a tool's own subscription login is the route; which subscription plans or modes work per tool is not enumerated by Multica.
• Api accounts: Local tools use their own credentials; custom_env may also supply keys. Those values are plaintext in server storage; owner/admin unlock/read/change is audited and list/detail APIs expose only a count.
• Vendor account requirement: Multica Cloud requires a Multica account (email code or Google). A self-hosted server has its own email-code sign-in and needs no Multica Cloud account; codes go to the backend logs until email is configured. A signed-in coding tool account is always separate and required.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Pinned Multica source

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Per-tool subscription support, local models and account switching were not established.
• Existing subscription support cannot be inferred from API-key support.

1. Install AI coding tools

   Finding: Re-read 2026-10-09: Sign in to each tool on its own machine; Multica never receives login tokens. "Supported" means Multica can invoke the CLI; it does not supply the tool account, subscription or model quota. The table lists 25 CLIs. Minimum versions for eight tools; below minimum the runtime is not registered.

   Locator

   Choose a tool; Sign in on your machine

   Retrieved

   2026-11-07

Where agents run: On your computer

Typed value: Yes.

Connected computers execute local-tool runs while Cloud or self-hosted Multica coordinates them. Vendor-hosted runtime remains waitlisted. A separate Qoder Cloud Agents bridge connects provider-hosted environments.

• Local: Desktop starts a built-in daemon, or the CLI daemon runs on the laptop.
• Byo remote: The CLI install and setup commands run on a remote or headless computer over SSH; runs execute there.
• Managed cloud: Multica-hosted runtime remains not live on downloads; Qoder Cloud Agents is a distinct PAT-configured remote runtime, not Multica compute provisioning.
• Hybrid: One workspace can mix several connected computers as runtimes, each private or public.
• Payer: The user pays for their own machines and tool accounts; Multica does not supply model quota.
• Expiry: A runtime offline more than 7 days with no bound agents is cleaned up automatically; session expiry not established.
• Client disconnect: CLI daemon runs in the background; autostart at login requires explicit enable. Desktop owns its own daemon. Execution requires the selected runtime online; no browser-disconnect test.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-10

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Pinned Multica source

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Hosted coordination and execution are separate services.
• Qoder credentials, remote environment and provider setup are required; this is not a universal Multica-hosted compute claim.
• No run, disconnect or self-host deployment test.

1. Daemon and runtimes

   Finding: Connected-computer daemon claims local-tool runs, stores results on server, and has explicit login autostart. Runtimes offline over seven days with no bound agents are cleaned up. Separate Qoder Cloud Agents bridge uses a PAT and remote provider environment without a local daemon; defaults three concurrent runs and 60-minute timeout, configurable.

   Locator

   Daemon vs runtime; Execution location; Dispatch and online status; Concurrency limits; Private and public runtimes; Custom runtime profiles; Task runtime environment

   Retrieved

   2026-11-07

2. Desktop app

   Finding: Desktop Mac/Windows/Linux shares server data with web, manages separate daemon profiles, auto-updates with OS/architecture feeds and supports self-hosted apiUrl configuration. Terminal issue CLI installed separately.

   Locator

   Installation; Built-in daemon; Updating Desktop; Connecting to a self-hosted instance

   Retrieved

   2026-11-07

Where agents run: On your own server

Typed value: Yes.

Connected computers execute local-tool runs while Cloud or self-hosted Multica coordinates them. Vendor-hosted runtime remains waitlisted. A separate Qoder Cloud Agents bridge connects provider-hosted environments.

• Local: Desktop starts a built-in daemon, or the CLI daemon runs on the laptop.
• Byo remote: The CLI install and setup commands run on a remote or headless computer over SSH; runs execute there.
• Managed cloud: Multica-hosted runtime remains not live on downloads; Qoder Cloud Agents is a distinct PAT-configured remote runtime, not Multica compute provisioning.
• Hybrid: One workspace can mix several connected computers as runtimes, each private or public.
• Payer: The user pays for their own machines and tool accounts; Multica does not supply model quota.
• Expiry: A runtime offline more than 7 days with no bound agents is cleaned up automatically; session expiry not established.
• Client disconnect: CLI daemon runs in the background; autostart at login requires explicit enable. Desktop owns its own daemon. Execution requires the selected runtime online; no browser-disconnect test.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-10

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Pinned Multica source

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Hosted coordination and execution are separate services.
• Qoder credentials, remote environment and provider setup are required; this is not a universal Multica-hosted compute claim.
• No run, disconnect or self-host deployment test.

1. Download Multica

   Finding: Downloads show macOS Apple Silicon/Intel, Windows x64/ARM64 and Linux x64/ARM64 installers; current v0.8.1. Vendor-hosted runtime remains not live, waitlist-only. It is separate from connecting Qoder Cloud Agents.

   Locator

   Choose your platform; Prefer the CLI?; Cloud runtime (waitlist); Current version

   Retrieved

   2026-11-07

2. Daemon and runtimes

   Finding: Connected-computer daemon claims local-tool runs, stores results on server, and has explicit login autostart. Runtimes offline over seven days with no bound agents are cleaned up. Separate Qoder Cloud Agents bridge uses a PAT and remote provider environment without a local daemon; defaults three concurrent runs and 60-minute timeout, configurable.

   Locator

   Daemon vs runtime; Execution location; Dispatch and online status; Concurrency limits; Private and public runtimes; Custom runtime profiles; Task runtime environment

   Retrieved

   2026-11-07

Where agents run: In the vendor's cloud

Typed value: No.

Connected computers execute local-tool runs while Cloud or self-hosted Multica coordinates them. Vendor-hosted runtime remains waitlisted. A separate Qoder Cloud Agents bridge connects provider-hosted environments.

• Byo remote: The CLI install and setup commands run on a remote or headless computer over SSH; runs execute there.
• Managed cloud: Multica-hosted runtime remains not live on downloads; Qoder Cloud Agents is a distinct PAT-configured remote runtime, not Multica compute provisioning.

Checked

2026-11-13 · checked 2 days ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Pinned Multica source

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Hosted coordination and execution are separate services.
• Qoder credentials, remote environment and provider setup are required; this is not a universal Multica-hosted compute claim.
• No run, disconnect or self-host deployment test.

1. Download Multica

   Finding: Downloads show macOS Apple Silicon/Intel, Windows x64/ARM64 and Linux x64/ARM64 installers; current v0.8.1. Vendor-hosted runtime remains not live, waitlist-only. It is separate from connecting Qoder Cloud Agents.

   Locator

   Choose your platform; Prefer the CLI?; Cloud runtime (waitlist); Current version

   Retrieved

   2026-11-07

Workspace isolation: Git worktree

Typed value: Yes.

GitHub repository runs get their own worktree from a cached bare clone; local git directories can use per-run worktrees on agent/<agent>/<issue> branches, while a direct local-directory run uses the user's own checkout in place unless Parallel mode is chosen. Multica states it provides no filesystem, process or network sandbox and recommends a dedicated user, container or VM.

• Checkout: Per-run working directory for GitHub resources; local directories run in place against the user's own checkout unless Parallel mode is chosen.
• Branch: Parallel local-directory mode commits to agent/<agent>/<issue> branches; GitHub-resource branching is up to the agent and its instructions.
• Worktree: Repository checkouts use per-task git worktrees from cached bare clones; local directories can use per-run worktrees.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Default daemon path; Windows opt-in Codex sandbox is the one documented exception.
• Two-change code separation was not tested.

1. Project resources

   Finding: Re-read 2026-10-09: GitHub repositories are checked out per run through worktrees in a runtime-managed workspace. Local git directories run in place (serialized, directory lock) or in Parallel worktree mode on agent/<agent>/<issue> branches. Non-git directories run serially. Dependency caches, snapshots and port allocation are not mentioned.

   Locator

   Add a GitHub repository; Add a local directory; How runs share the directory

   Retrieved

   2026-10-09

2. Repository cache

   Finding: Re-read 2026-10-09: Pinned source repocache/cache.go (8db6cfe): the daemon keeps cached bare clones and creates per-task git worktrees from them. The file also calls isolateWorktreeIdentityContext for each worktree checkout and reconciles a Co-authored-by hook.

   Locator

   package header lines 1-35, CachedRepo line 160

   Retrieved

   2026-10-09

Workspace isolation: Container

Typed value: Yes.

GitHub repository runs get their own worktree from a cached bare clone; local git directories can use per-run worktrees on agent/<agent>/<issue> branches, while a direct local-directory run uses the user's own checkout in place unless Parallel mode is chosen. Multica states it provides no filesystem, process or network sandbox and recommends a dedicated user, container or VM.

• Checkout: Per-run working directory for GitHub resources; local directories run in place against the user's own checkout unless Parallel mode is chosen.
• Container: Not provided by Multica; the daemon can be run inside a container the operator sets up, which is the recommended boundary.
• Vm: Not provided by Multica; operator-provided VM is recommended for isolation.
• Os sandbox: Multica states it makes no filesystem-sandbox guarantee and runs tools unsandboxed by default (Codex danger-full-access, Claude Code bypassPermissions); an opt-in native Codex sandbox exists on Windows only.
• Filesystem: Per-run directories avoid collisions but a run has the full file access of the daemon OS user.
• Process: Runs execute with the full permissions of the daemon user; no process isolation is provided (documented).
• Network: Runs can reach the network without restriction (documented).
• Secrets: Run-scoped API tokens are used, but the whole HOME and tool credentials of the daemon user are reachable; custom_env is stored server-side.
• Security boundary: Per-run directories and tokens are conveniences and not a boundary against a run that tries to escape (documented).

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Default daemon path; Windows opt-in Codex sandbox is the one documented exception.
• Two-change code separation was not tested.

1. Security model

   Finding: Re-read 2026-10-09: A run executes with the full permissions of the daemon OS user. Multica does not sandbox the filesystem. Approval prompts are answered automatically. Per-run working directories and per-run API tokens are called conveniences, not a boundary. On the default path Codex runs full-access and Claude Code bypasses permission checks; Codex native sandbox is an optional Windows setting.

   Locator

   The boundary is the daemon user; What Multica does isolate; What is not a boundary

   Retrieved

   2026-10-09

Workspace isolation: VM or microVM

Typed value: Yes.

GitHub repository runs get their own worktree from a cached bare clone; local git directories can use per-run worktrees on agent/<agent>/<issue> branches, while a direct local-directory run uses the user's own checkout in place unless Parallel mode is chosen. Multica states it provides no filesystem, process or network sandbox and recommends a dedicated user, container or VM.

• Checkout: Per-run working directory for GitHub resources; local directories run in place against the user's own checkout unless Parallel mode is chosen.
• Container: Not provided by Multica; the daemon can be run inside a container the operator sets up, which is the recommended boundary.
• Vm: Not provided by Multica; operator-provided VM is recommended for isolation.
• Os sandbox: Multica states it makes no filesystem-sandbox guarantee and runs tools unsandboxed by default (Codex danger-full-access, Claude Code bypassPermissions); an opt-in native Codex sandbox exists on Windows only.
• Filesystem: Per-run directories avoid collisions but a run has the full file access of the daemon OS user.
• Process: Runs execute with the full permissions of the daemon user; no process isolation is provided (documented).
• Network: Runs can reach the network without restriction (documented).
• Secrets: Run-scoped API tokens are used, but the whole HOME and tool credentials of the daemon user are reachable; custom_env is stored server-side.
• Security boundary: Per-run directories and tokens are conveniences and not a boundary against a run that tries to escape (documented).

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Default daemon path; Windows opt-in Codex sandbox is the one documented exception.
• Two-change code separation was not tested.

1. Security model

   Finding: Re-read 2026-10-09: A run executes with the full permissions of the daemon OS user. Multica does not sandbox the filesystem. Approval prompts are answered automatically. Per-run working directories and per-run API tokens are called conveniences, not a boundary. On the default path Codex runs full-access and Claude Code bypasses permission checks; Codex native sandbox is an optional Windows setting.

   Locator

   The boundary is the daemon user; What Multica does isolate; What is not a boundary

   Retrieved

   2026-10-09

Parallel runs

Typed value: Yes.

Multiple runs execute concurrently on a daemon (default 20 per daemon and 6 per agent) and work state is visible in the agent list, issue execution log, header chip and runtime page.

• Concurrent sessions: A daemon runs up to 20 runs at once by default; each agent up to 6; the effective limit is the smaller.
• Concurrent tasks: Many issues can have active runs across agents and runtimes; runs beyond the limit queue.
• Quotas: Documented defaults configurable per agent and through MULTICA_DAEMON_MAX_CONCURRENT_TASKS.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Observed concurrency was not tested; squads do not raise concurrency by themselves.

1. Daemon and runtimes

   Finding: Re-read 2026-10-09: The daemon is the background process on one computer. A runtime is one computer plus one tool or custom profile. Code and tool credentials stay on the computer; the server stores issues, comments, run records and results. Runtimes offline more than 7 days with no bound agents are cleaned up. Default 20 runs per daemon and 6 per agent. Runtimes are private by default. Custom profiles must fit an existing protocol family; "A custom profile does not add a new communication protocol."

   Locator

   Daemon vs runtime; Execution location; Dispatch and online status; Concurrency limits; Private and public runtimes; Custom runtime profiles; Task runtime environment

   Retrieved

   2026-10-09

2. Create and configure an agent

   Finding: Re-read 2026-10-09: Agents start blank or with Build with AI (needs an online runtime). Runtime, model and thinking level. custom_env values are stored in plaintext in the Multica server database; only workspace owners and admins can view or change them. Critical variables such as PATH, HOME and MULTICA_* cannot be overridden.

   Locator

   Starting points; Runtime, model, and thinking level; Configuration after creation; Environment variables and credentials

   Retrieved

   2026-10-09

Coordinator

Typed value: Yes.

Squads provide product-owned delegation: an agent leader receives the issue, @-mentions member agents, records an evaluation, and is re-triggered by replies; members can run on different tools. No provider-native subagent claims were evaluated.

• Roles: Squad leader and members with role descriptions and squad instructions.
• Model harness effort: Each agent has its own runtime, model and thinking level.
• Messages: Delegation and replies are issue comments with explicit @-mention markdown.
• Results return: Members post results back on the issue and the leader is re-triggered by defined rules.
• Cross harness: Vendor tutorial builds a squad from agents using different tools; not tested.
• Orchestration owner: Multica squads orchestrate; the leader is an ordinary agent run with a Squad Operating Protocol appended.
• Activation: Assigning or @-mentioning a squad; an archived or unrunnable leader blocks it.
• Authentication: Agent writes use run-scoped tokens; Access is checked against the leader.
• Live progress: Queue position, run status, steps and logs show inside comment threads and the execution log.
• Retained results: Comments and transcripts persist on the issue.
• Followup: Reply or @-mention to continue with a member or the leader after completion.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Child identity, live progress and reopen behavior were not observed; invocation specifics beyond mention markdown not tested.

1. Runs

   Finding: Re-read 2026-10-09: States deferred, queued, dispatched, waiting_local_directory, running, completed, failed, cancelled. Runs can be stopped from the execution log while deferred, queued, starting, waiting or running. A status change does not stop an active run. Retry from the execution log invokes the original agent and keeps files and session when possible. No pause control. Failure reasons include agent_blocked and missing_config. Dispatched runs fail after 5 minutes. Heartbeat every 15 seconds. Automatic retries only for transient faults (2 attempts, 3 for network interruptions). Transcripts kept.

   Locator

   Execution lifecycle; Viewing run history; Failures and automatic retries; Manual retry; State and timeout quick reference

   Retrieved

   2026-10-09

2. Multica changelog

   Finding: Re-read 2026-10-09: Re-read first 100,000 of 188,543 characters (remainder not read). Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01). Dated entries cited in claims: v0.4.35 (2026-08-26) Pro-plan billing and seat management behind one Cloud address; v0.4.37 (2026-08-31) says Multica installs natively on iPad; v0.5.2 (2026-09-23) and v0.5.3 (2026-09-24) steering of Claude Code, Codex and Grok tasks; v0.5.1 (2026-09-21) issue wakeup rules; v0.6.0 (2026-09-28) wakeups on status change, sub-issue completion and pull request movement, plus add, queue or restart when replying. No dated forward-looking plans in the part read.

   Locator

   Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01); v0.5.1, v0.5.2, v0.6.0, v0.6.1 entries; v0.4.35, v0.4.34

   Retrieved

   2026-10-09

   Source date

   2026-10-01

3. Squads

   Finding: Re-read 2026-10-09: Assignment to a squad wakes only the leader, which @-mentions members, records an evaluation and stops. The leader is woken again when a delegated member replies, a non-member comments or a member posts progress without a mention. Members can be agents or humans. Provider-native subagents are not described.

   Locator

   Squad composition; Execution flow after assignment; Leader re-trigger rules

   Retrieved

   2026-10-09

4. Agents

   Finding: Re-read 2026-10-09: Agent settings: name, instructions, skills, runtime, model and thinking level, Access (Only me default, Specific people, Entire workspace), concurrency, env, MCP. Availability comes from the runtime and workload from runs. Archiving cancels unfinished runs.

   Locator

   Agent configuration; Permissions and Access; Online, offline, and workload status

   Retrieved

   2026-10-09

5. Create and configure an agent

   Finding: Re-read 2026-10-09: Agents start blank or with Build with AI (needs an online runtime). Runtime, model and thinking level. custom_env values are stored in plaintext in the Multica server database; only workspace owners and admins can view or change them. Critical variables such as PATH, HOME and MULTICA_* cannot be overridden.

   Locator

   Starting points; Runtime, model, and thinking level; Configuration after creation; Environment variables and credentials

   Retrieved

   2026-10-09

6. @-mention agents in comments

   Finding: Re-read 2026-10-09: Mentions and replies start runs; a trigger preview is shown before sending. Simultaneous mentions of different agents are not merged; consecutive comments to one agent merge into the pending run. Runs wait when the runtime is offline. Access settings apply to mentions. No presence indicators.

   Locator

   Trigger preview; Automatic routing of replies; Coalescing consecutive comments; Access restrictions

   Retrieved

   2026-10-09

7. Authentication and tokens

   Finding: Re-read 2026-10-09: Browser sessions last 30 days. Personal access tokens (mul_ prefix, 30 days, 90 days, 1 year or never) work against REST endpoints. multica login creates a 90-day token. Run-scoped mat_ tokens last at most 24 hours and attribute actions to the agent. No dedicated REST API reference.

   Locator

   Personal access tokens; Using a PAT in API requests; Temporary tokens for agent runs

   Retrieved

   2026-10-09

8. Tutorial

   Finding: Re-read 2026-10-09: walkthrough. The first agent uses Claude with Sonnet (line 60); the Engineer agent, created through Multica helper, uses Opus (line 85); Reviewer uses Codex with GPT-5.6 Sol in a fresh context and never edits code (line 208). The Engineer opens the PR using the GitHub CLI on the user's computer (line 95). Merging is requested in a comment. Merge-driven status is configurable: the GitHub integration docs say that after PRs merge the issue moves to Done by default or is left alone (github-integration, "After PRs merge, move the issue to"). A PR that references an issue identifier links automatically (line 107).

   Locator

   Prepare the site repository; Reviewer; Merge and close out; Form a squad; Automation

   Retrieved

   2026-10-09

Native issue tracking

Typed value: Yes.

Native issues include creation, editing, comments, priority, labels, assignment, search, filters, projects, five views, backlog parking and explicit dispatch with separate retained runs.

• Create: Title-only creation from the Issues page, projects, CLI or quick create.
• Edit: Issues are editable in the app and by multica issue update.
• Discuss: Threaded comments, mentions, annotations and resolve.
• Prioritize: Priority field and CLI --priority.
• Label: Labels and custom properties, with CLI label commands.
• Assign: Member, agent or squad assignee.
• Search: Issue search in the CLI and instant issue and project search on web and desktop.
• Filter: Filter and sort by status, assignee, project, properties and project status.
• Reopen: No fixed flow between statuses, so a done issue can be moved back by changing status.
• Project epic views: Projects and list, board, table, Gantt and swimlane views.
• Idea parking: The built-in backlog prevents assignment-triggered execution; a follow-up comment to the assignee can still trigger a run while the issue is in backlog (assigning-issues docs).
• Explicit dispatch: Moving out of backlog or confirming Start dispatches the assigned agent.
• Task session separation: An issue retains distinct run records over time.
• Metadata: Status, priority, labels, dates, custom properties and key-value metadata.
• Durable states: Built-in and workspace custom statuses in four lifecycle categories, stored on the server.
• External tracker requirement: No external tracker is required; GitHub is optional for PR linking.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Custom unstarted statuses do not inherit backlog suppression.
• Issue archive was not found (deletion is permanent; cancelled keeps the record); the full save-refine-dispatch scenario with a second person was not run.

1. Issues

   Finding: Re-read 2026-10-09: Seven built-in statuses: backlog, todo, in_progress, in_review, done, blocked, cancelled. Sub-issues with stages and a parent completion notification. No dependency or blocked-by relation documented. Labels and priority described only briefly. When every linked PR merges, the issue moves to the workspace-chosen status, default done.

   Locator

   Parts of an issue; Choose an assignee; Status; Custom statuses; Projects and sub-issues; Switch views

   Retrieved

   2026-10-09

2. Runs

   Finding: Re-read 2026-10-09: States deferred, queued, dispatched, waiting_local_directory, running, completed, failed, cancelled. Runs can be stopped from the execution log while deferred, queued, starting, waiting or running. A status change does not stop an active run. Retry from the execution log invokes the original agent and keeps files and session when possible. No pause control. Failure reasons include agent_blocked and missing_config. Dispatched runs fail after 5 minutes. Heartbeat every 15 seconds. Automatic retries only for transient faults (2 attempts, 3 for network interruptions). Transcripts kept.

   Locator

   Execution lifecycle; Viewing run history; Failures and automatic retries; Manual retry; State and timeout quick reference

   Retrieved

   2026-10-09

3. Multica issue CLI

   Finding: Re-read 2026-10-09: Pinned source cmd_issue.go (8db6cfe): issue subcommands include list, get, pull-requests, children, create, update, assign, status, comment, runs, run-messages, usage, rerun, cancel-task and search; comment update requires --expected-revision; calls go through the shared server API.

   Locator

   issueCmd subcommands lines 222-456 (list/get/pull-requests/children/create/update/assign/status/comment/runs/usage/rerun/cancel-task/search); comment update --expected-revision lines 725 and 2584-2613

   Retrieved

   2026-10-09

4. Multica changelog

   Finding: Re-read 2026-10-09: Re-read first 100,000 of 188,543 characters (remainder not read). Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01). Dated entries cited in claims: v0.4.35 (2026-08-26) Pro-plan billing and seat management behind one Cloud address; v0.4.37 (2026-08-31) says Multica installs natively on iPad; v0.5.2 (2026-09-23) and v0.5.3 (2026-09-24) steering of Claude Code, Codex and Grok tasks; v0.5.1 (2026-09-21) issue wakeup rules; v0.6.0 (2026-09-28) wakeups on status change, sub-issue completion and pull request movement, plus add, queue or restart when replying. No dated forward-looking plans in the part read.

   Locator

   Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01); v0.5.1, v0.5.2, v0.6.0, v0.6.1 entries; v0.4.35, v0.4.34

   Retrieved

   2026-10-09

   Source date

   2026-10-01

5. Using the CLI

   Finding: Re-read 2026-10-09: Commands cover issues, projects, labels, agents, skills, autopilots, workspaces, repos, daemon and runtimes. `multica issue cancel-task <task-id> --issue <issue-id>` cancels a run. `multica issue rerun <id>` re-enqueues for the current assignee. Install via curl script, Homebrew or PowerShell. `issue comment update` requires --expected-revision (source, cmd_issue.go).

   Locator

   Installation; First connection; Common issue operations; Command reference

   Retrieved

   2026-10-09

6. GitHub integration

   Finding: Re-read 2026-10-09: GitHub App is read-only and "never pushes commits, comments, or status checks". PRs auto-link by identifier in branch name or title, or with closing keywords in the body. PR card shows state, size, CI status and mergeability. Merging all linked PRs can move the issue to a chosen status. Optional Co-authored-by trailer "multica-agent <github@multica.ai>". No statement on who merges or on importing GitHub Issues, Linear or Jira.

   Locator

   Connect GitHub; Link a PR to an issue; View PRs on an issue; When merged PRs move an issue

   Retrieved

   2026-10-09

7. Projects

   Finding: Re-read 2026-10-09: Projects group issues (one project per issue) with status, priority, lead, dates, description and resources. The description enters agent execution context. Lead is not a permission and does not auto-assign or run agents. No code search or indexing statement.

   Locator

   Parts of a project; Project description and execution context; Project lead

   Retrieved

   2026-10-09

8. Assign issues to agents

   Finding: Re-read 2026-10-09: Assignment starts a run unless the issue is in backlog or "Don't start yet" is chosen. Access options: Only me, Specific people, Entire workspace. "a run is bound to its runtime and never moves to another machine." CLI assign commands including --no-start.

   Locator

   Assign and start a run; Assign without starting; Assignment permissions; Use the CLI

   Retrieved

   2026-10-09

9. Comments

   Finding: Re-read 2026-10-09: Threaded comments with attachments, annotations, resolve or conclusion, mentions and reactions. Authors edit or delete their own comments; owners and admins edit or delete anyone's; agent-posted comments can only be deleted. Deletion is permanent. Drafts expire after 30 days. Retention and export not stated.

   Locator

   Post comments; Annotate; Resolve a discussion; @-mentions; Edit and delete

   Retrieved

   2026-10-09

Unattended triggers

Typed value: Yes.

Autopilots run on 5-field cron schedules or webhook triggers from the Multica server, and issue wakeup rules can re-wake an agent on a schedule, comment, status change, sub-issue completion or pull request change, with expiry.

• Schedules: Cron schedules with IANA time zone, multiple schedules per autopilot, run-now.
• Events: Webhook triggers with event filters (GitHub, GitLab and generic events) and replay of deliveries.
• Recurring tasks: Create-issue mode makes an issue per trigger; run-only mode creates runs without issues.
• Scheduler location: Server-side scheduler; execution still needs an online runtime.
• Overlaps: Run-only failures are not retried automatically, and the next scheduled run still fires as planned. The autopilot docs do not say whether runs can overlap or how an overlap is handled.
• Retries: Create-issue mode follows run retry rules; run-only mode never retries; autopilots pause after sustained failure.
• Client independence: Schedules fire from the server regardless of clients, but run-only mode is skipped when the runtime is offline. The quickstart troubleshooting says to keep Desktop open for a Desktop runtime to stay online.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• No schedule or wakeup scenario was run.
• An autopilot pauses itself after at least 50 completed or failed runs in seven days with a 90% failure rate, and its creator must resume it.

1. Autopilots

   Finding: Re-read 2026-10-09: Autopilots use 5-field cron with IANA time zones, several schedules per autopilot, and run-now. Webhook triggers (JSON up to 256 KiB, idempotency key, GitHub, GitLab and generic event inference, event filters, replay). Create-issue and run-only modes. Run-only failures are not retried and the next schedule still fires. Create-issue waits for an offline runtime; run-only is skipped. Manual pause stops schedules, webhooks and run-now. Automatic pause after at least 50 completed or failed runs in 7 days with a 90% failure rate. The page does not say whether runs can overlap.

   Locator

   Create; Execution mode; Run on a schedule; Run from a webhook; Failures, pausing, and deletion; Permissions

   Retrieved

   2026-10-09

Shared prompting

Typed value: Yes.

Workspace members share issues and comments with attribution; members can each comment, mention and steer agents with coalescing of simultaneous instructions; presence indicators and plan restrictions were not found.

• Coprompting: Any member who can run an agent can comment, mention or reply; a reply to a running agent can be added, queued or restart it. Two-account steering not tested.
• Ordering: Consecutive comments merge into one pending run; later comments wait and merge into one follow-up run; separate threads queue separately.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Presence and plan restrictions not found.

1. Multica changelog

   Finding: Re-read 2026-10-09: Re-read first 100,000 of 188,543 characters (remainder not read). Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01). Dated entries cited in claims: v0.4.35 (2026-08-26) Pro-plan billing and seat management behind one Cloud address; v0.4.37 (2026-08-31) says Multica installs natively on iPad; v0.5.2 (2026-09-23) and v0.5.3 (2026-09-24) steering of Claude Code, Codex and Grok tasks; v0.5.1 (2026-09-21) issue wakeup rules; v0.6.0 (2026-09-28) wakeups on status change, sub-issue completion and pull request movement, plus add, queue or restart when replying. No dated forward-looking plans in the part read.

   Locator

   Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01); v0.5.1, v0.5.2, v0.6.0, v0.6.1 entries; v0.4.35, v0.4.34

   Retrieved

   2026-10-09

   Source date

   2026-10-01

2. @-mention agents in comments

   Finding: Re-read 2026-10-09: Mentions and replies start runs; a trigger preview is shown before sending. Simultaneous mentions of different agents are not merged; consecutive comments to one agent merge into the pending run. Runs wait when the runtime is offline. Access settings apply to mentions. No presence indicators.

   Locator

   Trigger preview; Automatic routing of replies; Coalescing consecutive comments; Access restrictions

   Retrieved

   2026-10-09

Team roles

Typed value: Yes.

Workspaces have owner, admin and member roles, 7-day invitations and immediate revocation on removal; agent Access (only me, specific people, entire workspace) governs who can run an agent. SSO and provisioning were not found.

• Organization roles: Owner, admin and member with a permission matrix.
• Membership: Invitations by email valid 7 days; removed members lose access immediately and their runtimes and agents are deactivated.
• Unauthorized access: Documented enforcement through Access and roles; not tested with test accounts.
• Revocation: Member removal and PAT revocation take effect immediately (documented).

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Project and task roles, SSO and provisioning were not found; SSO requests are open (#5423, #1392).
• Plan scope of roles unknown.

1. Members and roles

   Finding: Re-read 2026-10-09: Roles owner, admin, member. Invitations valid 7 days. "A removed member loses workspace access immediately"; their runtimes are deactivated, agents archived and unfinished runs cancelled. Roles do not decide who can run an agent. No SSO or provisioning mention.

   Locator

   The three roles; Invite members; Remove a member

   Retrieved

   2026-10-09

Pull request workflow

Typed value: Yes.

Agents run Git and the GitHub CLI themselves; Multica adds per-task worktrees, a task Git identity, optional Co-authored-by trailers, PR auto-linking, CI and mergeability display and merge-driven status changes.

• Commits: Commits use the task Git identity. isolateWorktreeIdentityContext is defined in server/internal/daemon/repocache/identity.go lines 15 to 26 (8db6cfe) and called from cache.go on each worktree checkout; the docs do not describe that identity. Co-authored-by is an optional switch; when it is on, agent commits carry "Co-authored-by: multica-agent <github@multica.ai>".
• Pull requests: PRs are opened by the agent using the GitHub CLI on the user's computer (tutorial); the GitHub App does not create PRs.
• Comments: PR review comments are on GitHub; the integration posts none.
• Conflicts: In Parallel mode merge conflicts with the user's edits are resolved by the agent; PR mergeability shown.
• Product state: PR links, CI, mergeability and merge-driven status moves are product state.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• No draft PR was completed in a fixture; rebase and CI response flows not found.
• The task Git identity is source-inspected only; the docs do not describe it.

1. GitHub integration

   Finding: Re-read 2026-10-09: GitHub App is read-only and "never pushes commits, comments, or status checks". PRs auto-link by identifier in branch name or title, or with closing keywords in the body. PR card shows state, size, CI status and mergeability. Merging all linked PRs can move the issue to a chosen status. Optional Co-authored-by trailer "multica-agent <github@multica.ai>". No statement on who merges or on importing GitHub Issues, Linear or Jira.

   Locator

   Connect GitHub; Link a PR to an issue; View PRs on an issue; When merged PRs move an issue

   Retrieved

   2026-10-09

2. Tutorial

   Finding: Re-read 2026-10-09: walkthrough. The first agent uses Claude with Sonnet (line 60); the Engineer agent, created through Multica helper, uses Opus (line 85); Reviewer uses Codex with GPT-5.6 Sol in a fresh context and never edits code (line 208). The Engineer opens the PR using the GitHub CLI on the user's computer (line 95). Merging is requested in a comment. Merge-driven status is configurable: the GitHub integration docs say that after PRs merge the issue moves to Done by default or is left alone (github-integration, "After PRs merge, move the issue to"). A PR that references an issue identifier links automatically (line 107).

   Locator

   Prepare the site repository; Reviewer; Merge and close out; Form a squad; Automation

   Retrieved

   2026-10-09

Review interface

Typed value: No.

Review is issue- and PR-centric: in_review status, a pull request card with state, size, CI and mergeability, reviewer agents commenting on the issue, and a deliverables sidebar; the diff itself is reviewed on GitHub.

• Pending reviews: in_review status and board or list filters; inbox notifications.
• Change understanding: PR card shows changed files, added and deleted lines, CI status and mergeability.
• Comments: Issue comments; the GitHub integration does not post PR comments.
• Request changes: A project workflow step can set 'If rejected, send back to' so unacceptable work returns for rework; in the vendor tutorial a reviewer agent posts required changes as issue comments and the builder agent is @-mentioned to fix them. The GitHub integration posts nothing to the PR itself.
• Shipping guidance: A line under the PR list says what happens when linked PRs merge.

Checked

2026-11-13 · checked 2 days ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Keyboard and narrow-screen use, effort and missed evidence were not measured; request-changes rests on documented workflow send-back and comments, not a test.

1. GitHub integration

   Finding: Re-read 2026-10-09: GitHub App is read-only and "never pushes commits, comments, or status checks". PRs auto-link by identifier in branch name or title, or with closing keywords in the body. PR card shows state, size, CI status and mergeability. Merging all linked PRs can move the issue to a chosen status. Optional Co-authored-by trailer "multica-agent <github@multica.ai>". No statement on who merges or on importing GitHub Issues, Linear or Jira.

   Locator

   Connect GitHub; Link a PR to an issue; View PRs on an issue; When merged PRs move an issue

   Retrieved

   2026-10-09

2. Inbox and subscriptions

   Finding: Re-read 2026-10-09: Inbox covers assignments, updates on subscribed issues, mentions, reactions, run failures on subscribed issues, results of agent-created issues and autopilot notices. Run-failure notices archive once an issue reaches in_review, started, done or closed; blocked keeps them. Banners follow system and browser settings. Mobile push is not covered on this page.

   Locator

   What lands in the inbox; Tune notification types

   Retrieved

   2026-10-09

3. Multica workflows

   Finding: Workflow columns can hand issues to an agent or person, define the next state after completion and a send-back path. Blocked is reserved for outside obstacles.

   Locator

   Agent steps; Human steps; Handoffs

   Retrieved

   2026-11-07

Product license: Apache-2.0

Typed value: No. Custom terms.

Custom Multica License includes extra conditions.

• Client license: The repository-root LICENSE (Multica License: Apache-2.0 plus Part I conditions) at commit 8db6cfe is the only license file read. Part I requires keeping the Multica logo, product name and attribution in the Multica interface unless a branding waiver is granted. No client-specific license was found in the sources read.
• Server license: Same repository license; hosted or embedded service for third parties needs a commercial license, internal use incl. self-hosting is free.
• Source visibility: Public repository.
• Source revision: 8db6cfe19ae6fd5c35ec71bd8fea42a3ef3861ec

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Pinned Multica source

Availability

source only

Version

commit 8db6cfe

• No legal compliance verdict; inspect the full license for a specific use.
• The plugin SDK package declares Apache-2.0 separately; hosted parity is unknown.

1. Multica License

   Finding: Re-read 2026-10-09: Pinned LICENSE header (8db6cfe): "Multica License", provided under the Apache License 2.0 with additional conditions. Full conditions are summarized on the licensing page re-read today.

   Locator

   Part I conditions 1(a) hosted or embedded service, 1(b) branding, 1(c) attribution, 1(d); Part II Apache-2.0 text (333 lines)

   Retrieved

   2026-10-09

2. Licensing

   Finding: Re-read 2026-10-09: Internal use, including self-hosting for a whole organization, is free. Running for clients, letting outsiders sign in or interact, managed service, or embedding needs a commercial license. Branding and attribution conditions apply. Commercial license requests go through Contact Sales with a stated reply "within three business days".

   Locator

   Rule of thumb; Common scenarios; Other conditions; Getting a commercial license

   Retrieved

   2026-10-09

Product license: MIT

Typed value: No. Custom terms.

Custom Multica License includes extra conditions.

• Client license: The repository-root LICENSE (Multica License: Apache-2.0 plus Part I conditions) at commit 8db6cfe is the only license file read. Part I requires keeping the Multica logo, product name and attribution in the Multica interface unless a branding waiver is granted. No client-specific license was found in the sources read.
• Server license: Same repository license; hosted or embedded service for third parties needs a commercial license, internal use incl. self-hosting is free.
• Source visibility: Public repository.
• Source revision: 8db6cfe19ae6fd5c35ec71bd8fea42a3ef3861ec

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Pinned Multica source

Availability

source only

Version

commit 8db6cfe

• No legal compliance verdict; inspect the full license for a specific use.
• The plugin SDK package declares Apache-2.0 separately; hosted parity is unknown.

1. Multica License

   Finding: Re-read 2026-10-09: Pinned LICENSE header (8db6cfe): "Multica License", provided under the Apache License 2.0 with additional conditions. Full conditions are summarized on the licensing page re-read today.

   Locator

   Part I conditions 1(a) hosted or embedded service, 1(b) branding, 1(c) attribution, 1(d); Part II Apache-2.0 text (333 lines)

   Retrieved

   2026-10-09

2. Licensing

   Finding: Re-read 2026-10-09: Internal use, including self-hosting for a whole organization, is free. Running for clients, letting outsiders sign in or interact, managed service, or embedding needs a commercial license. Branding and attribution conditions apply. Commercial license requests go through Contact Sales with a stated reply "within three business days".

   Locator

   Rule of thumb; Common scenarios; Other conditions; Getting a commercial license

   Retrieved

   2026-10-09

Product license: GPL-3.0

Typed value: No. Custom terms.

Custom Multica License includes extra conditions.

• Client license: The repository-root LICENSE (Multica License: Apache-2.0 plus Part I conditions) at commit 8db6cfe is the only license file read. Part I requires keeping the Multica logo, product name and attribution in the Multica interface unless a branding waiver is granted. No client-specific license was found in the sources read.
• Server license: Same repository license; hosted or embedded service for third parties needs a commercial license, internal use incl. self-hosting is free.
• Source visibility: Public repository.
• Source revision: 8db6cfe19ae6fd5c35ec71bd8fea42a3ef3861ec

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Pinned Multica source

Availability

source only

Version

commit 8db6cfe

• No legal compliance verdict; inspect the full license for a specific use.
• The plugin SDK package declares Apache-2.0 separately; hosted parity is unknown.

1. Multica License

   Finding: Re-read 2026-10-09: Pinned LICENSE header (8db6cfe): "Multica License", provided under the Apache License 2.0 with additional conditions. Full conditions are summarized on the licensing page re-read today.

   Locator

   Part I conditions 1(a) hosted or embedded service, 1(b) branding, 1(c) attribution, 1(d); Part II Apache-2.0 text (333 lines)

   Retrieved

   2026-10-09

2. Licensing

   Finding: Re-read 2026-10-09: Internal use, including self-hosting for a whole organization, is free. Running for clients, letting outsiders sign in or interact, managed service, or embedding needs a commercial license. Branding and attribution conditions apply. Commercial license requests go through Contact Sales with a stated reply "within three business days".

   Locator

   Rule of thumb; Common scenarios; Other conditions; Getting a commercial license

   Retrieved

   2026-10-09

Product license: GPL-3.0-or-later

Typed value: No. Custom terms.

Custom Multica License includes extra conditions.

• Client license: The repository-root LICENSE (Multica License: Apache-2.0 plus Part I conditions) at commit 8db6cfe is the only license file read. Part I requires keeping the Multica logo, product name and attribution in the Multica interface unless a branding waiver is granted. No client-specific license was found in the sources read.
• Server license: Same repository license; hosted or embedded service for third parties needs a commercial license, internal use incl. self-hosting is free.
• Source visibility: Public repository.
• Source revision: 8db6cfe19ae6fd5c35ec71bd8fea42a3ef3861ec

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Pinned Multica source

Availability

source only

Version

commit 8db6cfe

• No legal compliance verdict; inspect the full license for a specific use.
• The plugin SDK package declares Apache-2.0 separately; hosted parity is unknown.

1. Multica License

   Finding: Re-read 2026-10-09: Pinned LICENSE header (8db6cfe): "Multica License", provided under the Apache License 2.0 with additional conditions. Full conditions are summarized on the licensing page re-read today.

   Locator

   Part I conditions 1(a) hosted or embedded service, 1(b) branding, 1(c) attribution, 1(d); Part II Apache-2.0 text (333 lines)

   Retrieved

   2026-10-09

2. Licensing

   Finding: Re-read 2026-10-09: Internal use, including self-hosting for a whole organization, is free. Running for clients, letting outsiders sign in or interact, managed service, or embedding needs a commercial license. Branding and attribution conditions apply. Commercial license requests go through Contact Sales with a stated reply "within three business days".

   Locator

   Rule of thumb; Common scenarios; Other conditions; Getting a commercial license

   Retrieved

   2026-10-09

Product license: AGPL-3.0

Typed value: No. Custom terms.

Custom Multica License includes extra conditions.

• Client license: The repository-root LICENSE (Multica License: Apache-2.0 plus Part I conditions) at commit 8db6cfe is the only license file read. Part I requires keeping the Multica logo, product name and attribution in the Multica interface unless a branding waiver is granted. No client-specific license was found in the sources read.
• Server license: Same repository license; hosted or embedded service for third parties needs a commercial license, internal use incl. self-hosting is free.
• Source visibility: Public repository.
• Source revision: 8db6cfe19ae6fd5c35ec71bd8fea42a3ef3861ec

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Pinned Multica source

Availability

source only

Version

commit 8db6cfe

• No legal compliance verdict; inspect the full license for a specific use.
• The plugin SDK package declares Apache-2.0 separately; hosted parity is unknown.

1. Multica License

   Finding: Re-read 2026-10-09: Pinned LICENSE header (8db6cfe): "Multica License", provided under the Apache License 2.0 with additional conditions. Full conditions are summarized on the licensing page re-read today.

   Locator

   Part I conditions 1(a) hosted or embedded service, 1(b) branding, 1(c) attribution, 1(d); Part II Apache-2.0 text (333 lines)

   Retrieved

   2026-10-09

2. Licensing

   Finding: Re-read 2026-10-09: Internal use, including self-hosting for a whole organization, is free. Running for clients, letting outsiders sign in or interact, managed service, or embedding needs a commercial license. Branding and attribution conditions apply. Commercial license requests go through Contact Sales with a stated reply "within three business days".

   Locator

   Rule of thumb; Common scenarios; Other conditions; Getting a commercial license

   Retrieved

   2026-10-09

Product license: AGPL-3.0-or-later

Typed value: No. Custom terms.

Custom Multica License includes extra conditions.

• Client license: The repository-root LICENSE (Multica License: Apache-2.0 plus Part I conditions) at commit 8db6cfe is the only license file read. Part I requires keeping the Multica logo, product name and attribution in the Multica interface unless a branding waiver is granted. No client-specific license was found in the sources read.
• Server license: Same repository license; hosted or embedded service for third parties needs a commercial license, internal use incl. self-hosting is free.
• Source visibility: Public repository.
• Source revision: 8db6cfe19ae6fd5c35ec71bd8fea42a3ef3861ec

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Pinned Multica source

Availability

source only

Version

commit 8db6cfe

• No legal compliance verdict; inspect the full license for a specific use.
• The plugin SDK package declares Apache-2.0 separately; hosted parity is unknown.

1. Multica License

   Finding: Re-read 2026-10-09: Pinned LICENSE header (8db6cfe): "Multica License", provided under the Apache License 2.0 with additional conditions. Full conditions are summarized on the licensing page re-read today.

   Locator

   Part I conditions 1(a) hosted or embedded service, 1(b) branding, 1(c) attribution, 1(d); Part II Apache-2.0 text (333 lines)

   Retrieved

   2026-10-09

2. Licensing

   Finding: Re-read 2026-10-09: Internal use, including self-hosting for a whole organization, is free. Running for clients, letting outsiders sign in or interact, managed service, or embedding needs a commercial license. Branding and attribution conditions apply. Commercial license requests go through Contact Sales with a stated reply "within three business days".

   Locator

   Rule of thumb; Common scenarios; Other conditions; Getting a commercial license

   Retrieved

   2026-10-09

Product license: Elastic License 2.0

Typed value: No. Custom terms.

Custom Multica License includes extra conditions.

• Client license: The repository-root LICENSE (Multica License: Apache-2.0 plus Part I conditions) at commit 8db6cfe is the only license file read. Part I requires keeping the Multica logo, product name and attribution in the Multica interface unless a branding waiver is granted. No client-specific license was found in the sources read.
• Server license: Same repository license; hosted or embedded service for third parties needs a commercial license, internal use incl. self-hosting is free.
• Source visibility: Public repository.
• Source revision: 8db6cfe19ae6fd5c35ec71bd8fea42a3ef3861ec

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Pinned Multica source

Availability

source only

Version

commit 8db6cfe

• No legal compliance verdict; inspect the full license for a specific use.
• The plugin SDK package declares Apache-2.0 separately; hosted parity is unknown.

1. Multica License

   Finding: Re-read 2026-10-09: Pinned LICENSE header (8db6cfe): "Multica License", provided under the Apache License 2.0 with additional conditions. Full conditions are summarized on the licensing page re-read today.

   Locator

   Part I conditions 1(a) hosted or embedded service, 1(b) branding, 1(c) attribution, 1(d); Part II Apache-2.0 text (333 lines)

   Retrieved

   2026-10-09

2. Licensing

   Finding: Re-read 2026-10-09: Internal use, including self-hosting for a whole organization, is free. Running for clients, letting outsiders sign in or interact, managed service, or embedding needs a commercial license. Branding and attribution conditions apply. Commercial license requests go through Contact Sales with a stated reply "within three business days".

   Locator

   Rule of thumb; Common scenarios; Other conditions; Getting a commercial license

   Retrieved

   2026-10-09

Product license: Custom terms

Typed value: Yes. Custom terms.

Custom Multica License includes extra conditions.

• Client license: The repository-root LICENSE (Multica License: Apache-2.0 plus Part I conditions) at commit 8db6cfe is the only license file read. Part I requires keeping the Multica logo, product name and attribution in the Multica interface unless a branding waiver is granted. No client-specific license was found in the sources read.
• Server license: Same repository license; hosted or embedded service for third parties needs a commercial license, internal use incl. self-hosting is free.
• Source visibility: Public repository.
• Source revision: 8db6cfe19ae6fd5c35ec71bd8fea42a3ef3861ec

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Pinned Multica source

Availability

source only

Version

commit 8db6cfe

• No legal compliance verdict; inspect the full license for a specific use.
• The plugin SDK package declares Apache-2.0 separately; hosted parity is unknown.

1. Multica License

   Finding: Re-read 2026-10-09: Pinned LICENSE header (8db6cfe): "Multica License", provided under the Apache License 2.0 with additional conditions. Full conditions are summarized on the licensing page re-read today.

   Locator

   Part I conditions 1(a) hosted or embedded service, 1(b) branding, 1(c) attribution, 1(d); Part II Apache-2.0 text (333 lines)

   Retrieved

   2026-10-09

2. Licensing

   Finding: Re-read 2026-10-09: Internal use, including self-hosting for a whole organization, is free. Running for clients, letting outsiders sign in or interact, managed service, or embedding needs a commercial license. Branding and attribution conditions apply. Commercial license requests go through Contact Sales with a stated reply "within three business days".

   Locator

   Rule of thumb; Common scenarios; Other conditions; Getting a commercial license

   Retrieved

   2026-10-09

Product license: Proprietary

Typed value: No. Custom terms.

Custom Multica License includes extra conditions.

• Client license: The repository-root LICENSE (Multica License: Apache-2.0 plus Part I conditions) at commit 8db6cfe is the only license file read. Part I requires keeping the Multica logo, product name and attribution in the Multica interface unless a branding waiver is granted. No client-specific license was found in the sources read.
• Server license: Same repository license; hosted or embedded service for third parties needs a commercial license, internal use incl. self-hosting is free.
• Source visibility: Public repository.
• Source revision: 8db6cfe19ae6fd5c35ec71bd8fea42a3ef3861ec

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Pinned Multica source

Availability

source only

Version

commit 8db6cfe

• No legal compliance verdict; inspect the full license for a specific use.
• The plugin SDK package declares Apache-2.0 separately; hosted parity is unknown.

1. Multica License

   Finding: Re-read 2026-10-09: Pinned LICENSE header (8db6cfe): "Multica License", provided under the Apache License 2.0 with additional conditions. Full conditions are summarized on the licensing page re-read today.

   Locator

   Part I conditions 1(a) hosted or embedded service, 1(b) branding, 1(c) attribution, 1(d); Part II Apache-2.0 text (333 lines)

   Retrieved

   2026-10-09

2. Licensing

   Finding: Re-read 2026-10-09: Internal use, including self-hosting for a whole organization, is free. Running for clients, letting outsiders sign in or interact, managed service, or embedding needs a commercial license. Branding and attribution conditions apply. Commercial license requests go through Contact Sales with a stated reply "within three business days".

   Locator

   Rule of thumb; Common scenarios; Other conditions; Getting a commercial license

   Retrieved

   2026-10-09

Self-hosting

Typed value: Yes.

Multica can be self-hosted (Docker Compose, Kubernetes) with Desktop and CLI pointed at it; self-hosted use needs no vendor account, though a daily anonymous telemetry snapshot is on by default. Workspace export and history portability were not found.

• Self hosting: Docker Compose and Kubernetes (Helm) deployment of web, API and Postgres.
• Vendor dependencies: Self-hosting needs no Multica account; optional vendor-run telemetry endpoint (opt-out) and optional Resend, Google OAuth, S3 and LLM services; Cloud uses AWS, Vercel, Stripe, Resend and PostHog.
• Formats: JSON from the CLI; PostgreSQL dumps for self-hosted data.
• Account independence: A self-hosted server and Desktop pointed at it via desktop.json run without a Multica Cloud account.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Pinned Multica source

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Deployment tested parity, import, cancellation and history portability remain unknown.

1. Multica homepage

   Finding: Re-read 2026-10-09: Names 26 coding tools including ZeroClaw. "Start free trial" button, no price list, "no artificial caps when you self-host", source-available wording. Dashboard mockup shows a "Cloud (Anthropic)" runtime, which the download page describes as not live.

   Locator

   Hero; Works with 20+ AI coding tools; Runtimes; Source available; FAQ

   Retrieved

   2026-10-09

2. Self-host quickstart

   Finding: Re-read 2026-10-09: Self-hosting runs Web, API and PostgreSQL through Docker Compose; Kubernetes via Helm is referenced. No email service by default; codes are printed to backend logs until Resend or SMTP is set. Migrations are forward-only. "Self-hosting replaces only the Multica Cloud part."

   Locator

   Multica service and computer; make selfhost; Back up Postgres; Kubernetes

   Retrieved

   2026-10-09

3. Self-hosting guide

   Finding: Re-read 2026-10-09: Pinned SELF_HOSTING.md (8db6cfe): configure RESEND_API_KEY for email codes; without email the code is printed to backend logs; fixed code only when APP_ENV=development.

   Locator

   Telemetry paragraph line 19; Kubernetes section

   Retrieved

   2026-10-09

Telemetry opt-out

Typed value: Yes.

Workspace content (issues, comments, run records, attachments) is stored by Multica; code and tool credentials stay on the connected computer except what agents write back; tools send prompts and code to their model providers. The privacy policy states no training use and lists subprocessors; telemetry is documented with opt-outs.

• Artifacts: Attachments stored by Multica (AWS) or the self-hosted storage.
• Telemetry disclosure: Self-host snapshot contents and Cloud analytics are disclosed.
• Telemetry defaults: Self-host snapshot is on by default; Cloud uses PostHog analytics and crash reports.
• Telemetry controls: DO_NOT_TRACK=1 and ANALYTICS_DISABLED=true on self-hosted servers.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Pinned Multica source

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Vendor statements only; no network traffic or first-run consent prompt was observed; chat titles and follow-ups send chat text to a configured LLM endpoint.

1. Environment variables

   Finding: Re-read 2026-10-09: Telemetry on by default: one anonymous self-host snapshot per UTC day; DO_NOT_TRACK=1 or true disables it; ANALYTICS_DISABLED=true turns off PostHog. MULTICA_DAEMON_MAX_CONCURRENT_TASKS default 20. MULTICA_AGENT_TIMEOUT default 0 (no limit). MULTICA_AGENT_IDLE_WATCHDOG default 2h; tool watchdog same by default. No iteration limit variable listed. Optional server-side LLM for chat titles sends chat content to a configured endpoint.

   Locator

   Daemon configuration; Observability and analytics; Server-side LLM

   Retrieved

   2026-10-09

Free access

Typed value: Yes.

Self-hosting is free for internal use (infrastructure and tool accounts are the user's), the website offers a Start free trial for Cloud with undisclosed terms, and the hosted cloud runtime is an early-access waitlist.

• Self host cost: Self-hosting for use inside one organization is free under the license; hosting for outsiders needs a commercial license.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Card requirement, ongoing free tier and paid evaluation terms are not published.

1. Licensing

   Finding: Re-read 2026-10-09: Internal use, including self-hosting for a whole organization, is free. Running for clients, letting outsiders sign in or interact, managed service, or embedding needs a commercial license. Branding and attribution conditions apply. Commercial license requests go through Contact Sales with a stated reply "within three business days".

   Locator

   Rule of thumb; Common scenarios; Other conditions; Getting a commercial license

   Retrieved

   2026-11-07

Starting price: Free

Typed value: Yes. Free.

Self-hosting is free for internal use (infrastructure and tool accounts are the user's), the website offers a Start free trial for Cloud with undisclosed terms, and the hosted cloud runtime is an early-access waitlist.

• Self host cost: Self-hosting for use inside one organization is free under the license; hosting for outsiders needs a commercial license.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Card requirement, ongoing free tier and paid evaluation terms are not published.

1. Licensing

   Finding: Re-read 2026-10-09: Internal use, including self-hosting for a whole organization, is free. Running for clients, letting outsiders sign in or interact, managed service, or embedding needs a commercial license. Branding and attribution conditions apply. Commercial license requests go through Contact Sales with a stated reply "within three business days".

   Locator

   Rule of thumb; Common scenarios; Other conditions; Getting a commercial license

   Retrieved

   2026-11-07

Starting price: Up to $20/month

Typed value: No. Free.

Self-hosting is free for internal use (infrastructure and tool accounts are the user's), the website offers a Start free trial for Cloud with undisclosed terms, and the hosted cloud runtime is an early-access waitlist.

• Self host cost: Self-hosting for use inside one organization is free under the license; hosting for outsiders needs a commercial license.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Card requirement, ongoing free tier and paid evaluation terms are not published.

1. Licensing

   Finding: Re-read 2026-10-09: Internal use, including self-hosting for a whole organization, is free. Running for clients, letting outsiders sign in or interact, managed service, or embedding needs a commercial license. Branding and attribution conditions apply. Commercial license requests go through Contact Sales with a stated reply "within three business days".

   Locator

   Rule of thumb; Common scenarios; Other conditions; Getting a commercial license

   Retrieved

   2026-11-07

Starting price: $21–40/month

Typed value: No. Free.

Self-hosting is free for internal use (infrastructure and tool accounts are the user's), the website offers a Start free trial for Cloud with undisclosed terms, and the hosted cloud runtime is an early-access waitlist.

• Self host cost: Self-hosting for use inside one organization is free under the license; hosting for outsiders needs a commercial license.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Card requirement, ongoing free tier and paid evaluation terms are not published.

1. Licensing

   Finding: Re-read 2026-10-09: Internal use, including self-hosting for a whole organization, is free. Running for clients, letting outsiders sign in or interact, managed service, or embedding needs a commercial license. Branding and attribution conditions apply. Commercial license requests go through Contact Sales with a stated reply "within three business days".

   Locator

   Rule of thumb; Common scenarios; Other conditions; Getting a commercial license

   Retrieved

   2026-11-07

Starting price: $41–100/month

Typed value: No. Free.

Self-hosting is free for internal use (infrastructure and tool accounts are the user's), the website offers a Start free trial for Cloud with undisclosed terms, and the hosted cloud runtime is an early-access waitlist.

• Self host cost: Self-hosting for use inside one organization is free under the license; hosting for outsiders needs a commercial license.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Card requirement, ongoing free tier and paid evaluation terms are not published.

1. Licensing

   Finding: Re-read 2026-10-09: Internal use, including self-hosting for a whole organization, is free. Running for clients, letting outsiders sign in or interact, managed service, or embedding needs a commercial license. Branding and attribution conditions apply. Commercial license requests go through Contact Sales with a stated reply "within three business days".

   Locator

   Rule of thumb; Common scenarios; Other conditions; Getting a commercial license

   Retrieved

   2026-11-07

Starting price: Over $100/month

Typed value: No. Free.

Self-hosting is free for internal use (infrastructure and tool accounts are the user's), the website offers a Start free trial for Cloud with undisclosed terms, and the hosted cloud runtime is an early-access waitlist.

• Self host cost: Self-hosting for use inside one organization is free under the license; hosting for outsiders needs a commercial license.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Card requirement, ongoing free tier and paid evaluation terms are not published.

1. Licensing

   Finding: Re-read 2026-10-09: Internal use, including self-hosting for a whole organization, is free. Running for clients, letting outsiders sign in or interact, managed service, or embedding needs a commercial license. Branding and attribution conditions apply. Commercial license requests go through Contact Sales with a stated reply "within three business days".

   Locator

   Rule of thumb; Common scenarios; Other conditions; Getting a commercial license

   Retrieved

   2026-11-07

Starting price: Contact for pricing

Typed value: No. Free.

Self-hosting is free for internal use (infrastructure and tool accounts are the user's), the website offers a Start free trial for Cloud with undisclosed terms, and the hosted cloud runtime is an early-access waitlist.

• Self host cost: Self-hosting for use inside one organization is free under the license; hosting for outsiders needs a commercial license.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Card requirement, ongoing free tier and paid evaluation terms are not published.

1. Licensing

   Finding: Re-read 2026-10-09: Internal use, including self-hosting for a whole organization, is free. Running for clients, letting outsiders sign in or interact, managed service, or embedding needs a commercial license. Branding and attribution conditions apply. Commercial license requests go through Contact Sales with a stated reply "within three business days".

   Locator

   Rule of thumb; Common scenarios; Other conditions; Getting a commercial license

   Retrieved

   2026-11-07

Pricing model: Free, no paid plan

Typed value: No.

No public price list was found: /pricing renders a not-found page and the site offers Get started, Book a demo and Contact sales. The homepage FAQ says use inside your own organization is free, including self-hosting. The changelog mentions subscribing to a Pro plan with billing and seat management, without a published price. Model and compute costs are separate and borne by the user. The public subscription interface confirms monthly/yearly human-seat billing but receives actual prices from the Cloud service.

• Interval: Workspace subscriptions have monthly and yearly billing intervals.
• Seats: Subscription unitAmount is per licensed human seat, with additional seat purchases.

Checked

2026-11-13 · checked 2 days ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Multica changelog

   Finding: Says a single Cloud address turns on cloud runtimes, billing and seat management together, and that billing reflects your Pro plan right after you subscribe. No price is given.

   Locator

   August 26, 2026 entry, Improvements and Bug Fixes

   Retrieved

   2026-11-10

2. Multica workspace subscription contract

   Finding: Cloud workspace subscriptions have monthly/yearly intervals and purchasable human seats. Displayed prices are unitAmount per licensed seat. The actual price and currency are server-supplied, so example values are not public prices.

   Locator

   Workspace subscriptions; WorkspaceSubscriptionPrice, lines 184-280

   Retrieved

   2026-11-13

Pricing model: Free plan

Typed value: Yes.

Self-hosting is free for internal use (infrastructure and tool accounts are the user's), the website offers a Start free trial for Cloud with undisclosed terms, and the hosted cloud runtime is an early-access waitlist.

• Self host cost: Self-hosting for use inside one organization is free under the license; hosting for outsiders needs a commercial license.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-10

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Card requirement, ongoing free tier and paid evaluation terms are not published.

1. Licensing

   Finding: Re-read 2026-10-09: Internal use, including self-hosting for a whole organization, is free. Running for clients, letting outsiders sign in or interact, managed service, or embedding needs a commercial license. Branding and attribution conditions apply. Commercial license requests go through Contact Sales with a stated reply "within three business days".

   Locator

   Rule of thumb; Common scenarios; Other conditions; Getting a commercial license

   Retrieved

   2026-11-07

Pricing model: Subscription

Typed value: Yes.

No public price list was found: /pricing renders a not-found page and the site offers Get started, Book a demo and Contact sales. The homepage FAQ says use inside your own organization is free, including self-hosting. The changelog mentions subscribing to a Pro plan with billing and seat management, without a published price. Model and compute costs are separate and borne by the user. The public subscription interface confirms monthly/yearly human-seat billing but receives actual prices from the Cloud service.

• Interval: Workspace subscriptions have monthly and yearly billing intervals.
• Seats: Subscription unitAmount is per licensed human seat, with additional seat purchases.

Checked

2026-11-13 · checked 2 days ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Multica changelog

   Finding: Says a single Cloud address turns on cloud runtimes, billing and seat management together, and that billing reflects your Pro plan right after you subscribe. No price is given.

   Locator

   August 26, 2026 entry, Improvements and Bug Fixes

   Retrieved

   2026-11-10

2. Multica workspace subscription contract

   Finding: Cloud workspace subscriptions have monthly/yearly intervals and purchasable human seats. Displayed prices are unitAmount per licensed seat. The actual price and currency are server-supplied, so example values are not public prices.

   Locator

   Workspace subscriptions; WorkspaceSubscriptionPrice, lines 184-280

   Retrieved

   2026-11-13

Pricing model: Per seat

Typed value: Yes.

No public price list was found: /pricing renders a not-found page and the site offers Get started, Book a demo and Contact sales. The homepage FAQ says use inside your own organization is free, including self-hosting. The changelog mentions subscribing to a Pro plan with billing and seat management, without a published price. Model and compute costs are separate and borne by the user. The public subscription interface confirms monthly/yearly human-seat billing but receives actual prices from the Cloud service.

• Interval: Workspace subscriptions have monthly and yearly billing intervals.
• Seats: Subscription unitAmount is per licensed human seat, with additional seat purchases.

Checked

2026-11-13 · checked 2 days ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Multica changelog

   Finding: Says a single Cloud address turns on cloud runtimes, billing and seat management together, and that billing reflects your Pro plan right after you subscribe. No price is given.

   Locator

   August 26, 2026 entry, Improvements and Bug Fixes

   Retrieved

   2026-11-10

2. Multica workspace subscription contract

   Finding: Cloud workspace subscriptions have monthly/yearly intervals and purchasable human seats. Displayed prices are unitAmount per licensed seat. The actual price and currency are server-supplied, so example values are not public prices.

   Locator

   Workspace subscriptions; WorkspaceSubscriptionPrice, lines 184-280

   Retrieved

   2026-11-13

Pricing model: Bring your own key

Typed value: Yes.

No public price list was found: /pricing renders a not-found page and the site offers Get started, Book a demo and Contact sales. The homepage FAQ says use inside your own organization is free, including self-hosting. The changelog mentions subscribing to a Pro plan with billing and seat management, without a published price. Model and compute costs are separate and borne by the user. The public subscription interface confirms monthly/yearly human-seat billing but receives actual prices from the Cloud service.

• Model cost: Model usage uses the user coding-tool accounts or API credentials and is paid separately to those providers.

Checked

2026-11-13 · checked 2 days ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Multica coding-tool credentials

   Finding: A Multica runtime invokes the coding tool already installed and signed in on the user computer. Tool account access determines available models; Amp explicitly requires AMP_API_KEY in the daemon/agent environment. Model credentials and billing stay with that user/provider account.

   Locator

   Supported tools; model sources; Amp credentials

   Retrieved

   2026-11-13

Paid plans from: No paid plan

Typed value: No. Contact sales.

No public price list was found: /pricing renders a not-found page and the site offers Get started, Book a demo and Contact sales. The homepage FAQ says use inside your own organization is free, including self-hosting. The changelog mentions subscribing to a Pro plan with billing and seat management, without a published price. Model and compute costs are separate and borne by the user. The public subscription interface confirms monthly/yearly human-seat billing but receives actual prices from the Cloud service.

Checked

2026-11-10 · checked 5 days ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Multica

   Finding: Offers "Get started", "Book a demo" and a footer "Contact sales" link. FAQ: using Multica inside your own organization is free, including self-hosting; a commercial licence is needed only to offer it to others or embed it in a product. Page metadata lists an offer at price 0 USD. No price list.

   Locator

   Hero buttons, FAQ "Can I use Multica commercially?", footer and JSON-LD offer

   Retrieved

   2026-11-10

2. Multica changelog

   Finding: Says a single Cloud address turns on cloud runtimes, billing and seat management together, and that billing reflects your Pro plan right after you subscribe. No price is given.

   Locator

   August 26, 2026 entry, Improvements and Bug Fixes

   Retrieved

   2026-11-10

Paid plans from: $10 or less/month

Typed value: No. Contact sales.

No public price list was found: /pricing renders a not-found page and the site offers Get started, Book a demo and Contact sales. The homepage FAQ says use inside your own organization is free, including self-hosting. The changelog mentions subscribing to a Pro plan with billing and seat management, without a published price. Model and compute costs are separate and borne by the user. The public subscription interface confirms monthly/yearly human-seat billing but receives actual prices from the Cloud service.

Checked

2026-11-10 · checked 5 days ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Multica

   Finding: Offers "Get started", "Book a demo" and a footer "Contact sales" link. FAQ: using Multica inside your own organization is free, including self-hosting; a commercial licence is needed only to offer it to others or embed it in a product. Page metadata lists an offer at price 0 USD. No price list.

   Locator

   Hero buttons, FAQ "Can I use Multica commercially?", footer and JSON-LD offer

   Retrieved

   2026-11-10

2. Multica changelog

   Finding: Says a single Cloud address turns on cloud runtimes, billing and seat management together, and that billing reflects your Pro plan right after you subscribe. No price is given.

   Locator

   August 26, 2026 entry, Improvements and Bug Fixes

   Retrieved

   2026-11-10

Paid plans from: $11–20/month

Typed value: No. Contact sales.

No public price list was found: /pricing renders a not-found page and the site offers Get started, Book a demo and Contact sales. The homepage FAQ says use inside your own organization is free, including self-hosting. The changelog mentions subscribing to a Pro plan with billing and seat management, without a published price. Model and compute costs are separate and borne by the user. The public subscription interface confirms monthly/yearly human-seat billing but receives actual prices from the Cloud service.

Checked

2026-11-10 · checked 5 days ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Multica

   Finding: Offers "Get started", "Book a demo" and a footer "Contact sales" link. FAQ: using Multica inside your own organization is free, including self-hosting; a commercial licence is needed only to offer it to others or embed it in a product. Page metadata lists an offer at price 0 USD. No price list.

   Locator

   Hero buttons, FAQ "Can I use Multica commercially?", footer and JSON-LD offer

   Retrieved

   2026-11-10

2. Multica changelog

   Finding: Says a single Cloud address turns on cloud runtimes, billing and seat management together, and that billing reflects your Pro plan right after you subscribe. No price is given.

   Locator

   August 26, 2026 entry, Improvements and Bug Fixes

   Retrieved

   2026-11-10

Paid plans from: $21–40/month

Typed value: No. Contact sales.

No public price list was found: /pricing renders a not-found page and the site offers Get started, Book a demo and Contact sales. The homepage FAQ says use inside your own organization is free, including self-hosting. The changelog mentions subscribing to a Pro plan with billing and seat management, without a published price. Model and compute costs are separate and borne by the user. The public subscription interface confirms monthly/yearly human-seat billing but receives actual prices from the Cloud service.

Checked

2026-11-10 · checked 5 days ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Multica

   Finding: Offers "Get started", "Book a demo" and a footer "Contact sales" link. FAQ: using Multica inside your own organization is free, including self-hosting; a commercial licence is needed only to offer it to others or embed it in a product. Page metadata lists an offer at price 0 USD. No price list.

   Locator

   Hero buttons, FAQ "Can I use Multica commercially?", footer and JSON-LD offer

   Retrieved

   2026-11-10

2. Multica changelog

   Finding: Says a single Cloud address turns on cloud runtimes, billing and seat management together, and that billing reflects your Pro plan right after you subscribe. No price is given.

   Locator

   August 26, 2026 entry, Improvements and Bug Fixes

   Retrieved

   2026-11-10

Paid plans from: $41–100/month

Typed value: No. Contact sales.

No public price list was found: /pricing renders a not-found page and the site offers Get started, Book a demo and Contact sales. The homepage FAQ says use inside your own organization is free, including self-hosting. The changelog mentions subscribing to a Pro plan with billing and seat management, without a published price. Model and compute costs are separate and borne by the user. The public subscription interface confirms monthly/yearly human-seat billing but receives actual prices from the Cloud service.

Checked

2026-11-10 · checked 5 days ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Multica

   Finding: Offers "Get started", "Book a demo" and a footer "Contact sales" link. FAQ: using Multica inside your own organization is free, including self-hosting; a commercial licence is needed only to offer it to others or embed it in a product. Page metadata lists an offer at price 0 USD. No price list.

   Locator

   Hero buttons, FAQ "Can I use Multica commercially?", footer and JSON-LD offer

   Retrieved

   2026-11-10

2. Multica changelog

   Finding: Says a single Cloud address turns on cloud runtimes, billing and seat management together, and that billing reflects your Pro plan right after you subscribe. No price is given.

   Locator

   August 26, 2026 entry, Improvements and Bug Fixes

   Retrieved

   2026-11-10

Paid plans from: Over $100/month

Typed value: No. Contact sales.

No public price list was found: /pricing renders a not-found page and the site offers Get started, Book a demo and Contact sales. The homepage FAQ says use inside your own organization is free, including self-hosting. The changelog mentions subscribing to a Pro plan with billing and seat management, without a published price. Model and compute costs are separate and borne by the user. The public subscription interface confirms monthly/yearly human-seat billing but receives actual prices from the Cloud service.

Checked

2026-11-10 · checked 5 days ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Multica

   Finding: Offers "Get started", "Book a demo" and a footer "Contact sales" link. FAQ: using Multica inside your own organization is free, including self-hosting; a commercial licence is needed only to offer it to others or embed it in a product. Page metadata lists an offer at price 0 USD. No price list.

   Locator

   Hero buttons, FAQ "Can I use Multica commercially?", footer and JSON-LD offer

   Retrieved

   2026-11-10

2. Multica changelog

   Finding: Says a single Cloud address turns on cloud runtimes, billing and seat management together, and that billing reflects your Pro plan right after you subscribe. No price is given.

   Locator

   August 26, 2026 entry, Improvements and Bug Fixes

   Retrieved

   2026-11-10

Paid plans from: Contact sales

Typed value: Yes. Contact sales.

No public price list was found: /pricing renders a not-found page and the site offers Get started, Book a demo and Contact sales. The homepage FAQ says use inside your own organization is free, including self-hosting. The changelog mentions subscribing to a Pro plan with billing and seat management, without a published price. Model and compute costs are separate and borne by the user. The public subscription interface confirms monthly/yearly human-seat billing but receives actual prices from the Cloud service.

Checked

2026-11-10 · checked 5 days ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Multica

   Finding: Offers "Get started", "Book a demo" and a footer "Contact sales" link. FAQ: using Multica inside your own organization is free, including self-hosting; a commercial licence is needed only to offer it to others or embed it in a product. Page metadata lists an offer at price 0 USD. No price list.

   Locator

   Hero buttons, FAQ "Can I use Multica commercially?", footer and JSON-LD offer

   Retrieved

   2026-11-10

2. Multica changelog

   Finding: Says a single Cloud address turns on cloud runtimes, billing and seat management together, and that billing reflects your Pro plan right after you subscribe. No price is given.

   Locator

   August 26, 2026 entry, Improvements and Bug Fixes

   Retrieved

   2026-11-10

Keeps going with laptop closed

Typed value: Yes.

Connected computers execute local-tool runs while Cloud or self-hosted Multica coordinates them. Vendor-hosted runtime remains waitlisted. A separate Qoder Cloud Agents bridge connects provider-hosted environments.

• Local: Desktop starts a built-in daemon, or the CLI daemon runs on the laptop.
• Byo remote: The CLI install and setup commands run on a remote or headless computer over SSH; runs execute there.
• Self hosted: Docker Compose (and Helm) self-hosting of the web, API and database; computers still run the daemon.
• Managed cloud: Multica-hosted runtime remains not live on downloads; Qoder Cloud Agents is a distinct PAT-configured remote runtime, not Multica compute provisioning.
• Hybrid: One workspace can mix several connected computers as runtimes, each private or public.
• Payer: The user pays for their own machines and tool accounts; Multica does not supply model quota.
• Expiry: A runtime offline more than 7 days with no bound agents is cleaned up automatically; session expiry not established.
• Client disconnect: CLI daemon runs in the background; autostart at login requires explicit enable. Desktop owns its own daemon. Execution requires the selected runtime online; no browser-disconnect test.

Checked

2026-11-13 · checked 2 days ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Pinned Multica source

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Hosted coordination and execution are separate services.
• Qoder credentials, remote environment and provider setup are required; this is not a universal Multica-hosted compute claim.
• No run, disconnect or self-host deployment test.

1. Daemon and runtimes

   Finding: Connected-computer daemon claims local-tool runs, stores results on server, and has explicit login autostart. Runtimes offline over seven days with no bound agents are cleaned up. Separate Qoder Cloud Agents bridge uses a PAT and remote provider environment without a local daemon; defaults three concurrent runs and 60-minute timeout, configurable.

   Locator

   Daemon vs runtime; Execution location; Dispatch and online status; Concurrency limits; Private and public runtimes; Custom runtime profiles; Task runtime environment

   Retrieved

   2026-11-07

2. Self-host quickstart

   Finding: Re-read 2026-10-09: Self-hosting runs Web, API and PostgreSQL through Docker Compose; Kubernetes via Helm is referenced. No email service by default; codes are printed to backend logs until Resend or SMTP is set. Migrations are forward-only. "Self-hosting replaces only the Multica Cloud part."

   Locator

   Multica service and computer; make selfhost; Back up Postgres; Kubernetes

   Retrieved

   2026-11-07

3. How Multica works

   Finding: Re-read 2026-10-09: The server coordinates and records work; connected computers execute it. Code directories and local files stay on the connected computer. The server stores issues, comments, statuses, run records and results. Custom env values are stored on the server. The boundary is the same on Cloud and self-hosted.

   Locator

   The full path of a run; The data and execution boundary

   Retrieved

   2026-11-07

Open-source license

Typed value: No. Custom terms.

Custom Multica License includes extra conditions.

• Client license: The repository-root LICENSE (Multica License: Apache-2.0 plus Part I conditions) at commit 8db6cfe is the only license file read. Part I requires keeping the Multica logo, product name and attribution in the Multica interface unless a branding waiver is granted. No client-specific license was found in the sources read.
• Server license: Same repository license; hosted or embedded service for third parties needs a commercial license, internal use incl. self-hosting is free.
• Source visibility: Public repository.
• Source revision: 8db6cfe19ae6fd5c35ec71bd8fea42a3ef3861ec

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Pinned Multica source

Availability

source only

Version

commit 8db6cfe

• No legal compliance verdict; inspect the full license for a specific use.
• The plugin SDK package declares Apache-2.0 separately; hosted parity is unknown.

1. Multica License

   Finding: Re-read 2026-10-09: Pinned LICENSE header (8db6cfe): "Multica License", provided under the Apache License 2.0 with additional conditions. Full conditions are summarized on the licensing page re-read today.

   Locator

   Part I conditions 1(a) hosted or embedded service, 1(b) branding, 1(c) attribution, 1(d); Part II Apache-2.0 text (333 lines)

   Retrieved

   2026-10-09

2. Licensing

   Finding: Re-read 2026-10-09: Internal use, including self-hosting for a whole organization, is free. Running for clients, letting outsiders sign in or interact, managed service, or embedding needs a commercial license. Branding and attribution conditions apply. Commercial license requests go through Contact Sales with a stated reply "within three business days".

   Locator

   Rule of thumb; Common scenarios; Other conditions; Getting a commercial license

   Retrieved

   2026-10-09

Any desktop app

Typed value: Yes.

Web app, Desktop app (macOS, Windows, Linux) and a CLI exist; the iOS client is self-built from source, with no App Store or Android client. Release stage is not labelled and versions are pre-1.0. The browser issue view includes a composer layout specifically for phone-sized viewports.

• Desktop os: Desktop installers for macOS (Apple Silicon and Intel), Windows (x64 and ARM64) and Linux (x64 and ARM64; AppImage, deb, rpm). Minimum OS versions are not stated in the sources read.
• Browser: Web app at multica.ai with email-code or Google sign-in; same account and data as Desktop.

Checked

2026-11-07 · checked 1 week ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Self-built iOS client

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Download Multica

   Finding: Downloads show macOS Apple Silicon/Intel, Windows x64/ARM64 and Linux x64/ARM64 installers; current v0.8.1. Vendor-hosted runtime remains not live, waitlist-only. It is separate from connecting Qoder Cloud Agents.

   Locator

   Choose your platform; Prefer the CLI?; Cloud runtime (waitlist); Current version

   Retrieved

   2026-11-07

2. Desktop app

   Finding: Desktop Mac/Windows/Linux shares server data with web, manages separate daemon profiles, auto-updates with OS/architecture feeds and supports self-hosted apiUrl configuration. Terminal issue CLI installed separately.

   Locator

   Installation; Built-in daemon; Updating Desktop; Connecting to a self-hosted instance

   Retrieved

   2026-11-07

Paid plan up to $20/month

Typed value: No. Contact sales.

No public price list was found: /pricing renders a not-found page and the site offers Get started, Book a demo and Contact sales. The homepage FAQ says use inside your own organization is free, including self-hosting. The changelog mentions subscribing to a Pro plan with billing and seat management, without a published price. Model and compute costs are separate and borne by the user. The public subscription interface confirms monthly/yearly human-seat billing but receives actual prices from the Cloud service.

Checked

2026-11-10 · checked 5 days ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Multica

   Finding: Offers "Get started", "Book a demo" and a footer "Contact sales" link. FAQ: using Multica inside your own organization is free, including self-hosting; a commercial licence is needed only to offer it to others or embed it in a product. Page metadata lists an offer at price 0 USD. No price list.

   Locator

   Hero buttons, FAQ "Can I use Multica commercially?", footer and JSON-LD offer

   Retrieved

   2026-11-10

2. Multica changelog

   Finding: Says a single Cloud address turns on cloud runtimes, billing and seat management together, and that billing reflects your Pro plan right after you subscribe. No price is given.

   Locator

   August 26, 2026 entry, Improvements and Bug Fixes

   Retrieved

   2026-11-10

Paid plan up to $40/month

Typed value: No. Contact sales.

No public price list was found: /pricing renders a not-found page and the site offers Get started, Book a demo and Contact sales. The homepage FAQ says use inside your own organization is free, including self-hosting. The changelog mentions subscribing to a Pro plan with billing and seat management, without a published price. Model and compute costs are separate and borne by the user. The public subscription interface confirms monthly/yearly human-seat billing but receives actual prices from the Cloud service.

Checked

2026-11-10 · checked 5 days ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Multica

   Finding: Offers "Get started", "Book a demo" and a footer "Contact sales" link. FAQ: using Multica inside your own organization is free, including self-hosting; a commercial licence is needed only to offer it to others or embed it in a product. Page metadata lists an offer at price 0 USD. No price list.

   Locator

   Hero buttons, FAQ "Can I use Multica commercially?", footer and JSON-LD offer

   Retrieved

   2026-11-10

2. Multica changelog

   Finding: Says a single Cloud address turns on cloud runtimes, billing and seat management together, and that billing reflects your Pro plan right after you subscribe. No price is given.

   Locator

   August 26, 2026 entry, Improvements and Bug Fixes

   Retrieved

   2026-11-10

Any phone client

Typed value: Yes.

Web app, Desktop app (macOS, Windows, Linux) and a CLI exist; the iOS client is self-built from source, with no App Store or Android client. Release stage is not labelled and versions are pre-1.0. The browser issue view includes a composer layout specifically for phone-sized viewports.

• Mobile apps: iOS only, built from source on a Mac with Xcode and installed over USB; not on the App Store; free-signing installs expire after 7 days; no Android client.
• Cross device continuity: Workspaces, issues, comments and run history live on the server, so the same work is visible from web, Desktop and the iOS app without manual sync.

Checked

2026-11-07 · checked 1 week ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Self-built iOS client

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Mobile app (iOS)

   Finding: Current mobile guide says source-built iPhone client, no App Store and no Android, seven-day free signing, server-owned workspace data. Native iPad support is separately documented in release notes; no device test.

   Locator

   Intro; Prerequisites; 7-day limit of free signing

   Retrieved

   2026-11-07

multica:ACC-01

Web app, Desktop app (macOS, Windows, Linux) and a CLI exist; the iOS client is self-built from source, with no App Store or Android client. Release stage is not labelled and versions are pre-1.0. The browser issue view includes a composer layout specifically for phone-sized viewports.

Checked

2026-11-07 · checked 1 week ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Self-built iOS client

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

1. Runs

   Finding: Re-read 2026-10-09: States deferred, queued, dispatched, waiting_local_directory, running, completed, failed, cancelled. Runs can be stopped from the execution log while deferred, queued, starting, waiting or running. A status change does not stop an active run. Retry from the execution log invokes the original agent and keeps files and session when possible. No pause control. Failure reasons include agent_blocked and missing_config. Dispatched runs fail after 5 minutes. Heartbeat every 15 seconds. Automatic retries only for transient faults (2 attempts, 3 for network interruptions). Transcripts kept.

   Locator

   Execution lifecycle; Viewing run history; Failures and automatic retries; Manual retry; State and timeout quick reference

   Retrieved

   2026-11-07

2. Mobile app (iOS)

   Finding: Current mobile guide says source-built iPhone client, no App Store and no Android, seven-day free signing, server-owned workspace data. Native iPad support is separately documented in release notes; no device test.

   Locator

   Intro; Prerequisites; 7-day limit of free signing

   Retrieved

   2026-11-07

3. Multica changelog

   Finding: Current changelog lists v0.8.1 dated November 6, 2026, after v0.8.0 November 3. Skills revision history, unread filters and Qoder updates are released, not future promises.

   Locator

   v0.8.1 (November 6, 2026), v0.8.0 (November 3) and historical release entries

   Retrieved

   2026-11-07

   Source date

   2026-11-06

4. Download Multica

   Finding: Downloads show macOS Apple Silicon/Intel, Windows x64/ARM64 and Linux x64/ARM64 installers; current v0.8.1. Vendor-hosted runtime remains not live, waitlist-only. It is separate from connecting Qoder Cloud Agents.

   Locator

   Choose your platform; Prefer the CLI?; Cloud runtime (waitlist); Current version

   Retrieved

   2026-11-07

5. Desktop app

   Finding: Desktop Mac/Windows/Linux shares server data with web, manages separate daemon profiles, auto-updates with OS/architecture feeds and supports self-hosted apiUrl configuration. Terminal issue CLI installed separately.

   Locator

   Installation; Built-in daemon; Updating Desktop; Connecting to a self-hosted instance

   Retrieved

   2026-11-07

6. Quickstart

   Finding: Web/Desktop sign-in uses email code or Google. Desktop connects a computer automatically; other computers install CLI and run setup. At least one installed/authenticated coding tool required; no bundled model quota.

   Locator

   Steps 1-5; Common problems

   Retrieved

   2026-11-07

7. Using the CLI

   Finding: CLI manages workspaces, issues, agents, automations and runtimes. OAuth setup/PAT login, shared issue IDs, status/assignment/comments, run inspect/stop/retry documented; installed --help is authoritative for flags.

   Locator

   Installation; First connection; Common issue operations; Command reference

   Retrieved

   2026-11-07

8. Assign issues to agents

   Finding: Re-read 2026-10-09: Assignment starts a run unless the issue is in backlog or "Don't start yet" is chosen. Access options: Only me, Specific people, Entire workspace. "a run is bound to its runtime and never moves to another machine." CLI assign commands including --no-start.

   Locator

   Assign and start a run; Assign without starting; Assignment permissions; Use the CLI

   Retrieved

   2026-11-07

9. Inbox and subscriptions

   Finding: Inbox collects assignment, comment, mention and agent-failure attention events; full history remains on the issue.

   Locator

   What lands in the inbox; Tune notification types

   Retrieved

   2026-11-07

10. Multica GitHub issues

    Finding: Newest issue list reread November 7. Requests are not vendor announcements; prior October counts are not refreshed.

    Locator

    Searches 2026-10-08: Android, App Store, SSO/SAML, dependency/blocked-by, budget/spend limit, cloud runtime

    Retrieved

    2026-11-07

11. Multica v0.4.37 release (2026-08-31)

    Finding: Re-read 2026-10-09 via the GitHub API: the v0.4.37 body lists commit 9c8c7f0 "feat(mobile): enable native iPad support (#7793)". The live changelog entry ("Install Multica natively on iPad, in any screen orientation") could not be re-fetched (HTTP 403); it rests on the reviewer read.

    Locator

    Release body: commit 9c8c7f0 "feat(mobile): enable native iPad support (#7793)"

    Retrieved

    2026-11-07

    Source date

    2026-08-31

12. Multica mobile browser issue composer

    Finding: The shared issue view explicitly adapts its comment composer to phone-sized browser viewports via useIsMobile. The application is exposed through the web app as well as desktop clients.

    Locator

    useStickyComposer; apps/web browser application

    Retrieved

    2026-11-13

multica:ACC-02

The vendor website, the providers table and the install table each list 29 supported coding tools, including ZeroClaw, Muse Code, Devin CLI and ZCode. Multica launches and drives each tool CLI through a local daemon rather than embedding a harness. Custom runtime profiles must fit an existing protocol family. Multica v0.8.2 detects and invokes Antigravity through the installed agy binary, with optional binary-path and model overrides.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-11-10

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Pinned Multica source

Version

Live docs v0.8.1 (docs source at tag v0.8.1, commit b1ea927); protocol source at commit 8db6cfe Antigravity source pass: v0.8.2 (b7f8efcaae6c5f3273c0038252b5d10c81b41068).

• Documentation and source based; no run with two different tools was observed.
• Supported means Multica can invoke the CLI; the tool, its account and model access come from the user.
• Install docs set minimum versions for eleven tools (Antigravity 1.1.10, Claude Code 2.0.0, Codex 0.100.0, GitHub Copilot CLI 1.0.0, Grok 0.2.89, Qwen Code 0.20.0, MiniMax Code 0.1.2, OpenCode 1.1.54, Dim 0.3.10, Devin CLI 3000.3.22, ZeroClaw 0.8.0); Muse Code needs 1.4.10 or later. A tool below its minimum is not registered as a runtime.
• The user supplies the Antigravity CLI and account; the existing documented minimum CLI version remains applicable.

1. Multica homepage

   Finding: Re-read 2026-10-09: Names 26 coding tools including ZeroClaw. "Start free trial" button, no price list, "no artificial caps when you self-host", source-available wording. Dashboard mockup shows a "Cloud (Anthropic)" runtime, which the download page describes as not live.

   Locator

   Hero; Works with 20+ AI coding tools; Runtimes; Source available; FAQ

   Retrieved

   2026-10-09

2. AI coding tools comparison

   Finding: Re-read 2026-10-09: Supported tools table (25 CLIs). Model lists come from each runtime. QwenPaw and MiniMax Code do not accept a model chosen in Multica. No full provider list. Session resumption continues for tools marked as supporting it; MiniMax Code starts a fresh session. MCP is not read for Antigravity, GitHub Copilot CLI, DevEco Code or Pi.

   Locator

   Supported tools table; Model sources; Session resumption; MCP configuration; Skill injection

   Retrieved

   2026-10-09

3. Daemon and runtimes

   Finding: Re-read 2026-10-09: The daemon is the background process on one computer. A runtime is one computer plus one tool or custom profile. Code and tool credentials stay on the computer; the server stores issues, comments, run records and results. Runtimes offline more than 7 days with no bound agents are cleaned up. Default 20 runs per daemon and 6 per agent. Runtimes are private by default. Custom profiles must fit an existing protocol family; "A custom profile does not add a new communication protocol."

   Locator

   Daemon vs runtime; Execution location; Dispatch and online status; Concurrency limits; Private and public runtimes; Custom runtime profiles; Task runtime environment

   Retrieved

   2026-10-09

4. Install AI coding tools

   Finding: Re-read 2026-10-09: Sign in to each tool on its own machine; Multica never receives login tokens. "Supported" means Multica can invoke the CLI; it does not supply the tool account, subscription or model quota. The table lists 25 CLIs. Minimum versions for eight tools; below minimum the runtime is not registered.

   Locator

   Choose a tool; Sign in on your machine

   Retrieved

   2026-10-09

5. Tutorial

   Finding: Re-read 2026-10-09: walkthrough. The first agent uses Claude with Sonnet (line 60); the Engineer agent, created through Multica helper, uses Opus (line 85); Reviewer uses Codex with GPT-5.6 Sol in a fresh context and never edits code (line 208). The Engineer opens the PR using the GitHub CLI on the user's computer (line 95). Merging is requested in a comment. Merge-driven status is configurable: the GitHub integration docs say that after PRs merge the issue moves to Done by default or is left alone (github-integration, "After PRs merge, move the issue to"). A PR that references an issue identifier links automatically (line 107).

   Locator

   Prepare the site repository; Reviewer; Merge and close out; Form a squad; Automation

   Retrieved

   2026-10-09

6. CLI and Agent Daemon Guide

   Finding: Re-read 2026-10-09: Pinned CLI_AND_DAEMON.md (8db6cfe): runtime table with protocol families including ACP for several tools; MCP servers passed over ACP session/new and resume requests; MiniMax Code 0.1.2 has no session-loading capability; remote MCP transports depend on declared capability.

   Locator

   Supported Agents table lines 217-250; How It Works lines 251-258; per-tool launch notes lines 355-396

   Retrieved

   2026-10-09

7. Claude Code backend

   Finding: Re-read 2026-10-09: Pinned claude.go (8db6cfe): runs Claude Code with stream-json input and output and keeps stdin open after the first message. Passes --max-turns from the run MaxTurns option (line 1110).

   Locator

   Execute (lines 36-90); buildClaudeArgs lines 1060-1115

   Retrieved

   2026-10-09

8. Runtime cost estimation

   Finding: Re-read 2026-10-09: Pinned runtimes/utils.ts (8db6cfe): static MODEL_PRICING table of provider rates; estimateCost computes cost from token counts and can prefer per-turn prices.

   Locator

   MODEL_PRICING table lines 203-400; estimateCost

   Retrieved

   2026-10-09

9. Codex backend

   Finding: Re-read 2026-10-09: Pinned codex.go (8db6cfe): drives the Codex app-server subcommand and turn events, with turn-interrupt timeouts.

   Locator

   Comments at lines 44-58 (app-server subcommand and turn/started reporting)

   Retrieved

   2026-10-09

10. Multica v0.4.33 release (2026-08-24)

    Finding: Re-read 2026-10-09 via the GitHub API: v0.4.33 body lists "feat(agent): add ZeroClaw as a native ACP runtime (MUL-6511) (#7351)". ZeroClaw is shipped in this release.

    Locator

    Release body: commit 8a5a6adb "feat(agent): add ZeroClaw as a native ACP runtime (MUL-6511) (#7351)"

    Retrieved

    2026-10-09

    Source date

    2026-08-24

11. Multica homepage

    Finding: Homepage now names 29 coding tools, source-available internal self-hosting, a free-trial button with no numeric trial terms, and connected-computer execution. Self-hosted Qoder Cloud Agents is a separately configured remote runtime.

    Locator

    Hero; Works with 20+ AI coding tools; Runtimes; Source available; FAQ

    Retrieved

    2026-11-07

12. AI coding tools comparison (docs source, v0.8.1)

    Finding: Docs source behind multica.ai/docs/providers at v0.8.1 lists 29 tools, adding Muse Code, Devin CLI, ZCode and ZeroClaw to the table. QwenPaw, MiniMax Code and ZeroClaw take their model from their own configuration. Antigravity, GitHub Copilot CLI, DevEco Code, Muse Code and ZeroClaw do not read the agent MCP configuration; managed MCP for Pi needs Pi 0.99.0 or later. Dim and ZeroClaw have no skill injection path.

    Locator

    Supported tools table lines 22-52; Model sources line 72; MCP configuration lines 88-92

    Retrieved

    2026-11-07

    Source date

    2026-11-06

13. Install AI coding tools (docs source, v0.8.1)

    Finding: Docs source behind multica.ai/docs/install-agent-runtime at v0.8.1 lists 29 detected commands and minimum versions for 11 tools (Antigravity, Claude Code, Codex, Copilot, Grok, Qwen Code, MiniMax Code, OpenCode, Dim, Devin CLI, ZeroClaw); Muse Code needs 1.4.10 or later. Tools below minimum are not registered.

    Locator

    Choose a tool table lines 20-52; Minimum version table lines 67-79; Muse Code accordion

    Retrieved

    2026-11-07

    Source date

    2026-11-06

14. Multica Antigravity support at v0.8.2

    Finding: Multica v0.8.2 detects and invokes Antigravity through the installed agy binary, with optional binary-path and model overrides.

    Locator

    server/internal/daemon/agents_probe.go lines 260-272, v0.8.2, commit b7f8efcaae6c5f3273c0038252b5d10c81b41068

    Retrieved

    2026-11-10

    Source date

    2026-11-10

15. Multica Antigravity support at v0.8.2

    Finding: Multica v0.8.2 detects and invokes Antigravity through the installed agy binary, with optional binary-path and model overrides.

    Locator

    CLI_AND_DAEMON.md lines 268-280, v0.8.2, commit b7f8efcaae6c5f3273c0038252b5d10c81b41068

    Retrieved

    2026-11-10

    Source date

    2026-11-10

multica:ACC-03

Multica does not provide model access in the sources read: each coding tool uses the account, subscription or API key configured for that tool on the user's machine. Multica Cloud requires a Multica account (email code or Google); a self-hosted server has its own email-code sign-in and needs no Multica Cloud account.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Pinned Multica source

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Per-tool subscription support, local models and account switching were not established.
• Existing subscription support cannot be inferred from API-key support.

1. Runs

   Finding: Re-read 2026-10-09: States deferred, queued, dispatched, waiting_local_directory, running, completed, failed, cancelled. Runs can be stopped from the execution log while deferred, queued, starting, waiting or running. A status change does not stop an active run. Retry from the execution log invokes the original agent and keeps files and session when possible. No pause control. Failure reasons include agent_blocked and missing_config. Dispatched runs fail after 5 minutes. Heartbeat every 15 seconds. Automatic retries only for transient faults (2 attempts, 3 for network interruptions). Transcripts kept.

   Locator

   Execution lifecycle; Viewing run history; Failures and automatic retries; Manual retry; State and timeout quick reference

   Retrieved

   2026-11-07

2. Download Multica

   Finding: Downloads show macOS Apple Silicon/Intel, Windows x64/ARM64 and Linux x64/ARM64 installers; current v0.8.1. Vendor-hosted runtime remains not live, waitlist-only. It is separate from connecting Qoder Cloud Agents.

   Locator

   Choose your platform; Prefer the CLI?; Cloud runtime (waitlist); Current version

   Retrieved

   2026-11-07

3. AI coding tools comparison

   Finding: Current provider table documents local-tool account/model/MCP/skill differences; table demo says 28 while it also includes ZCode and homepage says 29. No universal account compatibility inferred from count.

   Locator

   Supported tools table; Model sources; Session resumption; MCP configuration; Skill injection

   Retrieved

   2026-11-07

4. Quickstart

   Finding: Web/Desktop sign-in uses email code or Google. Desktop connects a computer automatically; other computers install CLI and run setup. At least one installed/authenticated coding tool required; no bundled model quota.

   Locator

   Steps 1-5; Common problems

   Retrieved

   2026-11-07

5. Create and configure an agent

   Finding: Current agent config docs: custom_env stays plaintext in server database; owner/admin unlock/read/change is audited and list/detail APIs expose only an opaque count. Agent Access can only be changed by its owner. Runtime/model/thinking/MCP settings have separate scope.

   Locator

   Starting points; Runtime, model, and thinking level; Configuration after creation; Environment variables and credentials

   Retrieved

   2026-11-07

6. Self-host quickstart

   Finding: Re-read 2026-10-09: Self-hosting runs Web, API and PostgreSQL through Docker Compose; Kubernetes via Helm is referenced. No email service by default; codes are printed to backend logs until Resend or SMTP is set. Migrations are forward-only. "Self-hosting replaces only the Multica Cloud part."

   Locator

   Multica service and computer; make selfhost; Back up Postgres; Kubernetes

   Retrieved

   2026-11-07

7. Install AI coding tools

   Finding: Re-read 2026-10-09: Sign in to each tool on its own machine; Multica never receives login tokens. "Supported" means Multica can invoke the CLI; it does not supply the tool account, subscription or model quota. The table lists 25 CLIs. Minimum versions for eight tools; below minimum the runtime is not registered.

   Locator

   Choose a tool; Sign in on your machine

   Retrieved

   2026-11-07

8. Cloud billing types

   Finding: Re-read 2026-10-09: Pinned billing types (8db6cfe): credit wallet with 1 USD = 1000 credits, credit batches and top-up states. Header states a separate multica-cloud billing service. No public description of what credits purchase.

   Locator

   Header comment lines 1-12; BillingBatch; BillingTopup

   Retrieved

   2026-11-07

multica:ACC-04

Documented onboarding is: sign in, connect a computer with Desktop or multica setup, create an agent, assign the first issue. Local non-git directories, local git repositories and any reachable Git URL are supported as project resources; first-task time was not measured.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-10-09

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• No fresh-install test was run; steps are from documentation.
• Cloud runtime onboarding is not available (waitlist).

1. Download Multica

   Finding: Re-read 2026-10-09: Current version v0.6.1. Installers: macOS Apple Silicon and Intel (.dmg/.zip), Windows x64 and ARM64 (.exe), Linux x64 and ARM64 (.AppImage, .deb, .rpm). CLI install over SSH. Cloud runtime shown as waitlist, "Not live yet". No iOS, Android or minimum OS statement.

   Locator

   Choose your platform; Prefer the CLI?; Cloud runtime (waitlist); Current version

   Retrieved

   2026-10-09

2. Desktop app

   Finding: Re-read 2026-10-09: Installers: macOS (.dmg), Windows (.exe), Linux (.AppImage, .deb, .rpm). Desktop starts a built-in daemon after sign-in. Auto-update on by default. Self-hosted connection through desktop.json. No minimum OS version stated.

   Locator

   Installation; Built-in daemon; Updating Desktop; Connecting to a self-hosted instance

   Retrieved

   2026-10-09

3. Quickstart

   Finding: Re-read 2026-10-09: Sign in by email code or Google on web or Desktop. Connect a computer: Desktop registers it automatically; web uses an install script then multica setup. Create an agent, create an issue and submit. Common problems: offline runtime, "Keep Desktop open".

   Locator

   Steps 1-5; Common problems

   Retrieved

   2026-10-09

4. GitHub integration

   Finding: Re-read 2026-10-09: GitHub App is read-only and "never pushes commits, comments, or status checks". PRs auto-link by identifier in branch name or title, or with closing keywords in the body. PR card shows state, size, CI status and mergeability. Merging all linked PRs can move the issue to a chosen status. Optional Co-authored-by trailer "multica-agent <github@multica.ai>". No statement on who merges or on importing GitHub Issues, Linear or Jira.

   Locator

   Connect GitHub; Link a PR to an issue; View PRs on an issue; When merged PRs move an issue

   Retrieved

   2026-10-09

5. Project resources

   Finding: Re-read 2026-10-09: GitHub repositories are checked out per run through worktrees in a runtime-managed workspace. Local git directories run in place (serialized, directory lock) or in Parallel worktree mode on agent/<agent>/<issue> branches. Non-git directories run serially. Dependency caches, snapshots and port allocation are not mentioned.

   Locator

   Add a GitHub repository; Add a local directory; How runs share the directory

   Retrieved

   2026-10-09

6. Assign issues to agents

   Finding: Re-read 2026-10-09: Assignment starts a run unless the issue is in backlog or "Don't start yet" is chosen. Access options: Only me, Specific people, Entire workspace. "a run is bound to its runtime and never moves to another machine." CLI assign commands including --no-start.

   Locator

   Assign and start a run; Assign without starting; Assignment permissions; Use the CLI

   Retrieved

   2026-10-09

7. @-mention agents in comments

   Finding: Re-read 2026-10-09: Mentions and replies start runs; a trigger preview is shown before sending. Simultaneous mentions of different agents are not merged; consecutive comments to one agent merge into the pending run. Runs wait when the runtime is offline. Access settings apply to mentions. No presence indicators.

   Locator

   Trigger preview; Automatic routing of replies; Coalescing consecutive comments; Access restrictions

   Retrieved

   2026-10-09

8. Self-host quickstart

   Finding: Re-read 2026-10-09: Self-hosting runs Web, API and PostgreSQL through Docker Compose; Kubernetes via Helm is referenced. No email service by default; codes are printed to backend logs until Resend or SMTP is set. Migrations are forward-only. "Self-hosting replaces only the Multica Cloud part."

   Locator

   Multica service and computer; make selfhost; Back up Postgres; Kubernetes

   Retrieved

   2026-10-09

9. Install AI coding tools

   Finding: Re-read 2026-10-09: Sign in to each tool on its own machine; Multica never receives login tokens. "Supported" means Multica can invoke the CLI; it does not supply the tool account, subscription or model quota. The table lists 25 CLIs. Minimum versions for eight tools; below minimum the runtime is not registered.

   Locator

   Choose a tool; Sign in on your machine

   Retrieved

   2026-10-09

multica:ACC-05

The CLI exposes broad issue, agent, project, autopilot and runtime operations over the shared server API, authenticated by personal access tokens; a REST API is used in documentation but no general API reference or MCP server was found.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-10-09

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Pinned Multica source

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Public SDK and general REST API stability unknown; MCP server exposure not found.
• Deployed parity between source and hosted service was not tested.

1. Multica issue CLI

   Finding: Re-read 2026-10-09: Pinned source cmd_issue.go (8db6cfe): issue subcommands include list, get, pull-requests, children, create, update, assign, status, comment, runs, run-messages, usage, rerun, cancel-task and search; comment update requires --expected-revision; calls go through the shared server API.

   Locator

   issueCmd subcommands lines 222-456 (list/get/pull-requests/children/create/update/assign/status/comment/runs/usage/rerun/cancel-task/search); comment update --expected-revision lines 725 and 2584-2613

   Retrieved

   2026-10-09

2. Daemon and runtimes

   Finding: Re-read 2026-10-09: The daemon is the background process on one computer. A runtime is one computer plus one tool or custom profile. Code and tool credentials stay on the computer; the server stores issues, comments, run records and results. Runtimes offline more than 7 days with no bound agents are cleaned up. Default 20 runs per daemon and 6 per agent. Runtimes are private by default. Custom profiles must fit an existing protocol family; "A custom profile does not add a new communication protocol."

   Locator

   Daemon vs runtime; Execution location; Dispatch and online status; Concurrency limits; Private and public runtimes; Custom runtime profiles; Task runtime environment

   Retrieved

   2026-10-09

3. Using the CLI

   Finding: Re-read 2026-10-09: Commands cover issues, projects, labels, agents, skills, autopilots, workspaces, repos, daemon and runtimes. `multica issue cancel-task <task-id> --issue <issue-id>` cancels a run. `multica issue rerun <id>` re-enqueues for the current assignee. Install via curl script, Homebrew or PowerShell. `issue comment update` requires --expected-revision (source, cmd_issue.go).

   Locator

   Installation; First connection; Common issue operations; Command reference

   Retrieved

   2026-10-09

4. Autopilots

   Finding: Re-read 2026-10-09: Autopilots use 5-field cron with IANA time zones, several schedules per autopilot, and run-now. Webhook triggers (JSON up to 256 KiB, idempotency key, GitHub, GitLab and generic event inference, event filters, replay). Create-issue and run-only modes. Run-only failures are not retried and the next schedule still fires. Create-issue waits for an offline runtime; run-only is skipped. Manual pause stops schedules, webhooks and run-now. Automatic pause after at least 50 completed or failed runs in 7 days with a 90% failure rate. The page does not say whether runs can overlap.

   Locator

   Create; Execution mode; Run on a schedule; Run from a webhook; Failures, pausing, and deletion; Permissions

   Retrieved

   2026-10-09

5. Authentication and tokens

   Finding: Re-read 2026-10-09: Browser sessions last 30 days. Personal access tokens (mul_ prefix, 30 days, 90 days, 1 year or never) work against REST endpoints. multica login creates a 90-day token. Run-scoped mat_ tokens last at most 24 hours and attribute actions to the agent. No dedicated REST API reference.

   Locator

   Personal access tokens; Using a PAT in API requests; Temporary tokens for agent runs

   Retrieved

   2026-10-09

6. Feature flags

   Finding: Re-read 2026-10-09: Pinned featureflags/keys.go (8db6cfe): billing_workspace_subscriptions defaults to off and gates workspace entitlement, Stripe Checkout and seat reconcile; composio_mcp_apps, plugins_v1 and triage_v1 are other gates.

   Locator

   BillingWorkspaceSubscriptions, ComposioMCPApps, PluginsV1, TriageV1 (lines 8-60)

   Retrieved

   2026-10-09

7. Public API v1 (Plugin API)

   Finding: Re-read 2026-10-09: Pinned source publicapi/v1/openapi.yaml (8db6cfe): OpenAPI v1 covers plugin-token access to context, issues, comments and storage. It is a plugin contract, not a general REST reference.

   Locator

   servers; /issues/{issue_ref}; /issues/{issue_ref}/comments; /storage

   Retrieved

   2026-10-09

8. Plugin SDK README

   Finding: Re-read 2026-10-09: Pinned source plugin-sdk README (8db6cfe): plugin surfaces run in a sandboxed iframe with allow-scripts only; they read issues, post comments authored by the user without @-mention dispatch, and use scoped storage. Catalog gated by plugins_v1.

   Locator

   What a surface is; Publishing; What you can do, and what bounds it

   Retrieved

   2026-10-09

9. Multica GitHub issues

   Finding: Re-read 2026-10-09: GitHub searches on 2026-10-09 return 16 open Android results, 12 App Store results and 13 SSO results. Open community requests: #3864 and #3412 (Android), #6996 (mobile push), #7794 and #1218 (blocker dependencies), #6950 (spending limit), #5423 (Azure AAD), #4151 (open-source the hosted runtime). None is a vendor announcement. The repository reports 1,839 open issues and pull requests combined.

   Locator

   Searches 2026-10-08: Android, App Store, SSO/SAML, dependency/blocked-by, budget/spend limit, cloud runtime

   Retrieved

   2026-10-09

multica:ACC-06

Workspace owners/admins keep an MCP server library that is assigned per agent and passed to most supported tools; skills import from GitHub, ClawHub, Skills.sh, local archives or a connected computer. Setup is product-managed for MCP and skills, while some tools keep their own MCP configuration.

Checked

2026-10-09 · checked 1 month ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Live docs v0.8.1 (docs source at tag v0.8.1, commit b1ea927); feature flags at commit 8db6cfe

• No external-tool call and access boundary was verified.
• Custom tools beyond MCP and skills were not found.

1. Multica changelog

   Finding: Re-read 2026-10-09: Re-read first 100,000 of 188,543 characters (remainder not read). Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01). Dated entries cited in claims: v0.4.35 (2026-08-26) Pro-plan billing and seat management behind one Cloud address; v0.4.37 (2026-08-31) says Multica installs natively on iPad; v0.5.2 (2026-09-23) and v0.5.3 (2026-09-24) steering of Claude Code, Codex and Grok tasks; v0.5.1 (2026-09-21) issue wakeup rules; v0.6.0 (2026-09-28) wakeups on status change, sub-issue completion and pull request movement, plus add, queue or restart when replying. No dated forward-looking plans in the part read.

   Locator

   Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01); v0.5.1, v0.5.2, v0.6.0, v0.6.1 entries; v0.4.35, v0.4.34

   Retrieved

   2026-10-09

   Source date

   2026-10-01

2. AI coding tools comparison

   Finding: Re-read 2026-10-09: Supported tools table (25 CLIs). Model lists come from each runtime. QwenPaw and MiniMax Code do not accept a model chosen in Multica. No full provider list. Session resumption continues for tools marked as supporting it; MiniMax Code starts a fresh session. MCP is not read for Antigravity, GitHub Copilot CLI, DevEco Code or Pi.

   Locator

   Supported tools table; Model sources; Session resumption; MCP configuration; Skill injection

   Retrieved

   2026-10-09

3. Daemon and runtimes

   Finding: Re-read 2026-10-09: The daemon is the background process on one computer. A runtime is one computer plus one tool or custom profile. Code and tool credentials stay on the computer; the server stores issues, comments, run records and results. Runtimes offline more than 7 days with no bound agents are cleaned up. Default 20 runs per daemon and 6 per agent. Runtimes are private by default. Custom profiles must fit an existing protocol family; "A custom profile does not add a new communication protocol."

   Locator

   Daemon vs runtime; Execution location; Dispatch and online status; Concurrency limits; Private and public runtimes; Custom runtime profiles; Task runtime environment

   Retrieved

   2026-10-09

4. Using the CLI

   Finding: Re-read 2026-10-09: Commands cover issues, projects, labels, agents, skills, autopilots, workspaces, repos, daemon and runtimes. `multica issue cancel-task <task-id> --issue <issue-id>` cancels a run. `multica issue rerun <id>` re-enqueues for the current assignee. Install via curl script, Homebrew or PowerShell. `issue comment update` requires --expected-revision (source, cmd_issue.go).

   Locator

   Installation; First connection; Common issue operations; Command reference

   Retrieved

   2026-10-09

5. Create and configure an agent

   Finding: Re-read 2026-10-09: Agents start blank or with Build with AI (needs an online runtime). Runtime, model and thinking level. custom_env values are stored in plaintext in the Multica server database; only workspace owners and admins can view or change them. Critical variables such as PATH, HOME and MULTICA_* cannot be overridden.

   Locator

   Starting points; Runtime, model, and thinking level; Configuration after creation; Environment variables and credentials

   Retrieved

   2026-10-09

6. Skills

   Finding: Re-read 2026-10-09: Skills are SKILL.md bundles, created manually or imported from a local folder or archive, GitHub, ClawHub, Skills.sh, or copied from a connected runtime. Skills attach per agent; changes apply from the next run. No review or sandbox of imported content stated.

   Locator

   Creating or importing a skill; Updating an imported skill; Workspace skills and repository skills; Edit permissions

   Retrieved

   2026-10-09

7. Feature flags

   Finding: Re-read 2026-10-09: Pinned featureflags/keys.go (8db6cfe): billing_workspace_subscriptions defaults to off and gates workspace entitlement, Stripe Checkout and seat reconcile; composio_mcp_apps, plugins_v1 and triage_v1 are other gates.

   Locator

   BillingWorkspaceSubscriptions, ComposioMCPApps, PluginsV1, TriageV1 (lines 8-60)

   Retrieved

   2026-10-09

8. Multica coding tools

   Finding: Multica invokes installed signed-in coding tools, including Claude Code, Codex, Cursor Agent, Grok, OpenCode and Pi. MCP custom tools follow each runtime’s documented configuration support.

   Locator

   Supported tools; Model sources; MCP configuration

   Retrieved

   2026-11-07

9. AI coding tools comparison (docs source, v0.8.1)

   Finding: Docs source behind multica.ai/docs/providers at v0.8.1 lists 29 tools, adding Muse Code, Devin CLI, ZCode and ZeroClaw to the table. QwenPaw, MiniMax Code and ZeroClaw take their model from their own configuration. Antigravity, GitHub Copilot CLI, DevEco Code, Muse Code and ZeroClaw do not read the agent MCP configuration; managed MCP for Pi needs Pi 0.99.0 or later. Dim and ZeroClaw have no skill injection path.

   Locator

   Supported tools table lines 22-52; Model sources line 72; MCP configuration lines 88-92

   Retrieved

   2026-11-07

   Source date

   2026-11-06

multica:ACC-07

Desktop uses Electron; mobile docs specify React Native.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-10-09

Plan

Not specified in this finding

Surface

Pinned Multica source; Self-built iOS client

Availability

source only

Version

commit 8db6cfe

• Installed binary parity with the pinned source is unverified.
• Hybrid structure (shared web UI inside Electron) was not inspected.

1. Mobile app (iOS)

   Finding: Re-read 2026-10-09: The iOS client is "not on the App Store yet". Build a Release from the public repository on a Mac with Xcode and install over USB. Free Apple ID signing "only work for 7 days". The self-installed build does not auto-update. "There is no Android client yet." No iPad statement. No feature list.

   Locator

   Intro; Prerequisites; 7-day limit of free signing

   Retrieved

   2026-10-09

2. Desktop package

   Finding: Re-read 2026-10-09: Pinned source apps/desktop/package.json (8db6cfe): Electron ^39.2.6, electron-builder ^26.0.12, electron-vite ^5.0.0. The Desktop app is an Electron build.

   Locator

   dependencies: electron ^39.2.6, electron-builder ^26.0.12, electron-vite ^5.0.0 (lines 72-74)

   Retrieved

   2026-10-09

3. Mobile package

   Finding: Re-read 2026-10-09: Pinned source apps/mobile/package.json (8db6cfe): Expo ~55.0.23 and react-native 0.83.6; the mobile client is an Expo and React Native app.

   Locator

   dependencies expo ~55.0.23 (line 46), react-native 0.83.6 (line 68)

   Retrieved

   2026-10-09

multica:PLAN-01

Multica issues are the native record: issues are created in the app, CLI, chat bots or by prompting an agent. GitHub is linked only for pull requests, read-only; no import from Linear, GitHub Issues or Jira was found.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-10-09

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• External issue import, edit sync and round trips were not found; an open GitHub issues request exists (#8822).
• Documentation based; no intake scenario was run.

1. Issues

   Finding: Re-read 2026-10-09: Seven built-in statuses: backlog, todo, in_progress, in_review, done, blocked, cancelled. Sub-issues with stages and a parent completion notification. No dependency or blocked-by relation documented. Labels and priority described only briefly. When every linked PR merges, the issue moves to the workspace-chosen status, default done.

   Locator

   Parts of an issue; Choose an assignee; Status; Custom statuses; Projects and sub-issues; Switch views

   Retrieved

   2026-10-09

2. Quickstart

   Finding: Re-read 2026-10-09: Sign in by email code or Google on web or Desktop. Connect a computer: Desktop registers it automatically; web uses an install script then multica setup. Create an agent, create an issue and submit. Common problems: offline runtime, "Keep Desktop open".

   Locator

   Steps 1-5; Common problems

   Retrieved

   2026-10-09

3. Using the CLI

   Finding: Re-read 2026-10-09: Commands cover issues, projects, labels, agents, skills, autopilots, workspaces, repos, daemon and runtimes. `multica issue cancel-task <task-id> --issue <issue-id>` cancels a run. `multica issue rerun <id>` re-enqueues for the current assignee. Install via curl script, Homebrew or PowerShell. `issue comment update` requires --expected-revision (source, cmd_issue.go).

   Locator

   Installation; First connection; Common issue operations; Command reference

   Retrieved

   2026-10-09

4. Autopilots

   Finding: Re-read 2026-10-09: Autopilots use 5-field cron with IANA time zones, several schedules per autopilot, and run-now. Webhook triggers (JSON up to 256 KiB, idempotency key, GitHub, GitLab and generic event inference, event filters, replay). Create-issue and run-only modes. Run-only failures are not retried and the next schedule still fires. Create-issue waits for an offline runtime; run-only is skipped. Manual pause stops schedules, webhooks and run-now. Automatic pause after at least 50 completed or failed runs in 7 days with a 90% failure rate. The page does not say whether runs can overlap.

   Locator

   Create; Execution mode; Run on a schedule; Run from a webhook; Failures, pausing, and deletion; Permissions

   Retrieved

   2026-10-09

5. GitHub integration

   Finding: Re-read 2026-10-09: GitHub App is read-only and "never pushes commits, comments, or status checks". PRs auto-link by identifier in branch name or title, or with closing keywords in the body. PR card shows state, size, CI status and mergeability. Merging all linked PRs can move the issue to a chosen status. Optional Co-authored-by trailer "multica-agent <github@multica.ai>". No statement on who merges or on importing GitHub Issues, Linear or Jira.

   Locator

   Connect GitHub; Link a PR to an issue; View PRs on an issue; When merged PRs move an issue

   Retrieved

   2026-10-09

6. Chat with agents

   Finding: Re-read 2026-10-09: Private one-to-one chat with an agent outside issues. Attachments supported ("attach images or files"). Session continues where possible. Stopping a run restores unprocessed input to the editor. Offline runtime makes messages wait. No code search, indexing or retrieval statement.

   Locator

   Intro; Multi-turn context; Watch and stop a run

   Retrieved

   2026-10-09

7. Chat integrations

   Finding: Re-read 2026-10-09: Feishu/Lark, Slack, DingTalk, WeCom and Telegram. "New connections are currently open only for mainland-China Feishu." Account binding on first message; membership re-checked on every message.

   Locator

   Choose a platform; Account binding; Self-hosting

   Retrieved

   2026-10-09

8. Workspaces

   Finding: Re-read 2026-10-09: A workspace is the isolation boundary for members, issues, projects, agents, skills and run history. Owners and admins manage settings; members view them. Deletion is permanent. No export or portability statement. No SSO mention.

   Locator

   What a workspace contains; Delete a workspace

   Retrieved

   2026-10-09

9. Multica GitHub issues

   Finding: Re-read 2026-10-09: GitHub searches on 2026-10-09 return 16 open Android results, 12 App Store results and 13 SSO results. Open community requests: #3864 and #3412 (Android), #6996 (mobile push), #7794 and #1218 (blocker dependencies), #6950 (spending limit), #5423 (Azure AAD), #4151 (open-source the hosted runtime). None is a vendor announcement. The repository reports 1,839 open issues and pull requests combined.

   Locator

   Searches 2026-10-08: Android, App Store, SSO/SAML, dependency/blocked-by, budget/spend limit, cloud runtime

   Retrieved

   2026-10-09

multica:PLAN-02

Issues hold the task brief and requirements (description text, comments, attachments); no separate structured plan object or acceptance-criteria field was found in docs or the CLI.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-10-09

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• No test of amendment while running was executed.
• Editors for plans and acceptance criteria not found as a separate feature.

1. Issues

   Finding: Re-read 2026-10-09: Seven built-in statuses: backlog, todo, in_progress, in_review, done, blocked, cancelled. Sub-issues with stages and a parent completion notification. No dependency or blocked-by relation documented. Labels and priority described only briefly. When every linked PR merges, the issue moves to the workspace-chosen status, default done.

   Locator

   Parts of an issue; Choose an assignee; Status; Custom statuses; Projects and sub-issues; Switch views

   Retrieved

   2026-10-09

2. Runs

   Finding: Re-read 2026-10-09: States deferred, queued, dispatched, waiting_local_directory, running, completed, failed, cancelled. Runs can be stopped from the execution log while deferred, queued, starting, waiting or running. A status change does not stop an active run. Retry from the execution log invokes the original agent and keeps files and session when possible. No pause control. Failure reasons include agent_blocked and missing_config. Dispatched runs fail after 5 minutes. Heartbeat every 15 seconds. Automatic retries only for transient faults (2 attempts, 3 for network interruptions). Transcripts kept.

   Locator

   Execution lifecycle; Viewing run history; Failures and automatic retries; Manual retry; State and timeout quick reference

   Retrieved

   2026-10-09

3. Multica issue CLI

   Finding: Re-read 2026-10-09: Pinned source cmd_issue.go (8db6cfe): issue subcommands include list, get, pull-requests, children, create, update, assign, status, comment, runs, run-messages, usage, rerun, cancel-task and search; comment update requires --expected-revision; calls go through the shared server API.

   Locator

   issueCmd subcommands lines 222-456 (list/get/pull-requests/children/create/update/assign/status/comment/runs/usage/rerun/cancel-task/search); comment update --expected-revision lines 725 and 2584-2613

   Retrieved

   2026-10-09

4. Issue handler

   Finding: Re-read 2026-10-09: Pinned source internal/handler/issue.go (8db6cfe): the issue response carries parent_issue_id, stage, revision, custom properties and status; status keys resolve against the workspace status catalog.

   Locator

   IssueResponse DTO lines 40-90 (status, parent_issue_id, stage, revision, properties); status key resolution via workspace catalog lines 185-200

   Retrieved

   2026-10-09

5. Multica changelog

   Finding: Re-read 2026-10-09: Re-read first 100,000 of 188,543 characters (remainder not read). Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01). Dated entries cited in claims: v0.4.35 (2026-08-26) Pro-plan billing and seat management behind one Cloud address; v0.4.37 (2026-08-31) says Multica installs natively on iPad; v0.5.2 (2026-09-23) and v0.5.3 (2026-09-24) steering of Claude Code, Codex and Grok tasks; v0.5.1 (2026-09-21) issue wakeup rules; v0.6.0 (2026-09-28) wakeups on status change, sub-issue completion and pull request movement, plus add, queue or restart when replying. No dated forward-looking plans in the part read.

   Locator

   Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01); v0.5.1, v0.5.2, v0.6.0, v0.6.1 entries; v0.4.35, v0.4.34

   Retrieved

   2026-10-09

   Source date

   2026-10-01

6. GitHub integration

   Finding: Re-read 2026-10-09: GitHub App is read-only and "never pushes commits, comments, or status checks". PRs auto-link by identifier in branch name or title, or with closing keywords in the body. PR card shows state, size, CI status and mergeability. Merging all linked PRs can move the issue to a chosen status. Optional Co-authored-by trailer "multica-agent <github@multica.ai>". No statement on who merges or on importing GitHub Issues, Linear or Jira.

   Locator

   Connect GitHub; Link a PR to an issue; View PRs on an issue; When merged PRs move an issue

   Retrieved

   2026-10-09

7. @-mention agents in comments

   Finding: Re-read 2026-10-09: Mentions and replies start runs; a trigger preview is shown before sending. Simultaneous mentions of different agents are not merged; consecutive comments to one agent merge into the pending run. Runs wait when the runtime is offline. Access settings apply to mentions. No presence indicators.

   Locator

   Trigger preview; Automatic routing of replies; Coalescing consecutive comments; Access restrictions

   Retrieved

   2026-10-09

8. Issue timeline

   Finding: Re-read 2026-10-09: Pinned source internal/handler/activity.go (8db6cfe): the issue timeline interleaves activity and comments with durable actor_type and actor_id attribution; deleted thread roots keep a tombstone.

   Locator

   TimelineEntry lines 14-50

   Retrieved

   2026-10-09

multica:PLAN-03

Issues have parent-child relationships.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Blocker dependencies are not documented and no CLI command uses them; open requests #7794 and #1218 ask for blocked_by with dispatch admission.
• Dependency enforcement, readiness and identity retention while growing a task were not tested.

1. Issues

   Finding: Re-read 2026-10-09: Seven built-in statuses: backlog, todo, in_progress, in_review, done, blocked, cancelled. Sub-issues with stages and a parent completion notification. No dependency or blocked-by relation documented. Labels and priority described only briefly. When every linked PR merges, the issue moves to the workspace-chosen status, default done.

   Locator

   Parts of an issue; Choose an assignee; Status; Custom statuses; Projects and sub-issues; Switch views

   Retrieved

   2026-10-09

2. Issue handler

   Finding: Re-read 2026-10-09: Pinned source internal/handler/issue.go (8db6cfe): the issue response carries parent_issue_id, stage, revision, custom properties and status; status keys resolve against the workspace status catalog.

   Locator

   IssueResponse DTO lines 40-90 (status, parent_issue_id, stage, revision, properties); status key resolution via workspace catalog lines 185-200

   Retrieved

   2026-10-09

3. Multica changelog

   Finding: Re-read 2026-10-09: Re-read first 100,000 of 188,543 characters (remainder not read). Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01). Dated entries cited in claims: v0.4.35 (2026-08-26) Pro-plan billing and seat management behind one Cloud address; v0.4.37 (2026-08-31) says Multica installs natively on iPad; v0.5.2 (2026-09-23) and v0.5.3 (2026-09-24) steering of Claude Code, Codex and Grok tasks; v0.5.1 (2026-09-21) issue wakeup rules; v0.6.0 (2026-09-28) wakeups on status change, sub-issue completion and pull request movement, plus add, queue or restart when replying. No dated forward-looking plans in the part read.

   Locator

   Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01); v0.5.1, v0.5.2, v0.6.0, v0.6.1 entries; v0.4.35, v0.4.34

   Retrieved

   2026-10-09

   Source date

   2026-10-01

4. Projects

   Finding: Re-read 2026-10-09: Projects group issues (one project per issue) with status, priority, lead, dates, description and resources. The description enters agent execution context. Lead is not a permission and does not auto-assign or run agents. No code search or indexing statement.

   Locator

   Parts of a project; Project description and execution context; Project lead

   Retrieved

   2026-10-09

5. Multica GitHub issues

   Finding: Re-read 2026-10-09: GitHub searches on 2026-10-09 return 16 open Android results, 12 App Store results and 13 SSO results. Open community requests: #3864 and #3412 (Android), #6996 (mobile push), #7794 and #1218 (blocker dependencies), #6950 (spending limit), #5423 (Azure AAD), #4151 (open-source the hosted runtime). None is a vendor announcement. The repository reports 1,839 open issues and pull requests combined.

   Locator

   Searches 2026-10-08: Android, App Store, SSO/SAML, dependency/blocked-by, budget/spend limit, cloud runtime

   Retrieved

   2026-10-09

6. Multica workflows

   Finding: Workflow columns can hand issues to an agent or person, define the next state after completion and a send-back path. Blocked is reserved for outside obstacles.

   Locator

   Agent steps; Human steps; Handoffs

   Retrieved

   2026-11-07

multica:PLAN-04

Agent instructions, workspace context, project descriptions and reusable skills provide shared context; sessions resume where the tool supports it. No managed cross-harness memory or stale-context controls were found.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Managed memory across sessions or harnesses was not found; tool-native memory is the tool's.
• No new-session or colleague takeover test was run.

1. Runs

   Finding: Re-read 2026-10-09: States deferred, queued, dispatched, waiting_local_directory, running, completed, failed, cancelled. Runs can be stopped from the execution log while deferred, queued, starting, waiting or running. A status change does not stop an active run. Retry from the execution log invokes the original agent and keeps files and session when possible. No pause control. Failure reasons include agent_blocked and missing_config. Dispatched runs fail after 5 minutes. Heartbeat every 15 seconds. Automatic retries only for transient faults (2 attempts, 3 for network interruptions). Transcripts kept.

   Locator

   Execution lifecycle; Viewing run history; Failures and automatic retries; Manual retry; State and timeout quick reference

   Retrieved

   2026-10-09

2. AI coding tools comparison

   Finding: Re-read 2026-10-09: Supported tools table (25 CLIs). Model lists come from each runtime. QwenPaw and MiniMax Code do not accept a model chosen in Multica. No full provider list. Session resumption continues for tools marked as supporting it; MiniMax Code starts a fresh session. MCP is not read for Antigravity, GitHub Copilot CLI, DevEco Code or Pi.

   Locator

   Supported tools table; Model sources; Session resumption; MCP configuration; Skill injection

   Retrieved

   2026-10-09

3. Agents

   Finding: Re-read 2026-10-09: Agent settings: name, instructions, skills, runtime, model and thinking level, Access (Only me default, Specific people, Entire workspace), concurrency, env, MCP. Availability comes from the runtime and workload from runs. Archiving cancels unfinished runs.

   Locator

   Agent configuration; Permissions and Access; Online, offline, and workload status

   Retrieved

   2026-10-09

4. Skills

   Finding: Re-read 2026-10-09: Skills are SKILL.md bundles, created manually or imported from a local folder or archive, GitHub, ClawHub, Skills.sh, or copied from a connected runtime. Skills attach per agent; changes apply from the next run. No review or sandbox of imported content stated.

   Locator

   Creating or importing a skill; Updating an imported skill; Workspace skills and repository skills; Edit permissions

   Retrieved

   2026-10-09

5. Projects

   Finding: Re-read 2026-10-09: Projects group issues (one project per issue) with status, priority, lead, dates, description and resources. The description enters agent execution context. Lead is not a permission and does not auto-assign or run agents. No code search or indexing statement.

   Locator

   Parts of a project; Project description and execution context; Project lead

   Retrieved

   2026-10-09

6. Chat with agents

   Finding: Re-read 2026-10-09: Private one-to-one chat with an agent outside issues. Attachments supported ("attach images or files"). Session continues where possible. Stopping a run restores unprocessed input to the editor. Offline runtime makes messages wait. No code search, indexing or retrieval statement.

   Locator

   Intro; Multi-turn context; Watch and stop a run

   Retrieved

   2026-10-09

7. Workspaces

   Finding: Re-read 2026-10-09: A workspace is the isolation boundary for members, issues, projects, agents, skills and run history. Owners and admins manage settings; members view them. Deletion is permanent. No export or portability statement. No SSO mention.

   Locator

   What a workspace contains; Delete a workspace

   Retrieved

   2026-10-09

8. Multica daemon and runtimes

   Finding: Codex native memory is off by default per run and can be enabled with MULTICA_CODEX_MEMORY. Hermes memory is per agent with a 90-day unused retention policy.

   Locator

   Codex native memory; Sessions, memory and temporary directories

   Retrieved

   2026-11-07

multica:PLAN-05

Multica passes attachments and chat media to agents but no product-level code search, indexing, architecture retrieval or conflict detection was found; code understanding comes from the underlying coding tool.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-10-09

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Everything except multimodal inputs was not established; no architecture-conflict scenario was run.

1. Multica changelog

   Finding: Re-read 2026-10-09: Re-read first 100,000 of 188,543 characters (remainder not read). Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01). Dated entries cited in claims: v0.4.35 (2026-08-26) Pro-plan billing and seat management behind one Cloud address; v0.4.37 (2026-08-31) says Multica installs natively on iPad; v0.5.2 (2026-09-23) and v0.5.3 (2026-09-24) steering of Claude Code, Codex and Grok tasks; v0.5.1 (2026-09-21) issue wakeup rules; v0.6.0 (2026-09-28) wakeups on status change, sub-issue completion and pull request movement, plus add, queue or restart when replying. No dated forward-looking plans in the part read.

   Locator

   Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01); v0.5.1, v0.5.2, v0.6.0, v0.6.1 entries; v0.4.35, v0.4.34

   Retrieved

   2026-10-09

   Source date

   2026-10-01

2. Chat with agents

   Finding: Re-read 2026-10-09: Private one-to-one chat with an agent outside issues. Attachments supported ("attach images or files"). Session continues where possible. Stopping a run restores unprocessed input to the editor. Offline runtime makes messages wait. No code search, indexing or retrieval statement.

   Locator

   Intro; Multi-turn context; Watch and stop a run

   Retrieved

   2026-10-09

3. Chat integrations

   Finding: Re-read 2026-10-09: Feishu/Lark, Slack, DingTalk, WeCom and Telegram. "New connections are currently open only for mainland-China Feishu." Account binding on first message; membership re-checked on every message.

   Locator

   Choose a platform; Account binding; Self-hosting

   Retrieved

   2026-10-09

multica:PLAN-06

Native issues include creation, editing, comments, priority, labels, assignment, search, filters, projects, five views, backlog parking and explicit dispatch with separate retained runs.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-10-09

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Custom unstarted statuses do not inherit backlog suppression.
• Issue archive was not found (deletion is permanent; cancelled keeps the record); the full save-refine-dispatch scenario with a second person was not run.

1. Issues

   Finding: Re-read 2026-10-09: Seven built-in statuses: backlog, todo, in_progress, in_review, done, blocked, cancelled. Sub-issues with stages and a parent completion notification. No dependency or blocked-by relation documented. Labels and priority described only briefly. When every linked PR merges, the issue moves to the workspace-chosen status, default done.

   Locator

   Parts of an issue; Choose an assignee; Status; Custom statuses; Projects and sub-issues; Switch views

   Retrieved

   2026-10-09

2. Runs

   Finding: Re-read 2026-10-09: States deferred, queued, dispatched, waiting_local_directory, running, completed, failed, cancelled. Runs can be stopped from the execution log while deferred, queued, starting, waiting or running. A status change does not stop an active run. Retry from the execution log invokes the original agent and keeps files and session when possible. No pause control. Failure reasons include agent_blocked and missing_config. Dispatched runs fail after 5 minutes. Heartbeat every 15 seconds. Automatic retries only for transient faults (2 attempts, 3 for network interruptions). Transcripts kept.

   Locator

   Execution lifecycle; Viewing run history; Failures and automatic retries; Manual retry; State and timeout quick reference

   Retrieved

   2026-10-09

3. Multica issue CLI

   Finding: Re-read 2026-10-09: Pinned source cmd_issue.go (8db6cfe): issue subcommands include list, get, pull-requests, children, create, update, assign, status, comment, runs, run-messages, usage, rerun, cancel-task and search; comment update requires --expected-revision; calls go through the shared server API.

   Locator

   issueCmd subcommands lines 222-456 (list/get/pull-requests/children/create/update/assign/status/comment/runs/usage/rerun/cancel-task/search); comment update --expected-revision lines 725 and 2584-2613

   Retrieved

   2026-10-09

4. Multica changelog

   Finding: Re-read 2026-10-09: Re-read first 100,000 of 188,543 characters (remainder not read). Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01). Dated entries cited in claims: v0.4.35 (2026-08-26) Pro-plan billing and seat management behind one Cloud address; v0.4.37 (2026-08-31) says Multica installs natively on iPad; v0.5.2 (2026-09-23) and v0.5.3 (2026-09-24) steering of Claude Code, Codex and Grok tasks; v0.5.1 (2026-09-21) issue wakeup rules; v0.6.0 (2026-09-28) wakeups on status change, sub-issue completion and pull request movement, plus add, queue or restart when replying. No dated forward-looking plans in the part read.

   Locator

   Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01); v0.5.1, v0.5.2, v0.6.0, v0.6.1 entries; v0.4.35, v0.4.34

   Retrieved

   2026-10-09

   Source date

   2026-10-01

5. Using the CLI

   Finding: Re-read 2026-10-09: Commands cover issues, projects, labels, agents, skills, autopilots, workspaces, repos, daemon and runtimes. `multica issue cancel-task <task-id> --issue <issue-id>` cancels a run. `multica issue rerun <id>` re-enqueues for the current assignee. Install via curl script, Homebrew or PowerShell. `issue comment update` requires --expected-revision (source, cmd_issue.go).

   Locator

   Installation; First connection; Common issue operations; Command reference

   Retrieved

   2026-10-09

6. GitHub integration

   Finding: Re-read 2026-10-09: GitHub App is read-only and "never pushes commits, comments, or status checks". PRs auto-link by identifier in branch name or title, or with closing keywords in the body. PR card shows state, size, CI status and mergeability. Merging all linked PRs can move the issue to a chosen status. Optional Co-authored-by trailer "multica-agent <github@multica.ai>". No statement on who merges or on importing GitHub Issues, Linear or Jira.

   Locator

   Connect GitHub; Link a PR to an issue; View PRs on an issue; When merged PRs move an issue

   Retrieved

   2026-10-09

7. Projects

   Finding: Re-read 2026-10-09: Projects group issues (one project per issue) with status, priority, lead, dates, description and resources. The description enters agent execution context. Lead is not a permission and does not auto-assign or run agents. No code search or indexing statement.

   Locator

   Parts of a project; Project description and execution context; Project lead

   Retrieved

   2026-10-09

8. Assign issues to agents

   Finding: Re-read 2026-10-09: Assignment starts a run unless the issue is in backlog or "Don't start yet" is chosen. Access options: Only me, Specific people, Entire workspace. "a run is bound to its runtime and never moves to another machine." CLI assign commands including --no-start.

   Locator

   Assign and start a run; Assign without starting; Assignment permissions; Use the CLI

   Retrieved

   2026-10-09

9. Comments

   Finding: Re-read 2026-10-09: Threaded comments with attachments, annotations, resolve or conclusion, mentions and reactions. Authors edit or delete their own comments; owners and admins edit or delete anyone's; agent-posted comments can only be deleted. Deletion is permanent. Drafts expire after 30 days. Retention and export not stated.

   Locator

   Post comments; Annotate; Resolve a discussion; @-mentions; Edit and delete

   Retrieved

   2026-10-09

multica:PLAN-07

Agents use CLI against shared issue records.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-10-09

Plan

Not specified in this finding

Surface

Pinned Multica source; Multica Cloud/web/desktop

Availability

source only

Version

commit 8db6cfe; v0.6.1

• Claiming work and dependency creation by agents were not found.
• Issue-wide locking and permission end-to-end tests remain open.

1. Issues

   Finding: Re-read 2026-10-09: Seven built-in statuses: backlog, todo, in_progress, in_review, done, blocked, cancelled. Sub-issues with stages and a parent completion notification. No dependency or blocked-by relation documented. Labels and priority described only briefly. When every linked PR merges, the issue moves to the workspace-chosen status, default done.

   Locator

   Parts of an issue; Choose an assignee; Status; Custom statuses; Projects and sub-issues; Switch views

   Retrieved

   2026-10-09

2. Multica issue CLI

   Finding: Re-read 2026-10-09: Pinned source cmd_issue.go (8db6cfe): issue subcommands include list, get, pull-requests, children, create, update, assign, status, comment, runs, run-messages, usage, rerun, cancel-task and search; comment update requires --expected-revision; calls go through the shared server API.

   Locator

   issueCmd subcommands lines 222-456 (list/get/pull-requests/children/create/update/assign/status/comment/runs/usage/rerun/cancel-task/search); comment update --expected-revision lines 725 and 2584-2613

   Retrieved

   2026-10-09

3. Issue handler

   Finding: Re-read 2026-10-09: Pinned source internal/handler/issue.go (8db6cfe): the issue response carries parent_issue_id, stage, revision, custom properties and status; status keys resolve against the workspace status catalog.

   Locator

   IssueResponse DTO lines 40-90 (status, parent_issue_id, stage, revision, properties); status key resolution via workspace catalog lines 185-200

   Retrieved

   2026-10-09

4. Daemon and runtimes

   Finding: Re-read 2026-10-09: The daemon is the background process on one computer. A runtime is one computer plus one tool or custom profile. Code and tool credentials stay on the computer; the server stores issues, comments, run records and results. Runtimes offline more than 7 days with no bound agents are cleaned up. Default 20 runs per daemon and 6 per agent. Runtimes are private by default. Custom profiles must fit an existing protocol family; "A custom profile does not add a new communication protocol."

   Locator

   Daemon vs runtime; Execution location; Dispatch and online status; Concurrency limits; Private and public runtimes; Custom runtime profiles; Task runtime environment

   Retrieved

   2026-10-09

5. Using the CLI

   Finding: Re-read 2026-10-09: Commands cover issues, projects, labels, agents, skills, autopilots, workspaces, repos, daemon and runtimes. `multica issue cancel-task <task-id> --issue <issue-id>` cancels a run. `multica issue rerun <id>` re-enqueues for the current assignee. Install via curl script, Homebrew or PowerShell. `issue comment update` requires --expected-revision (source, cmd_issue.go).

   Locator

   Installation; First connection; Common issue operations; Command reference

   Retrieved

   2026-10-09

6. Assign issues to agents

   Finding: Re-read 2026-10-09: Assignment starts a run unless the issue is in backlog or "Don't start yet" is chosen. Access options: Only me, Specific people, Entire workspace. "a run is bound to its runtime and never moves to another machine." CLI assign commands including --no-start.

   Locator

   Assign and start a run; Assign without starting; Assignment permissions; Use the CLI

   Retrieved

   2026-10-09

7. Authentication and tokens

   Finding: Re-read 2026-10-09: Browser sessions last 30 days. Personal access tokens (mul_ prefix, 30 days, 90 days, 1 year or never) work against REST endpoints. multica login creates a 90-day token. Run-scoped mat_ tokens last at most 24 hours and attribute actions to the agent. No dedicated REST API reference.

   Locator

   Personal access tokens; Using a PAT in API requests; Temporary tokens for agent runs

   Retrieved

   2026-10-09

8. Issue timeline

   Finding: Re-read 2026-10-09: Pinned source internal/handler/activity.go (8db6cfe): the issue timeline interleaves activity and comments with durable actor_type and actor_id attribution; deleted thread roots keep a tombstone.

   Locator

   TimelineEntry lines 14-50

   Retrieved

   2026-10-09

multica:PLAN-08

Issue descriptions can hold persistent requirements editable by people and agents. A dedicated living specification, revision approval and drift checking remain unestablished.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

Multica docs and v0.8.1 documentation inspected 2026-11-07

• Requirements live in issue descriptions; specification revision history, code links and drift detection are not established.

1. Multica issue CLI

   Finding: Re-read 2026-10-09: Pinned source cmd_issue.go (8db6cfe): issue subcommands include list, get, pull-requests, children, create, update, assign, status, comment, runs, run-messages, usage, rerun, cancel-task and search; comment update requires --expected-revision; calls go through the shared server API.

   Locator

   issueCmd subcommands lines 222-456 (list/get/pull-requests/children/create/update/assign/status/comment/runs/usage/rerun/cancel-task/search); comment update --expected-revision lines 725 and 2584-2613

   Retrieved

   2026-11-07

2. Multica issues

   Finding: An issue description contains goals, requirements and acceptance criteria; discussions, state changes and execution history remain with the issue.

   Locator

   Parts of an issue; Create an issue

   Retrieved

   2026-11-07

multica:COORD-01

Multiple runs execute concurrently on a daemon (default 20 per daemon and 6 per agent) and work state is visible in the agent list, issue execution log, header chip and runtime page.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-10-09

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Observed concurrency was not tested; squads do not raise concurrency by themselves.

1. Runs

   Finding: Re-read 2026-10-09: States deferred, queued, dispatched, waiting_local_directory, running, completed, failed, cancelled. Runs can be stopped from the execution log while deferred, queued, starting, waiting or running. A status change does not stop an active run. Retry from the execution log invokes the original agent and keeps files and session when possible. No pause control. Failure reasons include agent_blocked and missing_config. Dispatched runs fail after 5 minutes. Heartbeat every 15 seconds. Automatic retries only for transient faults (2 attempts, 3 for network interruptions). Transcripts kept.

   Locator

   Execution lifecycle; Viewing run history; Failures and automatic retries; Manual retry; State and timeout quick reference

   Retrieved

   2026-10-09

2. Daemon and runtimes

   Finding: Re-read 2026-10-09: The daemon is the background process on one computer. A runtime is one computer plus one tool or custom profile. Code and tool credentials stay on the computer; the server stores issues, comments, run records and results. Runtimes offline more than 7 days with no bound agents are cleaned up. Default 20 runs per daemon and 6 per agent. Runtimes are private by default. Custom profiles must fit an existing protocol family; "A custom profile does not add a new communication protocol."

   Locator

   Daemon vs runtime; Execution location; Dispatch and online status; Concurrency limits; Private and public runtimes; Custom runtime profiles; Task runtime environment

   Retrieved

   2026-10-09

3. Squads

   Finding: Re-read 2026-10-09: Assignment to a squad wakes only the leader, which @-mentions members, records an evaluation and stops. The leader is woken again when a delegated member replies, a non-member comments or a member posts progress without a mention. Members can be agents or humans. Provider-native subagents are not described.

   Locator

   Squad composition; Execution flow after assignment; Leader re-trigger rules

   Retrieved

   2026-10-09

4. Agents

   Finding: Re-read 2026-10-09: Agent settings: name, instructions, skills, runtime, model and thinking level, Access (Only me default, Specific people, Entire workspace), concurrency, env, MCP. Availability comes from the runtime and workload from runs. Archiving cancels unfinished runs.

   Locator

   Agent configuration; Permissions and Access; Online, offline, and workload status

   Retrieved

   2026-10-09

5. Create and configure an agent

   Finding: Re-read 2026-10-09: Agents start blank or with Build with AI (needs an online runtime). Runtime, model and thinking level. custom_env values are stored in plaintext in the Multica server database; only workspace owners and admins can view or change them. Critical variables such as PATH, HOME and MULTICA_* cannot be overridden.

   Locator

   Starting points; Runtime, model, and thinking level; Configuration after creation; Environment variables and credentials

   Retrieved

   2026-10-09

6. Environment variables

   Finding: Re-read 2026-10-09: Telemetry on by default: one anonymous self-host snapshot per UTC day; DO_NOT_TRACK=1 or true disables it; ANALYTICS_DISABLED=true turns off PostHog. MULTICA_DAEMON_MAX_CONCURRENT_TASKS default 20. MULTICA_AGENT_TIMEOUT default 0 (no limit). MULTICA_AGENT_IDLE_WATCHDOG default 2h; tool watchdog same by default. No iteration limit variable listed. Optional server-side LLM for chat titles sends chat content to a configured endpoint.

   Locator

   Daemon configuration; Observability and analytics; Server-side LLM

   Retrieved

   2026-10-09

multica:COORD-02

Issues can be assigned to members, agents or squads; runs queue for a runtime and are claimed by it; consecutive triggers coalesce and a local directory lock can defer execution.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-10-09

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Concurrent duplicate-claim behavior not tested.

1. Issues

   Finding: Re-read 2026-10-09: Seven built-in statuses: backlog, todo, in_progress, in_review, done, blocked, cancelled. Sub-issues with stages and a parent completion notification. No dependency or blocked-by relation documented. Labels and priority described only briefly. When every linked PR merges, the issue moves to the workspace-chosen status, default done.

   Locator

   Parts of an issue; Choose an assignee; Status; Custom statuses; Projects and sub-issues; Switch views

   Retrieved

   2026-10-09

2. Runs

   Finding: Re-read 2026-10-09: States deferred, queued, dispatched, waiting_local_directory, running, completed, failed, cancelled. Runs can be stopped from the execution log while deferred, queued, starting, waiting or running. A status change does not stop an active run. Retry from the execution log invokes the original agent and keeps files and session when possible. No pause control. Failure reasons include agent_blocked and missing_config. Dispatched runs fail after 5 minutes. Heartbeat every 15 seconds. Automatic retries only for transient faults (2 attempts, 3 for network interruptions). Transcripts kept.

   Locator

   Execution lifecycle; Viewing run history; Failures and automatic retries; Manual retry; State and timeout quick reference

   Retrieved

   2026-10-09

3. Daemon and runtimes

   Finding: Re-read 2026-10-09: The daemon is the background process on one computer. A runtime is one computer plus one tool or custom profile. Code and tool credentials stay on the computer; the server stores issues, comments, run records and results. Runtimes offline more than 7 days with no bound agents are cleaned up. Default 20 runs per daemon and 6 per agent. Runtimes are private by default. Custom profiles must fit an existing protocol family; "A custom profile does not add a new communication protocol."

   Locator

   Daemon vs runtime; Execution location; Dispatch and online status; Concurrency limits; Private and public runtimes; Custom runtime profiles; Task runtime environment

   Retrieved

   2026-10-09

4. Squads

   Finding: Re-read 2026-10-09: Assignment to a squad wakes only the leader, which @-mentions members, records an evaluation and stops. The leader is woken again when a delegated member replies, a non-member comments or a member posts progress without a mention. Members can be agents or humans. Provider-native subagents are not described.

   Locator

   Squad composition; Execution flow after assignment; Leader re-trigger rules

   Retrieved

   2026-10-09

5. Agents

   Finding: Re-read 2026-10-09: Agent settings: name, instructions, skills, runtime, model and thinking level, Access (Only me default, Specific people, Entire workspace), concurrency, env, MCP. Availability comes from the runtime and workload from runs. Archiving cancels unfinished runs.

   Locator

   Agent configuration; Permissions and Access; Online, offline, and workload status

   Retrieved

   2026-10-09

6. Project resources

   Finding: Re-read 2026-10-09: GitHub repositories are checked out per run through worktrees in a runtime-managed workspace. Local git directories run in place (serialized, directory lock) or in Parallel worktree mode on agent/<agent>/<issue> branches. Non-git directories run serially. Dependency caches, snapshots and port allocation are not mentioned.

   Locator

   Add a GitHub repository; Add a local directory; How runs share the directory

   Retrieved

   2026-10-09

7. Assign issues to agents

   Finding: Re-read 2026-10-09: Assignment starts a run unless the issue is in backlog or "Don't start yet" is chosen. Access options: Only me, Specific people, Entire workspace. "a run is bound to its runtime and never moves to another machine." CLI assign commands including --no-start.

   Locator

   Assign and start a run; Assign without starting; Assignment permissions; Use the CLI

   Retrieved

   2026-10-09

8. @-mention agents in comments

   Finding: Re-read 2026-10-09: Mentions and replies start runs; a trigger preview is shown before sending. Simultaneous mentions of different agents are not merged; consecutive comments to one agent merge into the pending run. Runs wait when the runtime is offline. Access settings apply to mentions. No presence indicators.

   Locator

   Trigger preview; Automatic routing of replies; Coalescing consecutive comments; Access restrictions

   Retrieved

   2026-10-09

multica:COORD-03

Squads provide product-owned delegation: an agent leader receives the issue, @-mentions member agents, records an evaluation, and is re-triggered by replies; members can run on different tools. No provider-native subagent claims were evaluated.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Child identity, live progress and reopen behavior were not observed; invocation specifics beyond mention markdown not tested.

1. Runs

   Finding: Re-read 2026-10-09: States deferred, queued, dispatched, waiting_local_directory, running, completed, failed, cancelled. Runs can be stopped from the execution log while deferred, queued, starting, waiting or running. A status change does not stop an active run. Retry from the execution log invokes the original agent and keeps files and session when possible. No pause control. Failure reasons include agent_blocked and missing_config. Dispatched runs fail after 5 minutes. Heartbeat every 15 seconds. Automatic retries only for transient faults (2 attempts, 3 for network interruptions). Transcripts kept.

   Locator

   Execution lifecycle; Viewing run history; Failures and automatic retries; Manual retry; State and timeout quick reference

   Retrieved

   2026-10-09

2. Multica changelog

   Finding: Re-read 2026-10-09: Re-read first 100,000 of 188,543 characters (remainder not read). Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01). Dated entries cited in claims: v0.4.35 (2026-08-26) Pro-plan billing and seat management behind one Cloud address; v0.4.37 (2026-08-31) says Multica installs natively on iPad; v0.5.2 (2026-09-23) and v0.5.3 (2026-09-24) steering of Claude Code, Codex and Grok tasks; v0.5.1 (2026-09-21) issue wakeup rules; v0.6.0 (2026-09-28) wakeups on status change, sub-issue completion and pull request movement, plus add, queue or restart when replying. No dated forward-looking plans in the part read.

   Locator

   Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01); v0.5.1, v0.5.2, v0.6.0, v0.6.1 entries; v0.4.35, v0.4.34

   Retrieved

   2026-10-09

   Source date

   2026-10-01

3. Squads

   Finding: Re-read 2026-10-09: Assignment to a squad wakes only the leader, which @-mentions members, records an evaluation and stops. The leader is woken again when a delegated member replies, a non-member comments or a member posts progress without a mention. Members can be agents or humans. Provider-native subagents are not described.

   Locator

   Squad composition; Execution flow after assignment; Leader re-trigger rules

   Retrieved

   2026-10-09

4. Agents

   Finding: Re-read 2026-10-09: Agent settings: name, instructions, skills, runtime, model and thinking level, Access (Only me default, Specific people, Entire workspace), concurrency, env, MCP. Availability comes from the runtime and workload from runs. Archiving cancels unfinished runs.

   Locator

   Agent configuration; Permissions and Access; Online, offline, and workload status

   Retrieved

   2026-10-09

5. Create and configure an agent

   Finding: Re-read 2026-10-09: Agents start blank or with Build with AI (needs an online runtime). Runtime, model and thinking level. custom_env values are stored in plaintext in the Multica server database; only workspace owners and admins can view or change them. Critical variables such as PATH, HOME and MULTICA_* cannot be overridden.

   Locator

   Starting points; Runtime, model, and thinking level; Configuration after creation; Environment variables and credentials

   Retrieved

   2026-10-09

6. @-mention agents in comments

   Finding: Re-read 2026-10-09: Mentions and replies start runs; a trigger preview is shown before sending. Simultaneous mentions of different agents are not merged; consecutive comments to one agent merge into the pending run. Runs wait when the runtime is offline. Access settings apply to mentions. No presence indicators.

   Locator

   Trigger preview; Automatic routing of replies; Coalescing consecutive comments; Access restrictions

   Retrieved

   2026-10-09

7. Authentication and tokens

   Finding: Re-read 2026-10-09: Browser sessions last 30 days. Personal access tokens (mul_ prefix, 30 days, 90 days, 1 year or never) work against REST endpoints. multica login creates a 90-day token. Run-scoped mat_ tokens last at most 24 hours and attribute actions to the agent. No dedicated REST API reference.

   Locator

   Personal access tokens; Using a PAT in API requests; Temporary tokens for agent runs

   Retrieved

   2026-10-09

8. Tutorial

   Finding: Re-read 2026-10-09: walkthrough. The first agent uses Claude with Sonnet (line 60); the Engineer agent, created through Multica helper, uses Opus (line 85); Reviewer uses Codex with GPT-5.6 Sol in a fresh context and never edits code (line 208). The Engineer opens the PR using the GitHub CLI on the user's computer (line 95). Merging is requested in a comment. Merge-driven status is configurable: the GitHub integration docs say that after PRs merge the issue moves to Done by default or is left alone (github-integration, "After PRs merge, move the issue to"). A PR that references an issue identifier links automatically (line 107).

   Locator

   Prepare the site repository; Reviewer; Merge and close out; Form a squad; Automation

   Retrieved

   2026-10-09

multica:COORD-04

Autopilots run on 5-field cron schedules or webhook triggers from the Multica server, and issue wakeup rules can re-wake an agent on a schedule, comment, status change, sub-issue completion or pull request change, with expiry.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-10-09

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• No schedule or wakeup scenario was run.
• An autopilot pauses itself after at least 50 completed or failed runs in seven days with a 90% failure rate, and its creator must resume it.

1. Runs

   Finding: Re-read 2026-10-09: States deferred, queued, dispatched, waiting_local_directory, running, completed, failed, cancelled. Runs can be stopped from the execution log while deferred, queued, starting, waiting or running. A status change does not stop an active run. Retry from the execution log invokes the original agent and keeps files and session when possible. No pause control. Failure reasons include agent_blocked and missing_config. Dispatched runs fail after 5 minutes. Heartbeat every 15 seconds. Automatic retries only for transient faults (2 attempts, 3 for network interruptions). Transcripts kept.

   Locator

   Execution lifecycle; Viewing run history; Failures and automatic retries; Manual retry; State and timeout quick reference

   Retrieved

   2026-10-09

2. Multica changelog

   Finding: Re-read 2026-10-09: Re-read first 100,000 of 188,543 characters (remainder not read). Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01). Dated entries cited in claims: v0.4.35 (2026-08-26) Pro-plan billing and seat management behind one Cloud address; v0.4.37 (2026-08-31) says Multica installs natively on iPad; v0.5.2 (2026-09-23) and v0.5.3 (2026-09-24) steering of Claude Code, Codex and Grok tasks; v0.5.1 (2026-09-21) issue wakeup rules; v0.6.0 (2026-09-28) wakeups on status change, sub-issue completion and pull request movement, plus add, queue or restart when replying. No dated forward-looking plans in the part read.

   Locator

   Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01); v0.5.1, v0.5.2, v0.6.0, v0.6.1 entries; v0.4.35, v0.4.34

   Retrieved

   2026-10-09

   Source date

   2026-10-01

3. Quickstart

   Finding: Re-read 2026-10-09: Sign in by email code or Google on web or Desktop. Connect a computer: Desktop registers it automatically; web uses an install script then multica setup. Create an agent, create an issue and submit. Common problems: offline runtime, "Keep Desktop open".

   Locator

   Steps 1-5; Common problems

   Retrieved

   2026-10-09

4. Autopilots

   Finding: Re-read 2026-10-09: Autopilots use 5-field cron with IANA time zones, several schedules per autopilot, and run-now. Webhook triggers (JSON up to 256 KiB, idempotency key, GitHub, GitLab and generic event inference, event filters, replay). Create-issue and run-only modes. Run-only failures are not retried and the next schedule still fires. Create-issue waits for an offline runtime; run-only is skipped. Manual pause stops schedules, webhooks and run-now. Automatic pause after at least 50 completed or failed runs in 7 days with a 90% failure rate. The page does not say whether runs can overlap.

   Locator

   Create; Execution mode; Run on a schedule; Run from a webhook; Failures, pausing, and deletion; Permissions

   Retrieved

   2026-10-09

5. Server scheduler

   Finding: Re-read 2026-10-09: Pinned scheduler/jobs_autopilot.go (8db6cfe): autopilot cron occurrences are planned against database time with the sys_cron_executions lease, on the server and independent of clients.

   Locator

   scheduler package: jobs_autopilot.go, jobs_issue_wakeup.go, manager.go

   Retrieved

   2026-10-09

6. Issue wakeup service

   Finding: Re-read 2026-10-09: Pinned issue_wakeup_system.go and issue_wakeup_condition.go (8db6cfe): wakeup condition types issue_field, children_done, pull_request (checks_finished or merged) and other_issue, with condition state and evidence records.

   Locator

   issue_wakeup.go, issue_wakeup_condition.go, issue_wakeup_system.go

   Retrieved

   2026-10-09

7. Multica v0.5.1 release (2026-09-21)

   Finding: Re-read 2026-10-09 via the GitHub API: release v0.5.1, published 2026-09-21. The body lists "MUL-7418: add issue event and time wakeups (#8467)".

   Locator

   Release body: MUL-7418 "add issue event and time wakeups (#8467)"

   Retrieved

   2026-10-09

   Source date

   2026-09-21

8. Multica v0.6.0 release (2026-09-28)

   Finding: Re-read 2026-10-09 via the GitHub API: release v0.6.0, published 2026-09-28. The body lists "MUL-7680: issue wakeup v2 - conditions, runaway protection, check-ins and visibility (#8807)".

   Locator

   Release body: MUL-7680 "issue wakeup v2 - conditions, runaway protection, check-ins and visibility (#8807)"

   Retrieved

   2026-10-09

   Source date

   2026-09-28

multica:COORD-05

Run history exposes stop and retry; running Claude Code, Codex and Grok tasks can be steered with new instructions; failures and blocked agents surface in the issue and inbox.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-10-09

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Task status change does not automatically stop an active run.
• Run-level pause was not found; autopilot pause is a trigger control. Chat versus terminal-mode parity and silent waits were not tested.

1. Issues

   Finding: Re-read 2026-10-09: Seven built-in statuses: backlog, todo, in_progress, in_review, done, blocked, cancelled. Sub-issues with stages and a parent completion notification. No dependency or blocked-by relation documented. Labels and priority described only briefly. When every linked PR merges, the issue moves to the workspace-chosen status, default done.

   Locator

   Parts of an issue; Choose an assignee; Status; Custom statuses; Projects and sub-issues; Switch views

   Retrieved

   2026-10-09

2. Runs

   Finding: Re-read 2026-10-09: States deferred, queued, dispatched, waiting_local_directory, running, completed, failed, cancelled. Runs can be stopped from the execution log while deferred, queued, starting, waiting or running. A status change does not stop an active run. Retry from the execution log invokes the original agent and keeps files and session when possible. No pause control. Failure reasons include agent_blocked and missing_config. Dispatched runs fail after 5 minutes. Heartbeat every 15 seconds. Automatic retries only for transient faults (2 attempts, 3 for network interruptions). Transcripts kept.

   Locator

   Execution lifecycle; Viewing run history; Failures and automatic retries; Manual retry; State and timeout quick reference

   Retrieved

   2026-10-09

3. Multica changelog

   Finding: Re-read 2026-10-09: Re-read first 100,000 of 188,543 characters (remainder not read). Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01). Dated entries cited in claims: v0.4.35 (2026-08-26) Pro-plan billing and seat management behind one Cloud address; v0.4.37 (2026-08-31) says Multica installs natively on iPad; v0.5.2 (2026-09-23) and v0.5.3 (2026-09-24) steering of Claude Code, Codex and Grok tasks; v0.5.1 (2026-09-21) issue wakeup rules; v0.6.0 (2026-09-28) wakeups on status change, sub-issue completion and pull request movement, plus add, queue or restart when replying. No dated forward-looking plans in the part read.

   Locator

   Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01); v0.5.1, v0.5.2, v0.6.0, v0.6.1 entries; v0.4.35, v0.4.34

   Retrieved

   2026-10-09

   Source date

   2026-10-01

4. Using the CLI

   Finding: Re-read 2026-10-09: Commands cover issues, projects, labels, agents, skills, autopilots, workspaces, repos, daemon and runtimes. `multica issue cancel-task <task-id> --issue <issue-id>` cancels a run. `multica issue rerun <id>` re-enqueues for the current assignee. Install via curl script, Homebrew or PowerShell. `issue comment update` requires --expected-revision (source, cmd_issue.go).

   Locator

   Installation; First connection; Common issue operations; Command reference

   Retrieved

   2026-10-09

5. Autopilots

   Finding: Re-read 2026-10-09: Autopilots use 5-field cron with IANA time zones, several schedules per autopilot, and run-now. Webhook triggers (JSON up to 256 KiB, idempotency key, GitHub, GitLab and generic event inference, event filters, replay). Create-issue and run-only modes. Run-only failures are not retried and the next schedule still fires. Create-issue waits for an offline runtime; run-only is skipped. Manual pause stops schedules, webhooks and run-now. Automatic pause after at least 50 completed or failed runs in 7 days with a 90% failure rate. The page does not say whether runs can overlap.

   Locator

   Create; Execution mode; Run on a schedule; Run from a webhook; Failures, pausing, and deletion; Permissions

   Retrieved

   2026-10-09

6. Security model

   Finding: Re-read 2026-10-09: A run executes with the full permissions of the daemon OS user. Multica does not sandbox the filesystem. Approval prompts are answered automatically. Per-run working directories and per-run API tokens are called conveniences, not a boundary. On the default path Codex runs full-access and Claude Code bypasses permission checks; Codex native sandbox is an optional Windows setting.

   Locator

   The boundary is the daemon user; What Multica does isolate; What is not a boundary

   Retrieved

   2026-10-09

7. Assign issues to agents

   Finding: Re-read 2026-10-09: Assignment starts a run unless the issue is in backlog or "Don't start yet" is chosen. Access options: Only me, Specific people, Entire workspace. "a run is bound to its runtime and never moves to another machine." CLI assign commands including --no-start.

   Locator

   Assign and start a run; Assign without starting; Assignment permissions; Use the CLI

   Retrieved

   2026-10-09

8. Inbox and subscriptions

   Finding: Re-read 2026-10-09: Inbox covers assignments, updates on subscribed issues, mentions, reactions, run failures on subscribed issues, results of agent-created issues and autopilot notices. Run-failure notices archive once an issue reaches in_review, started, done or closed; blocked keeps them. Banners follow system and browser settings. Mobile push is not covered on this page.

   Locator

   What lands in the inbox; Tune notification types

   Retrieved

   2026-10-09

multica:COORD-06

Issues can be browsed in list, board, table, Gantt and swimlane views with status, assignee and project filters, parent/sub-issue stages and a workspace dashboard; no dependency graph and no fixture-based test.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-10-09

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• No 12-state fixture was run; navigation steps and errors were not measured; no dependency view found.

1. Issues

   Finding: Re-read 2026-10-09: Seven built-in statuses: backlog, todo, in_progress, in_review, done, blocked, cancelled. Sub-issues with stages and a parent completion notification. No dependency or blocked-by relation documented. Labels and priority described only briefly. When every linked PR merges, the issue moves to the workspace-chosen status, default done.

   Locator

   Parts of an issue; Choose an assignee; Status; Custom statuses; Projects and sub-issues; Switch views

   Retrieved

   2026-10-09

2. Runs

   Finding: Re-read 2026-10-09: States deferred, queued, dispatched, waiting_local_directory, running, completed, failed, cancelled. Runs can be stopped from the execution log while deferred, queued, starting, waiting or running. A status change does not stop an active run. Retry from the execution log invokes the original agent and keeps files and session when possible. No pause control. Failure reasons include agent_blocked and missing_config. Dispatched runs fail after 5 minutes. Heartbeat every 15 seconds. Automatic retries only for transient faults (2 attempts, 3 for network interruptions). Transcripts kept.

   Locator

   Execution lifecycle; Viewing run history; Failures and automatic retries; Manual retry; State and timeout quick reference

   Retrieved

   2026-10-09

3. Multica changelog

   Finding: Re-read 2026-10-09: Re-read first 100,000 of 188,543 characters (remainder not read). Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01). Dated entries cited in claims: v0.4.35 (2026-08-26) Pro-plan billing and seat management behind one Cloud address; v0.4.37 (2026-08-31) says Multica installs natively on iPad; v0.5.2 (2026-09-23) and v0.5.3 (2026-09-24) steering of Claude Code, Codex and Grok tasks; v0.5.1 (2026-09-21) issue wakeup rules; v0.6.0 (2026-09-28) wakeups on status change, sub-issue completion and pull request movement, plus add, queue or restart when replying. No dated forward-looking plans in the part read.

   Locator

   Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01); v0.5.1, v0.5.2, v0.6.0, v0.6.1 entries; v0.4.35, v0.4.34

   Retrieved

   2026-10-09

   Source date

   2026-10-01

4. Using the CLI

   Finding: Re-read 2026-10-09: Commands cover issues, projects, labels, agents, skills, autopilots, workspaces, repos, daemon and runtimes. `multica issue cancel-task <task-id> --issue <issue-id>` cancels a run. `multica issue rerun <id>` re-enqueues for the current assignee. Install via curl script, Homebrew or PowerShell. `issue comment update` requires --expected-revision (source, cmd_issue.go).

   Locator

   Installation; First connection; Common issue operations; Command reference

   Retrieved

   2026-10-09

5. Agents

   Finding: Re-read 2026-10-09: Agent settings: name, instructions, skills, runtime, model and thinking level, Access (Only me default, Specific people, Entire workspace), concurrency, env, MCP. Availability comes from the runtime and workload from runs. Archiving cancels unfinished runs.

   Locator

   Agent configuration; Permissions and Access; Online, offline, and workload status

   Retrieved

   2026-10-09

6. Inbox and subscriptions

   Finding: Re-read 2026-10-09: Inbox covers assignments, updates on subscribed issues, mentions, reactions, run failures on subscribed issues, results of agent-created issues and autopilot notices. Run-failure notices archive once an issue reaches in_review, started, done or closed; blocked keeps them. Banners follow system and browser settings. Mobile push is not covered on this page.

   Locator

   What lands in the inbox; Tune notification types

   Retrieved

   2026-10-09

7. Workspace dashboard

   Finding: Re-read 2026-10-09: Pinned source dashboard-page.tsx (8db6cfe): workspace dashboard shows tokens and estimated cost by day and agent, run time, and failure classes; runtime page shows usage per runtime.

   Locator

   KPI cards, daily cost chart, agent run time, failure classes (lines 140-600)

   Retrieved

   2026-10-09

8. Issue timeline

   Finding: Re-read 2026-10-09: Pinned source internal/handler/activity.go (8db6cfe): the issue timeline interleaves activity and comments with durable actor_type and actor_id attribution; deleted thread roots keep a tombstone.

   Locator

   TimelineEntry lines 14-50

   Retrieved

   2026-10-09

multica:COORD-07

No mandatory workflow preset is required; a quick chat or issue works alone, work can grow into sub-issues, and an Agent Builder configures agents from natural language. Per-agent model and thinking level are set on the agent; what ran is visible in the execution log.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-10-09

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Discoverability and auth friction not evaluated.

1. Issues

   Finding: Re-read 2026-10-09: Seven built-in statuses: backlog, todo, in_progress, in_review, done, blocked, cancelled. Sub-issues with stages and a parent completion notification. No dependency or blocked-by relation documented. Labels and priority described only briefly. When every linked PR merges, the issue moves to the workspace-chosen status, default done.

   Locator

   Parts of an issue; Choose an assignee; Status; Custom statuses; Projects and sub-issues; Switch views

   Retrieved

   2026-10-09

2. Runs

   Finding: Re-read 2026-10-09: States deferred, queued, dispatched, waiting_local_directory, running, completed, failed, cancelled. Runs can be stopped from the execution log while deferred, queued, starting, waiting or running. A status change does not stop an active run. Retry from the execution log invokes the original agent and keeps files and session when possible. No pause control. Failure reasons include agent_blocked and missing_config. Dispatched runs fail after 5 minutes. Heartbeat every 15 seconds. Automatic retries only for transient faults (2 attempts, 3 for network interruptions). Transcripts kept.

   Locator

   Execution lifecycle; Viewing run history; Failures and automatic retries; Manual retry; State and timeout quick reference

   Retrieved

   2026-10-09

3. Multica changelog

   Finding: Re-read 2026-10-09: Re-read first 100,000 of 188,543 characters (remainder not read). Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01). Dated entries cited in claims: v0.4.35 (2026-08-26) Pro-plan billing and seat management behind one Cloud address; v0.4.37 (2026-08-31) says Multica installs natively on iPad; v0.5.2 (2026-09-23) and v0.5.3 (2026-09-24) steering of Claude Code, Codex and Grok tasks; v0.5.1 (2026-09-21) issue wakeup rules; v0.6.0 (2026-09-28) wakeups on status change, sub-issue completion and pull request movement, plus add, queue or restart when replying. No dated forward-looking plans in the part read.

   Locator

   Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01); v0.5.1, v0.5.2, v0.6.0, v0.6.1 entries; v0.4.35, v0.4.34

   Retrieved

   2026-10-09

   Source date

   2026-10-01

4. Quickstart

   Finding: Re-read 2026-10-09: Sign in by email code or Google on web or Desktop. Connect a computer: Desktop registers it automatically; web uses an install script then multica setup. Create an agent, create an issue and submit. Common problems: offline runtime, "Keep Desktop open".

   Locator

   Steps 1-5; Common problems

   Retrieved

   2026-10-09

5. Squads

   Finding: Re-read 2026-10-09: Assignment to a squad wakes only the leader, which @-mentions members, records an evaluation and stops. The leader is woken again when a delegated member replies, a non-member comments or a member posts progress without a mention. Members can be agents or humans. Provider-native subagents are not described.

   Locator

   Squad composition; Execution flow after assignment; Leader re-trigger rules

   Retrieved

   2026-10-09

6. Create and configure an agent

   Finding: Re-read 2026-10-09: Agents start blank or with Build with AI (needs an online runtime). Runtime, model and thinking level. custom_env values are stored in plaintext in the Multica server database; only workspace owners and admins can view or change them. Critical variables such as PATH, HOME and MULTICA_* cannot be overridden.

   Locator

   Starting points; Runtime, model, and thinking level; Configuration after creation; Environment variables and credentials

   Retrieved

   2026-10-09

7. Chat with agents

   Finding: Re-read 2026-10-09: Private one-to-one chat with an agent outside issues. Attachments supported ("attach images or files"). Session continues where possible. Stopping a run restores unprocessed input to the editor. Offline runtime makes messages wait. No code search, indexing or retrieval statement.

   Locator

   Intro; Multi-turn context; Watch and stop a run

   Retrieved

   2026-10-09

multica:RUN-01

Connected computers execute local-tool runs while Cloud or self-hosted Multica coordinates them. Vendor-hosted runtime remains waitlisted. A separate Qoder Cloud Agents bridge connects provider-hosted environments.

Checked

2026-11-07 · checked 1 week ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop; Pinned Multica source

Version

Live docs reread 2026-11-07 through v0.8.1; source at v0.6.1 commit 8db6cfe

• Hosted coordination and execution are separate services.
• Qoder credentials, remote environment and provider setup are required; this is not a universal Multica-hosted compute claim.
• No run, disconnect or self-host deployment test.

1. Mobile app (iOS)

   Finding: Current mobile guide says source-built iPhone client, no App Store and no Android, seven-day free signing, server-owned workspace data. Native iPad support is separately documented in release notes; no device test.

   Locator

   Intro; Prerequisites; 7-day limit of free signing

   Retrieved

   2026-11-07

2. Multica changelog

   Finding: Current changelog lists v0.8.1 dated November 6, 2026, after v0.8.0 November 3. Skills revision history, unread filters and Qoder updates are released, not future promises.

   Locator

   v0.8.1 (November 6, 2026), v0.8.0 (November 3) and historical release entries

   Retrieved

   2026-11-07

   Source date

   2026-11-06

3. Download Multica

   Finding: Downloads show macOS Apple Silicon/Intel, Windows x64/ARM64 and Linux x64/ARM64 installers; current v0.8.1. Vendor-hosted runtime remains not live, waitlist-only. It is separate from connecting Qoder Cloud Agents.

   Locator

   Choose your platform; Prefer the CLI?; Cloud runtime (waitlist); Current version

   Retrieved

   2026-11-07

4. Daemon and runtimes

   Finding: Connected-computer daemon claims local-tool runs, stores results on server, and has explicit login autostart. Runtimes offline over seven days with no bound agents are cleaned up. Separate Qoder Cloud Agents bridge uses a PAT and remote provider environment without a local daemon; defaults three concurrent runs and 60-minute timeout, configurable.

   Locator

   Daemon vs runtime; Execution location; Dispatch and online status; Concurrency limits; Private and public runtimes; Custom runtime profiles; Task runtime environment

   Retrieved

   2026-11-07

5. Desktop app

   Finding: Desktop Mac/Windows/Linux shares server data with web, manages separate daemon profiles, auto-updates with OS/architecture feeds and supports self-hosted apiUrl configuration. Terminal issue CLI installed separately.

   Locator

   Installation; Built-in daemon; Updating Desktop; Connecting to a self-hosted instance

   Retrieved

   2026-11-07

6. Quickstart

   Finding: Web/Desktop sign-in uses email code or Google. Desktop connects a computer automatically; other computers install CLI and run setup. At least one installed/authenticated coding tool required; no bundled model quota.

   Locator

   Steps 1-5; Common problems

   Retrieved

   2026-11-07

7. Assign issues to agents

   Finding: Re-read 2026-10-09: Assignment starts a run unless the issue is in backlog or "Don't start yet" is chosen. Access options: Only me, Specific people, Entire workspace. "a run is bound to its runtime and never moves to another machine." CLI assign commands including --no-start.

   Locator

   Assign and start a run; Assign without starting; Assignment permissions; Use the CLI

   Retrieved

   2026-11-07

8. Self-host quickstart

   Finding: Re-read 2026-10-09: Self-hosting runs Web, API and PostgreSQL through Docker Compose; Kubernetes via Helm is referenced. No email service by default; codes are printed to backend logs until Resend or SMTP is set. Migrations are forward-only. "Self-hosting replaces only the Multica Cloud part."

   Locator

   Multica service and computer; make selfhost; Back up Postgres; Kubernetes

   Retrieved

   2026-11-07

9. Install AI coding tools

   Finding: Re-read 2026-10-09: Sign in to each tool on its own machine; Multica never receives login tokens. "Supported" means Multica can invoke the CLI; it does not supply the tool account, subscription or model quota. The table lists 25 CLIs. Minimum versions for eight tools; below minimum the runtime is not registered.

   Locator

   Choose a tool; Sign in on your machine

   Retrieved

   2026-11-07

10. How Multica works

    Finding: Re-read 2026-10-09: The server coordinates and records work; connected computers execute it. Code directories and local files stay on the connected computer. The server stores issues, comments, statuses, run records and results. Custom env values are stored on the server. The boundary is the same on Cloud and self-hosted.

    Locator

    The full path of a run; The data and execution boundary

    Retrieved

    2026-11-07

11. Cloud billing types

    Finding: Re-read 2026-10-09: Pinned billing types (8db6cfe): credit wallet with 1 USD = 1000 credits, credit batches and top-up states. Header states a separate multica-cloud billing service. No public description of what credits purchase.

    Locator

    Header comment lines 1-12; BillingBatch; BillingTopup

    Retrieved

    2026-11-07

12. Self-hosting guide

    Finding: Re-read 2026-10-09: Pinned SELF_HOSTING.md (8db6cfe): configure RESEND_API_KEY for email codes; without email the code is printed to backend logs; fixed code only when APP_ENV=development.

    Locator

    Telemetry paragraph line 19; Kubernetes section

    Retrieved

    2026-11-07

multica:RUN-02

GitHub repository runs get their own worktree from a cached bare clone; local git directories can use per-run worktrees on agent/<agent>/<issue> branches, while a direct local-directory run uses the user's own checkout in place unless Parallel mode is chosen. Multica states it provides no filesystem, process or network sandbox and recommends a dedicated user, container or VM.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-10-09

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Default daemon path; Windows opt-in Codex sandbox is the one documented exception.
• Two-change code separation was not tested.

1. Daemon and runtimes

   Finding: Re-read 2026-10-09: The daemon is the background process on one computer. A runtime is one computer plus one tool or custom profile. Code and tool credentials stay on the computer; the server stores issues, comments, run records and results. Runtimes offline more than 7 days with no bound agents are cleaned up. Default 20 runs per daemon and 6 per agent. Runtimes are private by default. Custom profiles must fit an existing protocol family; "A custom profile does not add a new communication protocol."

   Locator

   Daemon vs runtime; Execution location; Dispatch and online status; Concurrency limits; Private and public runtimes; Custom runtime profiles; Task runtime environment

   Retrieved

   2026-10-09

2. Security model

   Finding: Re-read 2026-10-09: A run executes with the full permissions of the daemon OS user. Multica does not sandbox the filesystem. Approval prompts are answered automatically. Per-run working directories and per-run API tokens are called conveniences, not a boundary. On the default path Codex runs full-access and Claude Code bypasses permission checks; Codex native sandbox is an optional Windows setting.

   Locator

   The boundary is the daemon user; What Multica does isolate; What is not a boundary

   Retrieved

   2026-10-09

3. Create and configure an agent

   Finding: Re-read 2026-10-09: Agents start blank or with Build with AI (needs an online runtime). Runtime, model and thinking level. custom_env values are stored in plaintext in the Multica server database; only workspace owners and admins can view or change them. Critical variables such as PATH, HOME and MULTICA_* cannot be overridden.

   Locator

   Starting points; Runtime, model, and thinking level; Configuration after creation; Environment variables and credentials

   Retrieved

   2026-10-09

4. Project resources

   Finding: Re-read 2026-10-09: GitHub repositories are checked out per run through worktrees in a runtime-managed workspace. Local git directories run in place (serialized, directory lock) or in Parallel worktree mode on agent/<agent>/<issue> branches. Non-git directories run serially. Dependency caches, snapshots and port allocation are not mentioned.

   Locator

   Add a GitHub repository; Add a local directory; How runs share the directory

   Retrieved

   2026-10-09

5. Repository cache

   Finding: Re-read 2026-10-09: Pinned source repocache/cache.go (8db6cfe): the daemon keeps cached bare clones and creates per-task git worktrees from them. The file also calls isolateWorktreeIdentityContext for each worktree checkout and reconciles a Co-authored-by hook.

   Locator

   package header lines 1-35, CachedRepo line 160

   Retrieved

   2026-10-09

multica:RUN-03

Transient failures auto-retry (default 2 attempts, 3 for tool network errors) and a daemon restart reclaims interrupted runs; retries keep files and continue the session where possible. Credential, quota and configuration errors need a manual fix and retry.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-10-09

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Recovery and duplicate-action safety not observed.
• Compute replacement for a multi-day epic is not supported by moving runs between machines.

1. Runs

   Finding: Re-read 2026-10-09: States deferred, queued, dispatched, waiting_local_directory, running, completed, failed, cancelled. Runs can be stopped from the execution log while deferred, queued, starting, waiting or running. A status change does not stop an active run. Retry from the execution log invokes the original agent and keeps files and session when possible. No pause control. Failure reasons include agent_blocked and missing_config. Dispatched runs fail after 5 minutes. Heartbeat every 15 seconds. Automatic retries only for transient faults (2 attempts, 3 for network interruptions). Transcripts kept.

   Locator

   Execution lifecycle; Viewing run history; Failures and automatic retries; Manual retry; State and timeout quick reference

   Retrieved

   2026-10-09

2. AI coding tools comparison

   Finding: Re-read 2026-10-09: Supported tools table (25 CLIs). Model lists come from each runtime. QwenPaw and MiniMax Code do not accept a model chosen in Multica. No full provider list. Session resumption continues for tools marked as supporting it; MiniMax Code starts a fresh session. MCP is not read for Antigravity, GitHub Copilot CLI, DevEco Code or Pi.

   Locator

   Supported tools table; Model sources; Session resumption; MCP configuration; Skill injection

   Retrieved

   2026-10-09

3. Daemon and runtimes

   Finding: Re-read 2026-10-09: The daemon is the background process on one computer. A runtime is one computer plus one tool or custom profile. Code and tool credentials stay on the computer; the server stores issues, comments, run records and results. Runtimes offline more than 7 days with no bound agents are cleaned up. Default 20 runs per daemon and 6 per agent. Runtimes are private by default. Custom profiles must fit an existing protocol family; "A custom profile does not add a new communication protocol."

   Locator

   Daemon vs runtime; Execution location; Dispatch and online status; Concurrency limits; Private and public runtimes; Custom runtime profiles; Task runtime environment

   Retrieved

   2026-10-09

4. Desktop app

   Finding: Re-read 2026-10-09: Installers: macOS (.dmg), Windows (.exe), Linux (.AppImage, .deb, .rpm). Desktop starts a built-in daemon after sign-in. Auto-update on by default. Self-hosted connection through desktop.json. No minimum OS version stated.

   Locator

   Installation; Built-in daemon; Updating Desktop; Connecting to a self-hosted instance

   Retrieved

   2026-10-09

5. Quickstart

   Finding: Re-read 2026-10-09: Sign in by email code or Google on web or Desktop. Connect a computer: Desktop registers it automatically; web uses an install script then multica setup. Create an agent, create an issue and submit. Common problems: offline runtime, "Keep Desktop open".

   Locator

   Steps 1-5; Common problems

   Retrieved

   2026-10-09

6. Assign issues to agents

   Finding: Re-read 2026-10-09: Assignment starts a run unless the issue is in backlog or "Don't start yet" is chosen. Access options: Only me, Specific people, Entire workspace. "a run is bound to its runtime and never moves to another machine." CLI assign commands including --no-start.

   Locator

   Assign and start a run; Assign without starting; Assignment permissions; Use the CLI

   Retrieved

   2026-10-09

multica:RUN-04

Repository checkouts use cached bare clones and per-task worktrees; the user supplies and maintains tool installs and environments. No product-managed dependency caches, snapshots, service or port allocation were found.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-10-09

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Dependency installs, ports, collisions, snapshots and services were not found as product features.

1. Daemon and runtimes

   Finding: Re-read 2026-10-09: The daemon is the background process on one computer. A runtime is one computer plus one tool or custom profile. Code and tool credentials stay on the computer; the server stores issues, comments, run records and results. Runtimes offline more than 7 days with no bound agents are cleaned up. Default 20 runs per daemon and 6 per agent. Runtimes are private by default. Custom profiles must fit an existing protocol family; "A custom profile does not add a new communication protocol."

   Locator

   Daemon vs runtime; Execution location; Dispatch and online status; Concurrency limits; Private and public runtimes; Custom runtime profiles; Task runtime environment

   Retrieved

   2026-10-09

2. Quickstart

   Finding: Re-read 2026-10-09: Sign in by email code or Google on web or Desktop. Connect a computer: Desktop registers it automatically; web uses an install script then multica setup. Create an agent, create an issue and submit. Common problems: offline runtime, "Keep Desktop open".

   Locator

   Steps 1-5; Common problems

   Retrieved

   2026-10-09

3. Create and configure an agent

   Finding: Re-read 2026-10-09: Agents start blank or with Build with AI (needs an online runtime). Runtime, model and thinking level. custom_env values are stored in plaintext in the Multica server database; only workspace owners and admins can view or change them. Critical variables such as PATH, HOME and MULTICA_* cannot be overridden.

   Locator

   Starting points; Runtime, model, and thinking level; Configuration after creation; Environment variables and credentials

   Retrieved

   2026-10-09

4. Repository cache

   Finding: Re-read 2026-10-09: Pinned source repocache/cache.go (8db6cfe): the daemon keeps cached bare clones and creates per-task git worktrees from them. The file also calls isolateWorktreeIdentityContext for each worktree checkout and reconciles a Co-authored-by hook.

   Locator

   package header lines 1-35, CachedRepo line 160

   Retrieved

   2026-10-09

multica:RUN-05

The daemon enforces a configurable absolute run time limit (default none), an idle watchdog and a tool watchdog (default 2h silence), and classifies provider failures. The platform reports an iteration_limit failure reason when a run reaches its per-run iteration cap. Token and spend budgets were not established in the sources read.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-10-09

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Token and spend limits not found; spending limit requested in open issue #6950.
• Iteration cap: iteration_limit is a platform failure reason (failure.go lines 92 to 96; tasks.mdx line 102). The cap value is not stated, and how an operator sets it was not established.
• Claude Code runs receive --max-turns from the run MaxTurns option in source (claude.go line 1110). How an operator sets that option was not established.

1. Runs

   Finding: Re-read 2026-10-09: States deferred, queued, dispatched, waiting_local_directory, running, completed, failed, cancelled. Runs can be stopped from the execution log while deferred, queued, starting, waiting or running. A status change does not stop an active run. Retry from the execution log invokes the original agent and keeps files and session when possible. No pause control. Failure reasons include agent_blocked and missing_config. Dispatched runs fail after 5 minutes. Heartbeat every 15 seconds. Automatic retries only for transient faults (2 attempts, 3 for network interruptions). Transcripts kept.

   Locator

   Execution lifecycle; Viewing run history; Failures and automatic retries; Manual retry; State and timeout quick reference

   Retrieved

   2026-10-09

2. Daemon and runtimes

   Finding: Re-read 2026-10-09: The daemon is the background process on one computer. A runtime is one computer plus one tool or custom profile. Code and tool credentials stay on the computer; the server stores issues, comments, run records and results. Runtimes offline more than 7 days with no bound agents are cleaned up. Default 20 runs per daemon and 6 per agent. Runtimes are private by default. Custom profiles must fit an existing protocol family; "A custom profile does not add a new communication protocol."

   Locator

   Daemon vs runtime; Execution location; Dispatch and online status; Concurrency limits; Private and public runtimes; Custom runtime profiles; Task runtime environment

   Retrieved

   2026-10-09

3. Environment variables

   Finding: Re-read 2026-10-09: Telemetry on by default: one anonymous self-host snapshot per UTC day; DO_NOT_TRACK=1 or true disables it; ANALYTICS_DISABLED=true turns off PostHog. MULTICA_DAEMON_MAX_CONCURRENT_TASKS default 20. MULTICA_AGENT_TIMEOUT default 0 (no limit). MULTICA_AGENT_IDLE_WATCHDOG default 2h; tool watchdog same by default. No iteration limit variable listed. Optional server-side LLM for chat titles sends chat content to a configured endpoint.

   Locator

   Daemon configuration; Observability and analytics; Server-side LLM

   Retrieved

   2026-10-09

4. Claude Code backend

   Finding: Re-read 2026-10-09: Pinned claude.go (8db6cfe): runs Claude Code with stream-json input and output and keeps stdin open after the first message. Passes --max-turns from the run MaxTurns option (line 1110).

   Locator

   Execute (lines 36-90); buildClaudeArgs lines 1060-1115

   Retrieved

   2026-10-09

5. Multica GitHub issues

   Finding: Re-read 2026-10-09: GitHub searches on 2026-10-09 return 16 open Android results, 12 App Store results and 13 SSO results. Open community requests: #3864 and #3412 (Android), #6996 (mobile push), #7794 and #1218 (blocker dependencies), #6950 (spending limit), #5423 (Azure AAD), #4151 (open-source the hosted runtime). None is a vendor announcement. The repository reports 1,839 open issues and pull requests combined.

   Locator

   Searches 2026-10-08: Android, App Store, SSO/SAML, dependency/blocked-by, budget/spend limit, cloud runtime

   Retrieved

   2026-10-09

6. server/pkg/taskfailure/failure.go at 8db6cfe

   Finding: Re-read 2026-10-09: ReasonIterationLimit = "iteration_limit" is a platform-side failure reason. The comment says the agent reached its per-run iteration cap and emitted a fallback message; it is treated as a Multica-imposed budget. The cap value is not in this file.

   Locator

   Reason constants: ReasonIterationLimit (lines 92 to 96)

   Retrieved

   2026-10-09

7. apps/docs/content/docs/tasks.mdx at 8db6cfe

   Finding: Re-read 2026-10-09: the failure reasons table lists iteration_limit, "Hit the iteration cap for a run", with the action "Narrow the issue scope". The table does not give the cap value or how an operator sets it.

   Locator

   Failure reasons table, row iteration_limit (line 102)

   Retrieved

   2026-10-09

multica:RUN-06

Execution log exposes run state, timing and streaming transcript with classified failure reasons; a workspace dashboard shows usage, estimated cost, run time and failures by day and agent, and the CLI reports issue and runtime usage.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-11-07

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Displayed completion and reconnect consistency not independently tested; traces not found.

1. Runs

   Finding: Re-read 2026-10-09: States deferred, queued, dispatched, waiting_local_directory, running, completed, failed, cancelled. Runs can be stopped from the execution log while deferred, queued, starting, waiting or running. A status change does not stop an active run. Retry from the execution log invokes the original agent and keeps files and session when possible. No pause control. Failure reasons include agent_blocked and missing_config. Dispatched runs fail after 5 minutes. Heartbeat every 15 seconds. Automatic retries only for transient faults (2 attempts, 3 for network interruptions). Transcripts kept.

   Locator

   Execution lifecycle; Viewing run history; Failures and automatic retries; Manual retry; State and timeout quick reference

   Retrieved

   2026-10-09

2. Multica changelog

   Finding: Re-read 2026-10-09: Re-read first 100,000 of 188,543 characters (remainder not read). Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01). Dated entries cited in claims: v0.4.35 (2026-08-26) Pro-plan billing and seat management behind one Cloud address; v0.4.37 (2026-08-31) says Multica installs natively on iPad; v0.5.2 (2026-09-23) and v0.5.3 (2026-09-24) steering of Claude Code, Codex and Grok tasks; v0.5.1 (2026-09-21) issue wakeup rules; v0.6.0 (2026-09-28) wakeups on status change, sub-issue completion and pull request movement, plus add, queue or restart when replying. No dated forward-looking plans in the part read.

   Locator

   Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01); v0.5.1, v0.5.2, v0.6.0, v0.6.1 entries; v0.4.35, v0.4.34

   Retrieved

   2026-10-09

   Source date

   2026-10-01

3. Using the CLI

   Finding: Re-read 2026-10-09: Commands cover issues, projects, labels, agents, skills, autopilots, workspaces, repos, daemon and runtimes. `multica issue cancel-task <task-id> --issue <issue-id>` cancels a run. `multica issue rerun <id>` re-enqueues for the current assignee. Install via curl script, Homebrew or PowerShell. `issue comment update` requires --expected-revision (source, cmd_issue.go).

   Locator

   Installation; First connection; Common issue operations; Command reference

   Retrieved

   2026-10-09

4. Workspace dashboard

   Finding: Re-read 2026-10-09: Pinned source dashboard-page.tsx (8db6cfe): workspace dashboard shows tokens and estimated cost by day and agent, run time, and failure classes; runtime page shows usage per runtime.

   Locator

   KPI cards, daily cost chart, agent run time, failure classes (lines 140-600)

   Retrieved

   2026-10-09

5. Issue execution log

   Finding: Re-read 2026-10-09: Pinned source execution-log-section.tsx (8db6cfe): issue execution log shows per-run usage and cost and a cumulative cost curve estimated from tokens.

   Locator

   cumulativeCostAt, per-run usage cost, sparkline (lines 28-420)

   Retrieved

   2026-10-09

6. lines 131 to 244 (usage dashboard; six rollup queries)

   Finding: Re-read 2026-10-09: the project filter (projectId) is passed to all six rollups: daily usage, by-agent usage, run-time, run-time daily, failures daily and failures by agent (lines 206 to 232). Source-inspected only; no hands-on parity check.

   Locator

   lines 131 to 244 (usage dashboard; six rollup queries)

   Retrieved

   2026-10-09

multica:RUN-07

Estimated per-run and per-issue cost appears in the execution log with a cumulative curve, and the CLI reports issue usage. Figures are the provider-reported cost plus a rate-table estimate for uncosted tokens; custom rates apply only to the estimated part (packages/views/runtimes/utils.ts lines 676 to 702 at 8db6cfe). Billed invoice reconciliation, subscription allowance and compute fees are not established.

Checked

2026-11-07 · checked 1 week ago

Plan

Not specified in this finding

Surface

Pinned Multica source; Multica Cloud/web/desktop

Availability

source only

Version

commit 8db6cfe; v0.6.1

• Cost semantics, estimates and provider reconciliation unverified.
• Compute fees, alerts and export not found.

1. Multica issue CLI

   Finding: Re-read 2026-10-09: Pinned source cmd_issue.go (8db6cfe): issue subcommands include list, get, pull-requests, children, create, update, assign, status, comment, runs, run-messages, usage, rerun, cancel-task and search; comment update requires --expected-revision; calls go through the shared server API.

   Locator

   issueCmd subcommands lines 222-456 (list/get/pull-requests/children/create/update/assign/status/comment/runs/usage/rerun/cancel-task/search); comment update --expected-revision lines 725 and 2584-2613

   Retrieved

   2026-11-07

2. Multica changelog

   Finding: Current changelog lists v0.8.1 dated November 6, 2026, after v0.8.0 November 3. Skills revision history, unread filters and Qoder updates are released, not future promises.

   Locator

   v0.8.1 (November 6, 2026), v0.8.0 (November 3) and historical release entries

   Retrieved

   2026-11-07

   Source date

   2026-11-06

3. Runtime cost estimation

   Finding: Re-read 2026-10-09: Pinned runtimes/utils.ts (8db6cfe): static MODEL_PRICING table of provider rates; estimateCost computes cost from token counts and can prefer per-turn prices.

   Locator

   MODEL_PRICING table lines 203-400; estimateCost

   Retrieved

   2026-11-07

4. Workspace dashboard

   Finding: Re-read 2026-10-09: Pinned source dashboard-page.tsx (8db6cfe): workspace dashboard shows tokens and estimated cost by day and agent, run time, and failure classes; runtime page shows usage per runtime.

   Locator

   KPI cards, daily cost chart, agent run time, failure classes (lines 140-600)

   Retrieved

   2026-11-07

5. Issue execution log

   Finding: Re-read 2026-10-09: Pinned source execution-log-section.tsx (8db6cfe): issue execution log shows per-run usage and cost and a cumulative cost curve estimated from tokens.

   Locator

   cumulativeCostAt, per-run usage cost, sparkline (lines 28-420)

   Retrieved

   2026-11-07

6. lines 676 to 702, estimateCost

   Finding: Re-read 2026-10-09: estimateCost adds the provider-reported cost_usd_ticks (authoritative half) to a rate-table estimate for uncosted tokens; custom pricing overrides apply only to the estimated half.

   Locator

   lines 676 to 702, estimateCost

   Retrieved

   2026-11-07

7. Multica analytics

   Finding: Usage rolls up every five minutes and supports project, runtime, model, agent and issue detail. Costs are estimated unless the runtime reports its own charge; unpriced models can count as zero cost.

   Locator

   Page layout; Cost calculation; Issue cost; From the CLI

   Retrieved

   2026-11-07

multica:RUN-08

A daemon-wide cap (20) and per-agent cap (6) queue excess runs, and a directory lock serializes runs on the same local directory; CPU/RAM-aware scheduling and check de-duplication were not found.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-10-09

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Fairness, recovery under load, check reuse and bounded browser-test queues were not tested.

1. Runs

   Finding: Re-read 2026-10-09: States deferred, queued, dispatched, waiting_local_directory, running, completed, failed, cancelled. Runs can be stopped from the execution log while deferred, queued, starting, waiting or running. A status change does not stop an active run. Retry from the execution log invokes the original agent and keeps files and session when possible. No pause control. Failure reasons include agent_blocked and missing_config. Dispatched runs fail after 5 minutes. Heartbeat every 15 seconds. Automatic retries only for transient faults (2 attempts, 3 for network interruptions). Transcripts kept.

   Locator

   Execution lifecycle; Viewing run history; Failures and automatic retries; Manual retry; State and timeout quick reference

   Retrieved

   2026-10-09

2. Daemon and runtimes

   Finding: Re-read 2026-10-09: The daemon is the background process on one computer. A runtime is one computer plus one tool or custom profile. Code and tool credentials stay on the computer; the server stores issues, comments, run records and results. Runtimes offline more than 7 days with no bound agents are cleaned up. Default 20 runs per daemon and 6 per agent. Runtimes are private by default. Custom profiles must fit an existing protocol family; "A custom profile does not add a new communication protocol."

   Locator

   Daemon vs runtime; Execution location; Dispatch and online status; Concurrency limits; Private and public runtimes; Custom runtime profiles; Task runtime environment

   Retrieved

   2026-10-09

3. Project resources

   Finding: Re-read 2026-10-09: GitHub repositories are checked out per run through worktrees in a runtime-managed workspace. Local git directories run in place (serialized, directory lock) or in Parallel worktree mode on agent/<agent>/<issue> branches. Non-git directories run serially. Dependency caches, snapshots and port allocation are not mentioned.

   Locator

   Add a GitHub repository; Add a local directory; How runs share the directory

   Retrieved

   2026-10-09

multica:TEAM-01

Workspace members share issues and comments with attribution; members can each comment, mention and steer agents with coalescing of simultaneous instructions; presence indicators and plan restrictions were not found.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-10-09

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Presence and plan restrictions not found.

1. Multica issue CLI

   Finding: Re-read 2026-10-09: Pinned source cmd_issue.go (8db6cfe): issue subcommands include list, get, pull-requests, children, create, update, assign, status, comment, runs, run-messages, usage, rerun, cancel-task and search; comment update requires --expected-revision; calls go through the shared server API.

   Locator

   issueCmd subcommands lines 222-456 (list/get/pull-requests/children/create/update/assign/status/comment/runs/usage/rerun/cancel-task/search); comment update --expected-revision lines 725 and 2584-2613

   Retrieved

   2026-10-09

2. Multica changelog

   Finding: Re-read 2026-10-09: Re-read first 100,000 of 188,543 characters (remainder not read). Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01). Dated entries cited in claims: v0.4.35 (2026-08-26) Pro-plan billing and seat management behind one Cloud address; v0.4.37 (2026-08-31) says Multica installs natively on iPad; v0.5.2 (2026-09-23) and v0.5.3 (2026-09-24) steering of Claude Code, Codex and Grok tasks; v0.5.1 (2026-09-21) issue wakeup rules; v0.6.0 (2026-09-28) wakeups on status change, sub-issue completion and pull request movement, plus add, queue or restart when replying. No dated forward-looking plans in the part read.

   Locator

   Releases v0.1.0 (2026-03-22) to v0.6.1 (2026-10-01); v0.5.1, v0.5.2, v0.6.0, v0.6.1 entries; v0.4.35, v0.4.34

   Retrieved

   2026-10-09

   Source date

   2026-10-01

3. Daemon and runtimes

   Finding: Re-read 2026-10-09: The daemon is the background process on one computer. A runtime is one computer plus one tool or custom profile. Code and tool credentials stay on the computer; the server stores issues, comments, run records and results. Runtimes offline more than 7 days with no bound agents are cleaned up. Default 20 runs per daemon and 6 per agent. Runtimes are private by default. Custom profiles must fit an existing protocol family; "A custom profile does not add a new communication protocol."

   Locator

   Daemon vs runtime; Execution location; Dispatch and online status; Concurrency limits; Private and public runtimes; Custom runtime profiles; Task runtime environment

   Retrieved

   2026-10-09

4. Members and roles

   Finding: Re-read 2026-10-09: Roles owner, admin, member. Invitations valid 7 days. "A removed member loses workspace access immediately"; their runtimes are deactivated, agents archived and unfinished runs cancelled. Roles do not decide who can run an agent. No SSO or provisioning mention.

   Locator

   The three roles; Invite members; Remove a member

   Retrieved

   2026-10-09

5. Agents

   Finding: Re-read 2026-10-09: Agent settings: name, instructions, skills, runtime, model and thinking level, Access (Only me default, Specific people, Entire workspace), concurrency, env, MCP. Availability comes from the runtime and workload from runs. Archiving cancels unfinished runs.

   Locator

   Agent configuration; Permissions and Access; Online, offline, and workload status

   Retrieved

   2026-10-09

6. @-mention agents in comments

   Finding: Re-read 2026-10-09: Mentions and replies start runs; a trigger preview is shown before sending. Simultaneous mentions of different agents are not merged; consecutive comments to one agent merge into the pending run. Runs wait when the runtime is offline. Access settings apply to mentions. No presence indicators.

   Locator

   Trigger preview; Automatic routing of replies; Coalescing consecutive comments; Access restrictions

   Retrieved

   2026-10-09

7. Chat with agents

   Finding: Re-read 2026-10-09: Private one-to-one chat with an agent outside issues. Attachments supported ("attach images or files"). Session continues where possible. Stopping a run restores unprocessed input to the editor. Offline runtime makes messages wait. No code search, indexing or retrieval statement.

   Locator

   Intro; Multi-turn context; Watch and stop a run

   Retrieved

   2026-10-09

8. Comments

   Finding: Re-read 2026-10-09: Threaded comments with attachments, annotations, resolve or conclusion, mentions and reactions. Authors edit or delete their own comments; owners and admins edit or delete anyone's; agent-posted comments can only be deleted. Deletion is permanent. Drafts expire after 30 days. Retention and export not stated.

   Locator

   Post comments; Annotate; Resolve a discussion; @-mentions; Edit and delete

   Retrieved

   2026-10-09

9. Workspaces

   Finding: Re-read 2026-10-09: A workspace is the isolation boundary for members, issues, projects, agents, skills and run history. Owners and admins manage settings; members view them. Deletion is permanent. No export or portability statement. No SSO mention.

   Locator

   What a workspace contains; Delete a workspace

   Retrieved

   2026-10-09

10. Issue timeline

    Finding: Re-read 2026-10-09: Pinned source internal/handler/activity.go (8db6cfe): the issue timeline interleaves activity and comments with durable actor_type and actor_id attribution; deleted thread roots keep a tombstone.

    Locator

    TimelineEntry lines 14-50

    Retrieved

    2026-10-09

multica:TEAM-02

Workspaces have owner, admin and member roles, 7-day invitations and immediate revocation on removal; agent Access (only me, specific people, entire workspace) governs who can run an agent. SSO and provisioning were not found.

Checked

2026-10-09 · checked 1 month ago

Cross-check

cross-checked 2026-10-09

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Project and task roles, SSO and provisioning were not found; SSO requests are open (#5423, #1392).
• Plan scope of roles unknown.

1. Members and roles

   Finding: Re-read 2026-10-09: Roles owner, admin, member. Invitations valid 7 days. "A removed member loses workspace access immediately"; their runtimes are deactivated, agents archived and unfinished runs cancelled. Roles do not decide who can run an agent. No SSO or provisioning mention.

   Locator

   The three roles; Invite members; Remove a member

   Retrieved

   2026-10-09

2. Agents

   Finding: Re-read 2026-10-09: Agent settings: name, instructions, skills, runtime, model and thinking level, Access (Only me default, Specific people, Entire workspace), concurrency, env, MCP. Availability comes from the runtime and workload from runs. Archiving cancels unfinished runs.

   Locator

   Agent configuration; Permissions and Access; Online, offline, and workload status

   Retrieved

   2026-10-09

3. Authentication and tokens

   Finding: Re-read 2026-10-09: Browser sessions last 30 days. Personal access tokens (mul_ prefix, 30 days, 90 days, 1 year or never) work against REST endpoints. multica login creates a 90-day token. Run-scoped mat_ tokens last at most 24 hours and attribute actions to the agent. No dedicated REST API reference.

   Locator

   Personal access tokens; Using a PAT in API requests; Temporary tokens for agent runs

   Retrieved

   2026-10-09

4. Workspaces

   Finding: Re-read 2026-10-09: A workspace is the isolation boundary for members, issues, projects, agents, skills and run history. Owners and admins manage settings; members view them. Deletion is permanent. No export or portability statement. No SSO mention.

   Locator

   What a workspace contains; Delete a workspace

   Retrieved

   2026-10-09

5. Multica GitHub issues

   Finding: Re-read 2026-10-09: GitHub searches on 2026-10-09 return 16 open Android results, 12 App Store results and 13 SSO results. Open community requests: #3864 and #3412 (Android), #6996 (mobile push), #7794 and #1218 (blocker dependencies), #6950 (spending limit), #5423 (Azure AAD), #4151 (open-source the hosted runtime). None is a vendor announcement. The repository reports 1,839 open issues and pull requests combined.

   Locator

   Searches 2026-10-08: Android, App Store, SSO/SAML, dependency/blocked-by, budget/spend limit, cloud runtime

   Retrieved

   2026-10-09

multica:TEAM-03

Runs are unsandboxed and tool approval prompts are answered automatically by default; agent Access controls who can trigger agents, but no per-command, tool, network or delivery approval gate was found.

Checked

2026-10-09 · checked 1 month ago

Plan

Not specified in this finding

Surface

Multica Cloud/web/desktop

Version

v0.6.1 (released 2026-10-01) docs; source commit 8db6cfe

• Delivery, secret and tunnel approvals, approver identity and allow/deny/revoke flows were not found.
• Scope is the default daemon path; Windows Codex opt-in is an exception.

1. Security model

   Finding: Re-read 2026-10-09: A run executes with the full permissions of the daemon OS user. Multica does not sandbox the filesystem. Approval prompts are answered automatically. Per-run working directories and per-run API tokens are called conveniences, not a boundary. On the default path Codex runs full-access and Claude Code bypasses permission checks; Codex native sandbox is an optional Windows setting.

   Locator

   The boundary is the daemon user; What Multica does isolate; What is not a boundary

   Retrieved

   2026-10-09

2. Agents

   Finding: Re-read 2026-10-09: Agent settings: name, instructions, skills, runtime, model and thinking level, Access (Only me default, Specific people, Entire workspace), concurrency, env, MCP. Availability comes from the runtime and workload from runs. Archiving cancels unfinished runs.

   Locator

   Agent configuration; Permissions and Access; Online, offline, and workload status

   Retrieved

   2026-10-09

3. Authentication and tokens

   Finding: Re-read 2026-10-09: Browser sessions last 30 days. Personal access tokens (mul_ prefix, 30 days, 90 days, 1 year or never) work against REST endpoints. multica login creates a 90-day token. Run-scoped mat_ tokens last at most 24 hours and attribute actions to the agent. No dedicated REST API reference.

   Locator

   Personal access tokens; Using a PAT in API requests; Temporary tokens for agent runs

   Retrieved

   2026-10-09

4. CLI and Agent Daemon Guide

   Finding: Re-read 2026-10-09: Pinned CLI_AND_DAEMON.md (8db6cfe): runtime table with protocol families including ACP for several tools; MCP servers passed over ACP session/new and resume requests; MiniMax Code 0.1.2 has no session-loading capability; remote MCP transports depend on declared capability.

   Locator

   Supported Agents table lines 217-250; How It Works lines 251-258; per-tool launch notes lines 355-396

   Retrieved

   2026-10-09

5. Claude Code backend

   Finding: Re-read 2026-10-09: Pinned claude.go (8db6cfe): runs Claude Code with stream-json input and output and keeps stdin open after the first message. Passes --max-turns from the run MaxTurns option (line 1110).

   Locator

   Execute (lines 36-90); buildClaudeArgs lines 1060-1115

   Retrieved

   2026-10-09

6. Multica security model

   Finding: The daemon normally runs with its OS user’s full permissions. Operators can put it in a dedicated account, container or VM; these are externally configured boundaries.

   Locator

   Recommended setups; What Multica does isolate

   Retrieved

   2026-11-07

7. Multica authentication tokens

   Finding: A temporary run token is bound to user, workspace, agent and run, lasts at most 24 hours and is cleaned up at run end.

   Locator

   Temporary tokens for agent runs

   Retrieved

   2026-11-07