# Maestro

Podium publishes this catalog and sells an agent development environment. Podium chooses the products, criteria, sources and wording, so treat these pages as vendor-authored research. Check important claims against the linked primary sources. The same evidence rules apply to Podium and its competitors, but they do not remove this conflict of interest.

Page: https://adecomparison.com/ade/maestro/
Website: https://runmaestro.ai/
Research: covered

Method: https://adecomparison.com/method/

Rank by must-haves met, then preferences, then name. Read each finding's checked date. Findings stay published after their scheduled recheck. Checks over six months old may be outdated.

## maestro:ACC-01

Finding: Maestro documents cross-platform desktop and phone-browser control. Native distribution targets are macOS, Windows and Linux; phones use the built-in web interface, with no native iOS or Android target in this release.

Verification: sourced
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Not specified
Surface: desktop; ssh-remote
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

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

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/README.md
Locator: Overview, setup, features and component boundaries
Finding: Cross-platform Electron workspace with parallel agent sessions, Auto Run Markdown checklists or goal loops, remote control, usage views and Git worktree tools. Feature docs may include prerelease behavior.
Retrieved: 2026-11-07

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/cli.md
Locator: Sending messages; Global Flags; Auto Run
Finding: CLI sends/resumes agent sessions, runs playbooks and exposes structured JSON and failure codes. Some commands require the app reachable.
Retrieved: 2026-11-07

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/remote-control.md
Locator: Mobile Web Interface; Network Exposure
Finding: A browser/phone client uses the full host UI. URL token grants full control; LIVE-off returns loopback-only and rotates the token.
Retrieved: 2026-11-07

Source: https://github.com/RunMaestro/Maestro/blob/1d462eb41f69e01bf848156e3c47997ad971c462/package.json
Locator: Electron build mac, win and linux targets; docs/remote-control.md Mobile Web Interface
Finding: The scoped distribution builds Electron desktop packages for macOS, Windows and Linux. The phone client is the built-in browser interface; no native iOS or Android package exists in the inspected build targets.
Retrieved: 2026-11-13

## maestro:ACC-02

Finding: Maestro integrates several coding CLIs with provider-specific capabilities. At v1.0.2 the released providers also include Pi and Grok CLI (added in v1.0.0), while Gemini CLI is hidden and documented as not yet supported. Maestro v1.0.2 ships Antigravity CLI as an agy provider with headless stream-json output, conversation resume and permission-mode arguments.

Verification: agent-cross-checked
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Not specified
Surface: desktop; ssh-remote
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision. Antigravity source pass: v1.0.2 (1d462eb41f69e01bf848156e3c47997ad971c462).

The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
Antigravity requires its own CLI and login. Its provider definition cannot enforce read-only mode or disable tools.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/provider-notes.md
Locator: Token Source; Claude Code; Codex
Finding: Documents CLI transports, credential funding and provider-specific limits, including Standard-mode restrictions over SSH.
Retrieved: 2026-11-07

Source: https://github.com/RunMaestro/Maestro/blob/1d462eb41f69e01bf848156e3c47997ad971c462/src/shared/agentIds.ts#L15-L29
Locator: src/shared/agentIds.ts lines 15-29 (AGENT_IDS), commit 1d462eb
Finding: The canonical agent ID list at v1.0.2 includes claude-code, codex, gemini-cli, antigravity, qwen3-coder, opencode, factory-droid, hermes, pi, copilot-cli, omp and grok.
Retrieved: 2026-11-10

Source: https://github.com/RunMaestro/Maestro/blob/1d462eb41f69e01bf848156e3c47997ad971c462/src/main/agents/definitions.ts#L546-L580
Locator: src/main/agents/definitions.ts lines 546-580 (AGENT_DEFINITIONS id pi), commit 1d462eb
Finding: The visible Pi definition spawns the pi binary in JSON output mode with session resume, read-only tool restriction and model override.
Retrieved: 2026-11-10

Source: https://github.com/RunMaestro/Maestro/blob/1d462eb41f69e01bf848156e3c47997ad971c462/src/main/agents/definitions.ts#L845-L880
Locator: src/main/agents/definitions.ts lines 845-880 (AGENT_DEFINITIONS id grok), commit 1d462eb
Finding: The visible Grok CLI definition spawns the grok binary in batch mode with streaming JSON output and resume; there is no interactive PTY integration.
Retrieved: 2026-11-10

Source: https://github.com/RunMaestro/Maestro/blob/1d462eb41f69e01bf848156e3c47997ad971c462/src/main/agents/definitions.ts#L346-L350
Locator: src/main/agents/definitions.ts lines 346-350 (AGENT_DEFINITIONS id gemini-cli), commit 1d462eb
Finding: The gemini-cli definition is marked hidden and commented as not shipping, superseded by Antigravity, and kept only for type compatibility.
Retrieved: 2026-11-10

Source: https://github.com/RunMaestro/Maestro/blob/1d462eb41f69e01bf848156e3c47997ad971c462/README.md#L19-L19
Locator: README.md lines 19-19 (intro paragraph), commit 1d462eb
Finding: README lists the supported coding CLIs and says Gemini CLI support is planned based on user demand, i.e. not currently supported. Line 106 repeats that Gemini CLI may be added in future releases.
Retrieved: 2026-11-10

Source: https://github.com/RunMaestro/Maestro/blob/1d462eb41f69e01bf848156e3c47997ad971c462/docs/provider-notes.md#L184-L199
Locator: docs/provider-notes.md lines 184-199 (Pi section), commit 1d462eb
Finding: Documents Pi provider features (image attachments, session resume, read-only mode, cost tracking, model selection) and that Maestro uses Pi's JSON output mode.
Retrieved: 2026-11-10

Source: https://github.com/RunMaestro/Maestro/releases/tag/v1.0.0
Locator: GitHub release v1.0.0 notes, providers paragraph
Finding: v1.0.0 release notes say Antigravity CLI, Grok CLI, Hermes, Oh My Pi and Pi joined the providers, running locally or over SSH.
Retrieved: 2026-11-10

Source: https://github.com/RunMaestro/Maestro/blob/1d462eb41f69e01bf848156e3c47997ad971c462/src/main/agents/definitions.ts#L399-L430
Locator: src/main/agents/definitions.ts lines 399-430, v1.0.2, commit 1d462eb41f69e01bf848156e3c47997ad971c462
Finding: Maestro v1.0.2 ships Antigravity CLI as an agy provider with headless stream-json output, conversation resume and permission-mode arguments.
Retrieved: 2026-11-10

Source: https://github.com/RunMaestro/Maestro/blob/1d462eb41f69e01bf848156e3c47997ad971c462/src/shared/agentIds.ts#L7-L24
Locator: src/shared/agentIds.ts lines 7-24, v1.0.2, commit 1d462eb41f69e01bf848156e3c47997ad971c462
Finding: Maestro v1.0.2 ships Antigravity CLI as an agy provider with headless stream-json output, conversation resume and permission-mode arguments.
Retrieved: 2026-11-10

## maestro:ACC-03

Finding: Provider credentials decide subscription versus API billing.

Verification: agent-cross-checked
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Not specified
Surface: desktop; ssh-remote
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/provider-notes.md
Locator: Token Source; Claude Code; Codex
Finding: Documents CLI transports, credential funding and provider-specific limits, including Standard-mode restrictions over SSH.
Retrieved: 2026-11-07

## maestro:ACC-05

Finding: Maestro has bundled CLI control plus a separate read-only documentation-search MCP server.

Verification: agent-cross-checked
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Not specified
Surface: desktop; ssh-remote
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/cli.md
Locator: Sending messages; Global Flags; Auto Run
Finding: CLI sends/resumes agent sessions, runs playbooks and exposes structured JSON and failure codes. Some commands require the app reachable.
Retrieved: 2026-11-07

Source: https://docs.runmaestro.ai/mcp-server
Locator: Overview; Available tools; Technical details
Finding: Mintlify-hosted public read-only MCP exposes SearchMaestro for documentation search/retrieval, not session/task control. HTTP transport needs no authentication.
Retrieved: 2026-11-07

## maestro:ACC-06

Finding: Maestro inherits MCP tools, skills and authentication from configured coding providers.

Verification: agent-cross-checked
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Desktop local/SSH; headless Cue is separately documented with unresolved release parity
Surface: desktop; ssh-remote
Version: First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.

Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/README.md
Locator: How it works; Features; Quick start
Finding: Maestro passes prompts to locally configured provider CLIs and inherits their MCP tools, skills, permissions and authentication. Desktop installation supports user-owned operation. Its documentation MCP server searches docs rather than controlling tasks.
Retrieved: 2026-11-07

## maestro:ACC-07

Finding: The desktop package uses Electron.

Verification: agent-cross-checked
Checked: 2026-11-07
Scheduled recheck: 2027-02-05
Plan: Not specified
Surface: desktop
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/package.json
Locator: Dependencies, scripts and application metadata
Finding: Pinned build metadata identifies the implementation used by the documented application.
Retrieved: 2026-11-07

## maestro:PLAN-02

Finding: Auto Run uses editable Markdown plans with on-disk checkboxes and resettable run copies.

Verification: sourced
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Not specified
Surface: desktop; ssh-remote
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/autorun-playbooks.md
Locator: Setting up; Tasks; Model Override; Human-in-the-loop
Finding: Markdown checklists or goal loops run explicitly; active documents are read-only except paused runs. Per-run model and effort overrides are supported.
Retrieved: 2026-11-07

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/autorun-playbooks.md
Locator: Creating Tasks; Running Multiple Auto Run Documents; How a Goal Run Stops; Steering a Run in Flight; Auto-Resume After an Error; Human-in-the-Loop Gates; Stalled Documents; Halt Marker
Finding: Goal runs stop on completion, deadlock, finite iteration cap or three stalled iterations. Desktop HITL markers pause until Done, Resume; CLI emits document_gated and skips the document. Three no-progress dispatches abandon a document. Halt markers stop the playbook and prevent replay until removed. Per-run auto-resume defaults to five attempts. Steering notes typed in the Thought Stream are delivered at the start of the next task. Checkboxes and the editor reopen while a run is paused; Reset on Completion keeps working copies in runs/.
Retrieved: 2026-11-07

## maestro:PLAN-04

Finding: Maestro exposes Claude Code project memory for reading, editing and deletion, and passes provider-configured skills through to the underlying CLI.

Verification: sourced
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Not specified
Surface: desktop; ssh-remote
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/memories.md
Locator: Opening; Reading/editing; Finding
Finding: Claude-only project memory viewer reads/edits/deletes Markdown memory; other providers do not expose this panel.
Retrieved: 2026-11-07

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/README.md
Locator: How it works; Features; Quick start
Finding: Maestro passes prompts to locally configured provider CLIs and inherits their MCP tools, skills, permissions and authentication. Desktop installation supports user-owned operation. Its documentation MCP server searches docs rather than controlling tasks.
Retrieved: 2026-11-07

## maestro:PLAN-06

Finding: Markdown tasks can be saved and selected before explicit Auto Run.

Verification: agent-cross-checked
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Not specified
Surface: desktop; ssh-remote
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/autorun-playbooks.md
Locator: Setting up; Tasks; Model Override; Human-in-the-loop
Finding: Markdown checklists or goal loops run explicitly; active documents are read-only except paused runs. Per-run model and effort overrides are supported.
Retrieved: 2026-11-07

## maestro:COORD-01

Finding: Maestro documents multiple agent processes and worktree agents.

Verification: agent-cross-checked
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Not specified
Surface: desktop; ssh-remote
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/README.md
Locator: Overview, setup, features and component boundaries
Finding: Cross-platform Electron workspace with parallel agent sessions, Auto Run Markdown checklists or goal loops, remote control, usage views and Git worktree tools. Feature docs may include prerelease behavior.
Retrieved: 2026-11-07

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/configuration.md
Locator: Anonymous Check-in; Storage; Sync
Finding: Update check sends UUID/version/platform/theme telemetry, disabled with update checking. Folder sync warns against simultaneous devices and has no conflict resolution.
Retrieved: 2026-11-07

## maestro:COORD-02

Finding: Group Chat queues busy agents by default, with an explicit unsafe concurrent-edit alternative.

Verification: agent-cross-checked
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Desktop local/SSH; headless Cue is separately documented with unresolved release parity
Surface: desktop; ssh-remote
Version: First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.

Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/group-chat.md
Locator: Agent availability; Message queue; Remote agents
Finding: Group Chat moderators coordinate named local/remote agents. By default busy agents wait up to 15 minutes; disabling that safeguard permits concurrent file edits without a lock. Chat queues persist across reload/quit, restart paused, and retain failed sends until manual resume. Group chats can be deleted with their conversation history.
Retrieved: 2026-11-07

## maestro:COORD-03

Finding: Group Chat has a moderator, follow-up rounds and named local/remote participants.

Verification: agent-cross-checked
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Not specified
Surface: desktop; ssh-remote
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/group-chat.md
Locator: How it Works; Moderator role; Availability
Finding: A moderator coordinates named agents over multiple turns and routes results. Participants do not automatically see each other replies.
Retrieved: 2026-11-07

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/group-chat.md
Locator: Agent availability; Message queue; Remote agents
Finding: Group Chat moderators coordinate named local/remote agents. By default busy agents wait up to 15 minutes; disabling that safeguard permits concurrent file edits without a lock. Chat queues persist across reload/quit, restart paused, and retain failed sends until manual resume. Group chats can be deleted with their conversation history.
Retrieved: 2026-11-07

## maestro:COORD-04

Finding: Released desktop Cue sends prompts on file changes, timers, scheduled times, agent completions and GitHub events. Online headless-server documentation describes an additional deployment whose parity with this pinned release remains unestablished.

Verification: sourced
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Not specified
Surface: desktop
Version: 1d462eb41f69e01bf848156e3c47997ad971c462 (released desktop Cue; headless parity unresolved)

The release source establishes desktop Cue. Headless-server parity remains unestablished and is excluded from the current availability claim. Completion conditions and automatic retries remain unknown.

Source: https://docs.runmaestro.ai/maestro-cue-server
Locator: Before you start; Build; Install
Finding: Current public docs describe a source-built Linux/systemd or container runner for exported pipelines and agents. It runs unattended in YOLO, with server-side credentials. The same path is absent at the pinned repository revision.
Retrieved: 2026-11-07

Source: https://docs.runmaestro.ai/maestro-cue-server
Locator: Before you start; Operate; Known limits
Finding: Cue can run exported pipelines on Linux/systemd or containers without a desktop or logged-in user. Agents use server-side logins and YOLO permissions. Run database stores activity without output; engine logs hold output. In-flight runs become failed after engine restart. Stopping SSH shell steps stops the SSH client, not the remote command.
Retrieved: 2026-11-07

Source: https://github.com/RunMaestro/Maestro/blob/1d462eb41f69e01bf848156e3c47997ad971c462/docs/maestro-cue.md#L1-L30
Locator: docs/maestro-cue.md lines 1-30 (Cue Overview), commit 1d462eb
Finding: Cue is an event-driven automation engine, on by default, that sends prompts to agents when file changes, timers, agent completions, GitHub activity or pending tasks fire, defined as subscriptions in .maestro/cue.yaml.
Retrieved: 2026-11-10

Source: https://github.com/RunMaestro/Maestro/blob/1d462eb41f69e01bf848156e3c47997ad971c462/docs/maestro-cue-events.md#L45-L80
Locator: docs/maestro-cue-events.md lines 45-80 (time.heartbeat and time.scheduled), commit 1d462eb
Finding: time.heartbeat fires on a repeating interval and catches up after system sleep; time.scheduled is a cron-like trigger for specific times and weekdays.
Retrieved: 2026-11-10

Source: https://github.com/RunMaestro/Maestro/blob/1d462eb41f69e01bf848156e3c47997ad971c462/docs/maestro-cue-events.md#L400-L402
Locator: docs/maestro-cue-events.md lines 400-402 (github.pull_request), commit 1d462eb
Finding: The github.pull_request event polls GitHub for new pull requests via the gh CLI and triggers a subscription prompt; github.issue, github.label and webhook.received events follow in the same file.
Retrieved: 2026-11-10

Source: https://github.com/RunMaestro/Maestro/blob/1d462eb41f69e01bf848156e3c47997ad971c462/docs/maestro-cue-advanced.md#L309-L337
Locator: docs/maestro-cue-advanced.md lines 309-337 (max_concurrent and queue_size), commit 1d462eb
Finding: max_concurrent limits parallel Cue runs per agent (default 1, so events run one at a time); extra events are queued up to queue_size and overflow is dropped with a toast.
Retrieved: 2026-11-10

## maestro:COORD-06

Finding: Nested worktree agents expose parent relationships; the fleet fixture remains untested.

Verification: agent-cross-checked
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Not specified
Surface: desktop; ssh-remote
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/git-worktrees.md
Locator: Git menu; Worktree agents; Setup scripts
Finding: Git log/diff and PR actions integrate with nested worktree agents. Setup scripts run before first agent prompt, on the selected local/SSH host.
Retrieved: 2026-11-07

## maestro:COORD-07

Finding: Auto Run supports presets, model options and queued steering notes between tasks.

Verification: sourced
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Not specified
Surface: desktop; ssh-remote
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/autorun-playbooks.md
Locator: Setting up; Tasks; Model Override; Human-in-the-loop
Finding: Markdown checklists or goal loops run explicitly; active documents are read-only except paused runs. Per-run model and effort overrides are supported.
Retrieved: 2026-11-07

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/autorun-playbooks.md
Locator: Creating Tasks; Running Multiple Auto Run Documents; How a Goal Run Stops; Steering a Run in Flight; Auto-Resume After an Error; Human-in-the-Loop Gates; Stalled Documents; Halt Marker
Finding: Goal runs stop on completion, deadlock, finite iteration cap or three stalled iterations. Desktop HITL markers pause until Done, Resume; CLI emits document_gated and skips the document. Three no-progress dispatches abandon a document. Halt markers stop the playbook and prevent replay until removed. Per-run auto-resume defaults to five attempts. Steering notes typed in the Thought Stream are delivered at the start of the next task. Checkboxes and the editor reopen while a run is paused; Reset on Completion keeps working copies in runs/.
Retrieved: 2026-11-07

## maestro:RUN-01

Finding: Desktop/SSH execution and headless Cue server pipelines are user-operated. The scoped launcher has no vendor-managed runtime.

Verification: sourced
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Desktop and SSH execution; online headless Cue guide has unresolved parity with the pinned release source.
Surface: desktop; ssh-remote; Maestro Cue server
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

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

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/ssh-remote-execution.md
Locator: Overview; Configuring SSH Remotes; Per-Session Configuration; Collaborating over SSH; Limitations
Finding: Agents run on user-provided SSH hosts; remote CLI installation and credentials are prerequisites. Optional per-session shared history writes per-hostname JSONL files to the remote project, shown with hostname badges.
Retrieved: 2026-11-07

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/remote-control.md
Locator: Mobile Web Interface; Network Exposure
Finding: A browser/phone client uses the full host UI. URL token grants full control; LIVE-off returns loopback-only and rotates the token.
Retrieved: 2026-11-07

Source: https://docs.runmaestro.ai/maestro-cue-server
Locator: Before you start; Operate; Known limits
Finding: Cue can run exported pipelines on Linux/systemd or containers without a desktop or logged-in user. Agents use server-side logins and YOLO permissions. Run database stores activity without output; engine logs hold output. In-flight runs become failed after engine restart. Stopping SSH shell steps stops the SSH client, not the remote command.
Retrieved: 2026-11-07

Source: https://github.com/RunMaestro/Maestro/blob/1d462eb41f69e01bf848156e3c47997ad971c462/src/main/process-manager/ProcessManager.ts
Locator: spawn dispatch, lines 224-262; spawners/ChildProcessSpawner.ts lines 380-385; runners/SshCommandRunner.ts
Finding: Agent launch selects local PTY/child processes or SSH commands on a user-configured host. The inspected process-manager spawners and runners do not provision a vendor runtime or per-agent containers or VMs. A user may separately choose to run its host in a VM or container.
Retrieved: 2026-11-13

## maestro:RUN-02

Finding: Worktree agents use separate directories and branches. The scoped launcher starts local or SSH processes without provisioning per-agent containers or VMs.

Verification: sourced
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Not specified
Surface: desktop; ssh-remote
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

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

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/git-worktrees.md
Locator: Git menu; Worktree agents; Setup scripts
Finding: Git log/diff and PR actions integrate with nested worktree agents. Setup scripts run before first agent prompt, on the selected local/SSH host.
Retrieved: 2026-11-07

Source: https://github.com/RunMaestro/Maestro/blob/1d462eb41f69e01bf848156e3c47997ad971c462/src/main/process-manager/ProcessManager.ts
Locator: spawn dispatch, lines 224-262; spawners/ChildProcessSpawner.ts lines 380-385; runners/SshCommandRunner.ts
Finding: Agent launch selects local PTY/child processes or SSH commands on a user-configured host. The inspected process-manager spawners and runners do not provision a vendor runtime or per-agent containers or VMs. A user may separately choose to run its host in a VM or container.
Retrieved: 2026-11-13

## maestro:RUN-03

Finding: Agent Resilience pending retries do not survive quitting the app; Cue engine restarts mark in-flight runs failed, and Group Chat queues come back paused.

Verification: sourced
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Not specified
Surface: desktop; ssh-remote
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
service_restart and state_reconstruction come from the headless Cue server guide, which is absent from the pinned release source; released parity is unresolved.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/agent-resilience.md
Locator: Strategies; Never retry; Status card; Quit
Finding: Provider overload/quota errors retry with visible cards; credential/permission/crash failures do not. Pending retries do not survive app quit.
Retrieved: 2026-11-07

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/group-chat.md
Locator: Agent availability; Message queue; Remote agents
Finding: Group Chat moderators coordinate named local/remote agents. By default busy agents wait up to 15 minutes; disabling that safeguard permits concurrent file edits without a lock. Chat queues persist across reload/quit, restart paused, and retain failed sends until manual resume. Group chats can be deleted with their conversation history.
Retrieved: 2026-11-07

Source: https://docs.runmaestro.ai/maestro-cue-server
Locator: Before you start; Operate; Known limits
Finding: Cue can run exported pipelines on Linux/systemd or containers without a desktop or logged-in user. Agents use server-side logins and YOLO permissions. Run database stores activity without output; engine logs hold output. In-flight runs become failed after engine restart. Stopping SSH shell steps stops the SSH client, not the remote command.
Retrieved: 2026-11-07

## maestro:RUN-04

Finding: Worktree setup scripts prepare missing files before agents start.

Verification: agent-cross-checked
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Not specified
Surface: desktop; ssh-remote
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/git-worktrees.md
Locator: Git menu; Worktree agents; Setup scripts
Finding: Git log/diff and PR actions integrate with nested worktree agents. Setup scripts run before first agent prompt, on the selected local/SSH host.
Retrieved: 2026-11-07

## maestro:RUN-05

Finding: Maestro documents provider retries, per-run auto-resume caps and stalled-goal/document stops.

Verification: sourced
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Not specified
Surface: desktop; ssh-remote
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/agent-resilience.md
Locator: Strategies; Never retry; Status card; Quit
Finding: Provider overload/quota errors retry with visible cards; credential/permission/crash failures do not. Pending retries do not survive app quit.
Retrieved: 2026-11-07

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/autorun-playbooks.md
Locator: Creating Tasks; Running Multiple Auto Run Documents; How a Goal Run Stops; Steering a Run in Flight; Auto-Resume After an Error; Human-in-the-Loop Gates; Stalled Documents; Halt Marker
Finding: Goal runs stop on completion, deadlock, finite iteration cap or three stalled iterations. Desktop HITL markers pause until Done, Resume; CLI emits document_gated and skips the document. Three no-progress dispatches abandon a document. Halt markers stop the playbook and prevent replay until removed. Per-run auto-resume defaults to five attempts. Steering notes typed in the Thought Stream are delivered at the start of the next task. Checkboxes and the editor reopen while a run is paused; Reset on Completion keeps working copies in runs/.
Retrieved: 2026-11-07

## maestro:RUN-08

Finding: Group Chat queues busy agents and exposes explicit queue pause/resume. Resource-aware scheduling remains unknown.

Verification: agent-cross-checked
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Desktop local/SSH; headless Cue is separately documented with unresolved release parity
Surface: desktop; ssh-remote
Version: First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.

Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/group-chat.md
Locator: Agent availability; Message queue; Remote agents
Finding: Group Chat moderators coordinate named local/remote agents. By default busy agents wait up to 15 minutes; disabling that safeguard permits concurrent file edits without a lock. Chat queues persist across reload/quit, restart paused, and retain failed sends until manual resume. Group chats can be deleted with their conversation history.
Retrieved: 2026-11-07

## maestro:TEAM-01

Finding: Multiple people can prompt the same Maestro through browser clients. Optional Web Login attributes each browser message to its sender; browser agent/tab selections stay independent.

Verification: sourced
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Desktop local/SSH; headless Cue is separately documented with unresolved release parity
Surface: ssh-remote
Version: First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.

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

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/ssh-remote-execution.md
Locator: Overview; Configuring SSH Remotes; Per-Session Configuration; Collaborating over SSH; Limitations
Finding: Agents run on user-provided SSH hosts; remote CLI installation and credentials are prerequisites. Optional per-session shared history writes per-hostname JSONL files to the remote project, shown with hostname badges.
Retrieved: 2026-11-07

Source: https://github.com/RunMaestro/Maestro/blob/1d462eb41f69e01bf848156e3c47997ad971c462/docs/remote-control.md
Locator: Requiring a Login, lines 90-108
Finding: Multiple people can drive the same Maestro through optional Web Login. Browser prompts have per-user attribution and independent active tabs. The documentation explicitly says there are no roles; every account is an equal operator.
Retrieved: 2026-11-13

## maestro:TEAM-02

Finding: The scoped Web Login uses local username/password accounts. Every account is an equal operator, with no organization, project or task roles. Inspection of the web authentication implementation found no SAML, OIDC or other SSO integration.

Verification: sourced
Checked: 2026-11-13
Scheduled recheck: 2027-03-13
Plan: Not specified
Surface: desktop
Version: First-party source pass 2026-11-13; pinned code revisions are recorded in each cited source.

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

Source: https://github.com/RunMaestro/Maestro/blob/1d462eb41f69e01bf848156e3c47997ad971c462/docs/remote-control.md
Locator: Requiring a Login, lines 90-108
Finding: Multiple people can drive the same Maestro through optional Web Login. Browser prompts have per-user attribution and independent active tabs. The documentation explicitly says there are no roles; every account is an equal operator.
Retrieved: 2026-11-13

Source: https://github.com/RunMaestro/Maestro/blob/1d462eb41f69e01bf848156e3c47997ad971c462/src/main/web-server/auth/web-user-store.ts
Locator: WebUserRecord; WebSessionRecord; WebUserStore login/session methods
Finding: The scoped web authentication implementation persists local username/password accounts and browser sessions. Inspection of src/main/web-server/auth and routes/authRoutes.ts for SSO, SAML, OIDC and OAuth found no identity-provider login implementation.
Retrieved: 2026-11-13

## maestro:TEAM-03

Finding: Phone access uses a bearer URL token with full host control.

Verification: agent-cross-checked
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Not specified
Surface: desktop; ssh-remote
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/remote-control.md
Locator: Mobile Web Interface; Network Exposure
Finding: A browser/phone client uses the full host UI. URL token grants full control; LIVE-off returns loopback-only and rotates the token.
Retrieved: 2026-11-07

## maestro:TEAM-04

Finding: History persists summaries with session links, supports deletion and has a configured buffer.

Verification: sourced
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Not specified
Surface: desktop; ssh-remote
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/ssh-remote-execution.md
Locator: Overview; Configuring SSH Remotes; Per-Session Configuration; Collaborating over SSH; Limitations
Finding: Agents run on user-provided SSH hosts; remote CLI installation and credentials are prerequisites. Optional per-session shared history writes per-hostname JSONL files to the remote project, shown with hostname badges.
Retrieved: 2026-11-07

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/history.md
Locator: Entry types; Filters; Details
Finding: Timestamped AUTO/USER/AGENT/CUE entries can be searched and reopened by session ID; immutability is not established.
Retrieved: 2026-11-07

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/history.md
Locator: Entry types; Validated flag; Storage; Cross-host history
Finding: History links summaries, session IDs, timestamps and output. Validated is only a personal bookmark, not an execution gate. Entries can be deleted. JSON history defaults to 10000 entries per session; cross-host shared history is enabled per session through SSH Remote Execution.
Retrieved: 2026-11-07

## maestro:TEAM-05

Finding: Git menus and keyboard shortcuts expose diff and commit context.

Verification: agent-cross-checked
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Not specified
Surface: desktop; ssh-remote
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/git-worktrees.md
Locator: Git menu; Worktree agents; Setup scripts
Finding: Git log/diff and PR actions integrate with nested worktree agents. Setup scripts run before first agent prompt, on the selected local/SSH host.
Retrieved: 2026-11-07

## maestro:SHIP-01

Finding: History links completed Auto Run summaries to sessions and Git tools expose diffs.

Verification: agent-cross-checked
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Not specified
Surface: desktop; ssh-remote
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/git-worktrees.md
Locator: Git menu; Worktree agents; Setup scripts
Finding: Git log/diff and PR actions integrate with nested worktree agents. Setup scripts run before first agent prompt, on the selected local/SSH host.
Retrieved: 2026-11-07

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/history.md
Locator: Entry types; Filters; Details
Finding: Timestamped AUTO/USER/AGENT/CUE entries can be searched and reopened by session ID; immutability is not established.
Retrieved: 2026-11-07

## maestro:SHIP-02

Finding: Auto Run has human-gate and halt markers; History Validated is explicitly only a bookmark.

Verification: sourced
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Desktop local/SSH; headless Cue is separately documented with unresolved release parity
Surface: desktop; ssh-remote
Version: First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.

Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/autorun-playbooks.md
Locator: Creating Tasks; Running Multiple Auto Run Documents; How a Goal Run Stops; Steering a Run in Flight; Auto-Resume After an Error; Human-in-the-Loop Gates; Stalled Documents; Halt Marker
Finding: Goal runs stop on completion, deadlock, finite iteration cap or three stalled iterations. Desktop HITL markers pause until Done, Resume; CLI emits document_gated and skips the document. Three no-progress dispatches abandon a document. Halt markers stop the playbook and prevent replay until removed. Per-run auto-resume defaults to five attempts. Steering notes typed in the Thought Stream are delivered at the start of the next task. Checkboxes and the editor reopen while a run is paused; Reset on Completion keeps working copies in runs/.
Retrieved: 2026-11-07

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/history.md
Locator: Entry types; Validated flag; Storage; Cross-host history
Finding: History links summaries, session IDs, timestamps and output. Validated is only a personal bookmark, not an execution gate. Entries can be deleted. JSON history defaults to 10000 entries per session; cross-host shared history is enabled per session through SSH Remote Execution.
Retrieved: 2026-11-07

## maestro:SHIP-03

Finding: Git menu integrates worktrees, branch changes, push/pull and PR creation.

Verification: agent-cross-checked
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Not specified
Surface: desktop; ssh-remote
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/git-worktrees.md
Locator: Git menu; Worktree agents; Setup scripts
Finding: Git log/diff and PR actions integrate with nested worktree agents. Setup scripts run before first agent prompt, on the selected local/SSH host.
Retrieved: 2026-11-07

## maestro:OWN-01

Finding: Maestro root distribution uses AGPL-3.0.

Verification: agent-cross-checked
Checked: 2026-11-07
Scheduled recheck: 2027-02-05
Plan: Not specified
Surface: desktop; ssh-remote
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/LICENSE
Locator: Root license grant
Finding: The cited root license governs this repository distribution, subject to component notices.
Retrieved: 2026-11-07

## maestro:OWN-02

Finding: Maestro runs locally and can export Cue bundles for user-owned headless servers.

Verification: agent-cross-checked
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Desktop local/SSH; headless Cue is separately documented with unresolved release parity
Surface: desktop; Maestro Cue server
Version: First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.

Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
Headless Cue is documented online but absent from the pinned release source, as recorded in COORD-04; no released headless parity claim is made.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/README.md
Locator: How it works; Features; Quick start
Finding: Maestro passes prompts to locally configured provider CLIs and inherits their MCP tools, skills, permissions and authentication. Desktop installation supports user-owned operation. Its documentation MCP server searches docs rather than controlling tasks.
Retrieved: 2026-11-07

Source: https://docs.runmaestro.ai/maestro-cue-server
Locator: Before you start; Operate; Known limits
Finding: Cue can run exported pipelines on Linux/systemd or containers without a desktop or logged-in user. Agents use server-side logins and YOLO permissions. Run database stores activity without output; engine logs hold output. In-flight runs become failed after engine restart. Stopping SSH shell steps stops the SSH client, not the remote command.
Retrieved: 2026-11-07

## maestro:OWN-03

Finding: Anonymous check-in and optional folder sync have explicit data and conflict limits.

Verification: agent-cross-checked
Checked: 2026-11-07
Scheduled recheck: 2026-12-07
Plan: Not specified
Surface: desktop; ssh-remote
Version: First-party sources checked 2026-11-07; pinned implementations retain their cited revision.

The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
Cross-device sync is labelled Beta, supports one device at a time and has no conflict resolution.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/configuration.md
Locator: Anonymous Check-in; Storage; Sync
Finding: Update check sends UUID/version/platform/theme telemetry, disabled with update checking. Folder sync warns against simultaneous devices and has no conflict resolution.
Retrieved: 2026-11-07

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/README.md
Locator: How it works; Features; Quick start
Finding: Maestro passes prompts to locally configured provider CLIs and inherits their MCP tools, skills, permissions and authentication. Desktop installation supports user-owned operation. Its documentation MCP server searches docs rather than controlling tasks.
Retrieved: 2026-11-07

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/docs/configuration.md
Locator: Anonymous check-in; Cross-device sync
Finding: Update-linked anonymous check-ins exclude prompts, agent output, file paths and project names. Disabling startup update checks disables check-ins. Optional cloud-folder sync includes settings/sessions/groups; simultaneous devices can conflict with last write winning and no conflict resolution.
Retrieved: 2026-11-07

## maestro:OWN-04

Finding: Maestro is AGPL-3.0 open source and downloaded from GitHub Releases, with no price or paid plan published; model usage runs on your own provider accounts and plan quotas (e.g. Claude Max). Provider API keys can also fund model usage directly.

Verification: sourced
Checked: 2026-11-10
Scheduled recheck: 2026-11-24
Plan: Not specified
Surface: desktop; ssh-remote; Maestro Cue server
Version: First-party pricing sources read 2026-11-10

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

Source: https://runmaestro.ai/
Locator: 'The stage door' section; Legal footer (AGPL-3.0 License link); 'Elsewhere' (maestro-p)
Finding: Says Maestro is open source under AGPL-3.0. Downloads come from GitHub Releases, and the page shows no price or pricing page. maestro-p is described as running claude -p on your own Claude Max quota.
Retrieved: 2026-11-10

Source: https://docs.runmaestro.ai/llms.txt
Locator: Entries 'Multiple Accounts' and 'Agent Resilience'
Finding: The docs index describes running several accounts of the same provider and spreading work across their plan quotas, so model usage stays on your own provider accounts. No pricing page is listed.
Retrieved: 2026-11-10

Source: https://github.com/RunMaestro/Maestro/blob/1d462eb41f69e01bf848156e3c47997ad971c462/docs/provider-notes.md
Locator: Claude Code funding, lines 65-74
Finding: Claude Code can use the user subscription login or an API key, gateway or cloud-provider credential in the agent environment; API credentials are billed by their provider.
Retrieved: 2026-11-13

## maestro:OWN-06

Finding: Maestro has public issue support and released/RC scopes that differ.

Verification: sourced
Checked: 2026-11-07
Scheduled recheck: 2026-11-21
Plan: Desktop local/SSH; headless Cue is separately documented with unresolved release parity
Surface: desktop; ssh-remote
Version: First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.

Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

Source: https://github.com/RunMaestro/Maestro/blob/afd833d808cc3134ba9a2439f11513faf97c17e5/README.md
Locator: How it works; Features; Quick start
Finding: Maestro passes prompts to locally configured provider CLIs and inherits their MCP tools, skills, permissions and authentication. Desktop installation supports user-owned operation. Its documentation MCP server searches docs rather than controlling tasks.
Retrieved: 2026-11-07

## maestro:OWN-08

Finding: Maestro is a free AGPL-3.0 desktop download from GitHub Releases for macOS, Windows and Linux, and the website, README and licence show no paid tier. Model usage is paid separately through the user's own provider accounts.

Verification: agent-cross-checked
Checked: 2026-11-10
Scheduled recheck: 2026-11-24
Plan: Not specified
Surface: desktop
Version: v1.0.2

No installed-product test was run.
Card or account requirements for download were not checked beyond the public release page.

Source: https://github.com/RunMaestro/Maestro/blob/1d462eb41f69e01bf848156e3c47997ad971c462/README.md#L205-L207
Locator: README.md lines 205-207 (License section), commit 1d462eb
Finding: README states the project is under the AGPL-3.0 licence and does not mention any paid tier or price.
Retrieved: 2026-11-10

Source: https://github.com/RunMaestro/Maestro/releases/tag/v1.0.2
Locator: GitHub release v1.0.2 assets: maestro-1.0.2-arm64-mac.dmg, maestro-1.0.2-x64-mac.dmg, Maestro-Setup-1.0.2-x64.exe, Maestro-Portable-1.0.2-x64.exe, maestro-1.0.2-x86_64.AppImage, .deb, .rpm
Finding: The latest stable release publishes free downloadable installers for macOS, Windows and Linux on GitHub Releases.
Retrieved: 2026-11-10

Source: https://runmaestro.ai/
Locator: runmaestro.ai home page, fetched 2026-11-10
Finding: The website describes Maestro as open source under AGPL-3.0, downloaded from GitHub Releases, and shows no prices, paid plans, tiers, native phone apps, cloud service or team/SSO features.
Retrieved: 2026-11-10