Back to the Finder

multi-agent-shogun

Open-source Mac and Linux app. Agents run on your computer or on your own server.

Product websitegithub.com Compare with others Missing or wrong data?

multi-agent-shogun product interface, supplied by its publisher
Desktop app
Mac and Linux
Browser
Yes
Phone
Android and phone browser
Command line
Yes
Agents
Claude Code, Codex and OpenCode
Your subscription
Works with your own plan
Agents run
On your computer and on your own server
Laptop closed
Keeps going
Isolation
No
Parallel agents
Yes
Scheduled runs
Not listed
Coordinator agent
Yes
Built-in issues
Yes
Pull requests
No
Review screen
No
Team
Not listed
Self-hosting
Yes
Licence
MIT
Price from
Free
How it charges
No paid plan and bring your own key
Paid plans from
Not listed

Receipts

Checked
· oldest answer 2026-11-08
Findings
36 published · 29 cross-checked by a second agent · read them all
Sources
8 public pages on 1 site: github.com
Screenshot
github.com, retrieved · first party repository · shows appearance, not capability
Method
Same rules for all 103 researched ADEs. How we check · Report wrong data

What it does

Where you use it

Terminal workflow runs on Linux/macOS and WSL2; Android companion monitors and commands the remote formation. A supplied Python browser dashboard renders dashboard.md, including a phone-sized viewport. Windows execution requires WSL2 rather than a native Windows build.

Source and scope for Where you use it

Agents it runs

The v5.1.0 release supports five named coding CLIs in formation roles. Antigravity and Cursor appear in newer main-branch documentation; a released integration was not established.

Source and scope for Agents it runs

Accounts and subscriptions

CLI subscriptions are an explicit billing route; provider credentials stay with the CLI.

Source and scope for Accounts and subscriptions

Where agents run

Formation runs on a user host; Android reaches a Linux/WSL server over SSH.

Source and scope for Where agents run

How work is kept apart

The scoped formation launches separate tmux processes in host directories. It does not create Git worktrees or per-agent containers/VMs. Coding-harness sandbox modes are separate from formation isolation.

Source and scope for How work is kept apart

Parallel work

Multiple independent coding CLIs work concurrently in visible tmux panes.

Source and scope for Parallel work

Scheduled runs

Incoming ntfy commands can trigger agent work through a background listener.

Source and scope for Scheduled runs

Git and pull requests

The formation supplies Git branch-policy and short-lived branch auto-merge helpers. The inspected scripts have no native pull-request creation or management; agent guidance can discuss external PR review.

Source and scope for Git and pull requests

Licence and source

Repository source is MIT licensed.

Source and scope for Licence and source

Price

Software is free; existing coding-agent subscriptions/API usage and compute remain separate.

Source and scope for Price

JSON for agentsMarkdown for agents

Report wrong dataSuggest a missing ADE

Typed filters

Every value links to its receipt below. Read plan and surface restrictions before using a filter to decide.

Typed filter values
FilterValue
Desktop OS: macOSYes
Desktop OS: WindowsNo
Desktop OS: LinuxYes
Web clientYes
Phone access: Native iOSNo
Phone access: Native AndroidYes
Phone access: Phone browserYes
CLIYes cross-checked
Coding agents: Claude CodeYes cross-checked
Coding agents: CodexYes cross-checked
Coding agents: Cursor AgentNo
Coding agents: Gemini CLINo
Coding agents: OpenCodeYes cross-checked
Coding agents: PiNo
Coding agents: GrokNo
Coding agents: AiderNo
Coding agents: AntigravityNo
Use my subscriptionYes cross-checked
Where agents run: On your computerYes cross-checked
Where agents run: On your own serverYes cross-checked
Where agents run: In the vendor's cloudNo
Workspace isolation: Git worktreeNo
Workspace isolation: ContainerNo
Workspace isolation: VM or microVMNo
Parallel runsYes cross-checked
CoordinatorYes cross-checked
Native issue trackingYes cross-checked
Unattended triggersUnknown
Shared promptingUnknown
Team rolesNo
SSONo
Pull request workflowNo
Review interfaceNo
Product license: Apache-2.0No. MIT cross-checked
Product license: MITYes. MIT cross-checked
Product license: GPL-3.0No. MIT cross-checked
Product license: GPL-3.0-or-laterNo. MIT cross-checked
Product license: AGPL-3.0No. MIT cross-checked
Product license: AGPL-3.0-or-laterNo. MIT cross-checked
Product license: Elastic License 2.0No. MIT cross-checked
Product license: Custom termsNo. MIT cross-checked
Product license: ProprietaryNo. MIT cross-checked
Self-hostingYes cross-checked
Telemetry opt-outNo
Free accessYes cross-checked
Starting price: FreeYes. Free cross-checked
Starting price: Up to $20/monthNo. Free cross-checked
Starting price: $21–40/monthNo. Free cross-checked
Starting price: $41–100/monthNo. Free cross-checked
Starting price: Over $100/monthNo. Free cross-checked
Starting price: Contact for pricingNo. Free cross-checked
Pricing model: Free, no paid planYes cross-checked
Pricing model: Free planNo
Pricing model: SubscriptionNo
Pricing model: Per seatNo
Pricing model: Usage-basedNo
Pricing model: Per machine or computeNo
Pricing model: Bring your own keyYes
Pricing model: One-time purchaseNo
Paid plans from: No paid planUnknown
Paid plans from: $10 or less/monthUnknown
Paid plans from: $11–20/monthUnknown
Paid plans from: $21–40/monthUnknown
Paid plans from: $41–100/monthUnknown
Paid plans from: Over $100/monthUnknown
Paid plans from: Contact salesUnknown
Lifecycle status: ActiveUnknown
Lifecycle status: SunsettingUnknown
Keeps going with laptop closedYes
Open-source licenseYes. MIT cross-checked
Any desktop appYes
Paid plan up to $20/monthUnknown
Paid plan up to $40/monthUnknown
Any phone clientYes

Filter receipts

Desktop OS: macOS: Yes

Desktop OS: macOS

Typed value: Yes.

Terminal workflow runs on Linux/macOS and WSL2; Android companion monitors and commands the remote formation. A supplied Python browser dashboard renders dashboard.md, including a phone-sized viewport. Windows execution requires WSL2 rather than a native Windows build.

  • Mobile apps: Android companion APK via SSH; no iOS app.
  • Cli: Bash scripts and tmux terminal clients.
  • Task actions: Android terminal, agent grid and dashboard can monitor and send commands.
  • Notifications: ntfy progress notifications and incoming command listener.
  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Desktop OS: Windows: No

Desktop OS: Windows

Typed value: No.

Terminal workflow runs on Linux/macOS and WSL2; Android companion monitors and commands the remote formation. A supplied Python browser dashboard renders dashboard.md, including a phone-sized viewport. Windows execution requires WSL2 rather than a native Windows build.

  • Mobile apps: Android companion APK via SSH; no iOS app.
  • Cli: Bash scripts and tmux terminal clients.
  • Task actions: Android terminal, agent grid and dashboard can monitor and send commands.
  • Notifications: ntfy progress notifications and incoming command listener.
  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Desktop OS: Linux: Yes

Desktop OS: Linux

Typed value: Yes.

Terminal workflow runs on Linux/macOS and WSL2; Android companion monitors and commands the remote formation. A supplied Python browser dashboard renders dashboard.md, including a phone-sized viewport. Windows execution requires WSL2 rather than a native Windows build.

  • Mobile apps: Android companion APK via SSH; no iOS app.
  • Cli: Bash scripts and tmux terminal clients.
  • Task actions: Android terminal, agent grid and dashboard can monitor and send commands.
  • Notifications: ntfy progress notifications and incoming command listener.
  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Web client: Yes

Web client

Typed value: Yes.

Terminal workflow runs on Linux/macOS and WSL2; Android companion monitors and commands the remote formation. A supplied Python browser dashboard renders dashboard.md, including a phone-sized viewport. Windows execution requires WSL2 rather than a native Windows build.

  • Browser: The supplied dashboard-viewer.py serves an auto-refreshing read-only browser work dashboard.
  • Mobile browser: The same dashboard declares a device-width viewport and serves the work dashboard over HTTP.
  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
  1. Shogun browser dashboard

    Finding: The supplied Python HTTP server renders dashboard.md in a browser with auto-refresh and a device-width viewport. It is a read-only task/report dashboard; its scoped routes and rendering do not provide proposed-code diff review or prompt submission.

Phone access: Native iOS: No

Phone access: Native iOS

Typed value: No.

Terminal workflow runs on Linux/macOS and WSL2; Android companion monitors and commands the remote formation. A supplied Python browser dashboard renders dashboard.md, including a phone-sized viewport. Windows execution requires WSL2 rather than a native Windows build.

  • Mobile apps: Android companion APK via SSH; no iOS app.
  • Cli: Bash scripts and tmux terminal clients.
  • Task actions: Android terminal, agent grid and dashboard can monitor and send commands.
  • Notifications: ntfy progress notifications and incoming command listener.
  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Phone access: Native Android: Yes

Phone access: Native Android

Typed value: Yes.

Terminal workflow runs on Linux/macOS and WSL2; Android companion monitors and commands the remote formation. A supplied Python browser dashboard renders dashboard.md, including a phone-sized viewport. Windows execution requires WSL2 rather than a native Windows build.

  • Mobile apps: Android companion APK via SSH; no iOS app.
  • Cli: Bash scripts and tmux terminal clients.
  • Task actions: Android terminal, agent grid and dashboard can monitor and send commands.
  • Notifications: ntfy progress notifications and incoming command listener.
  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Phone access: Phone browser: Yes

Phone access: Phone browser

Typed value: Yes.

Terminal workflow runs on Linux/macOS and WSL2; Android companion monitors and commands the remote formation. A supplied Python browser dashboard renders dashboard.md, including a phone-sized viewport. Windows execution requires WSL2 rather than a native Windows build.

  • Browser: The supplied dashboard-viewer.py serves an auto-refreshing read-only browser work dashboard.
  • Mobile browser: The same dashboard declares a device-width viewport and serves the work dashboard over HTTP.
  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
  1. Shogun browser dashboard

    Finding: The supplied Python HTTP server renders dashboard.md in a browser with auto-refresh and a device-width viewport. It is a read-only task/report dashboard; its scoped routes and rendering do not provide proposed-code diff review or prompt submission.

CLI: Yes cross-checked

CLI

Typed value: Yes.

Shell scripts and YAML files expose formation control and status.

  • Cli: Startup script, agent status script and mailbox tools.
  • Operations: Launch formation, inspect panes/status and send YAML mailbox messages.
  • Authentication: Provider CLI login and SSH for phone access.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Coding agents: Claude Code: Yes cross-checked

Coding agents: Claude Code

Typed value: Yes.

The v5.1.0 release supports five named coding CLIs in formation roles. Antigravity and Cursor appear in newer main-branch documentation; a released integration was not established.

  • Session integration: Independent CLI instances in tmux panes; shared templates generate role-specific instructions.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  • Antigravity and Cursor are main-branch additions in the checked documentation; their released harness support remains unknown.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Coding agents: Codex: Yes cross-checked

Coding agents: Codex

Typed value: Yes.

The v5.1.0 release supports five named coding CLIs in formation roles. Antigravity and Cursor appear in newer main-branch documentation; a released integration was not established.

  • Session integration: Independent CLI instances in tmux panes; shared templates generate role-specific instructions.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  • Antigravity and Cursor are main-branch additions in the checked documentation; their released harness support remains unknown.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Coding agents: Cursor Agent: No

Coding agents: Cursor Agent

Typed value: No.

The v5.1.0 release supports five named coding CLIs in formation roles. Antigravity and Cursor appear in newer main-branch documentation; a released integration was not established.

  • Harnesses: The v5.1.0 release supports Claude Code, Codex, Copilot, Kimi Code and OpenCode. Released Antigravity and Cursor support is unknown; their documented integrations occur on a later main revision.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  • Antigravity and Cursor are main-branch additions in the checked documentation; their released harness support remains unknown.
  1. multi-agent-shogun Antigravity support at v5.1.0

    Finding: The latest release v5.1.0 documents Claude Code, Codex, Copilot, Kimi and OpenCode. Antigravity appears in newer main-branch documentation, but was not established in this released snapshot.

Coding agents: Gemini CLI: No

Coding agents: Gemini CLI

Typed value: No.

The v5.1.0 release supports five named coding CLIs in formation roles. Antigravity and Cursor appear in newer main-branch documentation; a released integration was not established.

  • Harnesses: The v5.1.0 release supports Claude Code, Codex, Copilot, Kimi Code and OpenCode. Released Antigravity and Cursor support is unknown; their documented integrations occur on a later main revision.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  • Antigravity and Cursor are main-branch additions in the checked documentation; their released harness support remains unknown.
  1. multi-agent-shogun Antigravity support at v5.1.0

    Finding: The latest release v5.1.0 documents Claude Code, Codex, Copilot, Kimi and OpenCode. Antigravity appears in newer main-branch documentation, but was not established in this released snapshot.

Coding agents: OpenCode: Yes cross-checked

Coding agents: OpenCode

Typed value: Yes.

The v5.1.0 release supports five named coding CLIs in formation roles. Antigravity and Cursor appear in newer main-branch documentation; a released integration was not established.

  • Session integration: Independent CLI instances in tmux panes; shared templates generate role-specific instructions.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  • Antigravity and Cursor are main-branch additions in the checked documentation; their released harness support remains unknown.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Coding agents: Pi: No

Coding agents: Pi

Typed value: No.

The v5.1.0 release supports five named coding CLIs in formation roles. Antigravity and Cursor appear in newer main-branch documentation; a released integration was not established.

  • Harnesses: The v5.1.0 release supports Claude Code, Codex, Copilot, Kimi Code and OpenCode. Released Antigravity and Cursor support is unknown; their documented integrations occur on a later main revision.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  • Antigravity and Cursor are main-branch additions in the checked documentation; their released harness support remains unknown.
  1. multi-agent-shogun Antigravity support at v5.1.0

    Finding: The latest release v5.1.0 documents Claude Code, Codex, Copilot, Kimi and OpenCode. Antigravity appears in newer main-branch documentation, but was not established in this released snapshot.

Coding agents: Grok: No

Coding agents: Grok

Typed value: No.

The v5.1.0 release supports five named coding CLIs in formation roles. Antigravity and Cursor appear in newer main-branch documentation; a released integration was not established.

  • Harnesses: The v5.1.0 release supports Claude Code, Codex, Copilot, Kimi Code and OpenCode. Released Antigravity and Cursor support is unknown; their documented integrations occur on a later main revision.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  • Antigravity and Cursor are main-branch additions in the checked documentation; their released harness support remains unknown.
  1. multi-agent-shogun Antigravity support at v5.1.0

    Finding: The latest release v5.1.0 documents Claude Code, Codex, Copilot, Kimi and OpenCode. Antigravity appears in newer main-branch documentation, but was not established in this released snapshot.

Coding agents: Aider: No

Coding agents: Aider

Typed value: No.

The v5.1.0 release supports five named coding CLIs in formation roles. Antigravity and Cursor appear in newer main-branch documentation; a released integration was not established.

  • Harnesses: The v5.1.0 release supports Claude Code, Codex, Copilot, Kimi Code and OpenCode. Released Antigravity and Cursor support is unknown; their documented integrations occur on a later main revision.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  • Antigravity and Cursor are main-branch additions in the checked documentation; their released harness support remains unknown.
  1. multi-agent-shogun Antigravity support at v5.1.0

    Finding: The latest release v5.1.0 documents Claude Code, Codex, Copilot, Kimi and OpenCode. Antigravity appears in newer main-branch documentation, but was not established in this released snapshot.

Coding agents: Antigravity: No

Coding agents: Antigravity

Typed value: No.

The v5.1.0 release supports five named coding CLIs in formation roles. Antigravity and Cursor appear in newer main-branch documentation; a released integration was not established.

  • Harnesses: The v5.1.0 release supports Claude Code, Codex, Copilot, Kimi Code and OpenCode. Released Antigravity and Cursor support is unknown; their documented integrations occur on a later main revision.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  • Antigravity and Cursor are main-branch additions in the checked documentation; their released harness support remains unknown.
  1. multi-agent-shogun Antigravity support at v5.1.0

    Finding: The latest release v5.1.0 documents Claude Code, Codex, Copilot, Kimi and OpenCode. Antigravity appears in newer main-branch documentation, but was not established in this released snapshot.

Use my subscription: Yes cross-checked

Use my subscription

Typed value: Yes.

CLI subscriptions are an explicit billing route; provider credentials stay with the CLI.

  • Agent subscriptions: README discusses flat-rate coding-agent subscriptions and cost_group plan routing.
  • Api accounts: OpenCode may use provider API keys configured in its own account.
  • Provider restrictions: Provider auth is outside settings.yaml; no claim of unlimited subscription usage.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Where agents run: On your computer: Yes cross-checked

Where agents run: On your computer

Typed value: Yes.

Formation runs on a user host; Android reaches a Linux/WSL server over SSH.

  • Local: tmux and agent CLIs run on local host.
  • Byo remote: Android prerequisites explicitly include a Linux server with SSH.
  • Other device continuation: Phone monitors and commands server tmux sessions.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Where agents run: On your own server: Yes cross-checked

Where agents run: On your own server

Typed value: Yes.

Formation runs on a user host; Android reaches a Linux/WSL server over SSH.

  • Local: tmux and agent CLIs run on local host.
  • Byo remote: Android prerequisites explicitly include a Linux server with SSH.
  • Other device continuation: Phone monitors and commands server tmux sessions.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Where agents run: In the vendor's cloud: No

Where agents run: In the vendor's cloud

Typed value: No.

Formation runs on a user host; Android reaches a Linux/WSL server over SSH.

  • Local: tmux and agent CLIs run on local host.
  • Byo remote: Android prerequisites explicitly include a Linux server with SSH.
  • Other device continuation: Phone monitors and commands server tmux sessions.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Workspace isolation: Git worktree: No

Workspace isolation: Git worktree

Typed value: No.

The scoped formation launches separate tmux processes in host directories. It does not create Git worktrees or per-agent containers/VMs. Coding-harness sandbox modes are separate from formation isolation.

  • Worktree: The inspected formation launcher and script/lib runtime do not provision worktree isolation.
  • Container: The inspected formation launcher and script/lib runtime do not provision container isolation.
  • Vm: The inspected formation launcher and script/lib runtime do not provision vm isolation.
  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
  1. Shogun formation launcher

    Finding: The scoped launcher creates detached tmux sessions/panes and starts installed coding CLIs in the host working directory. Inspection of launcher, lib and scripts found no product-created worktrees, per-agent containers or VMs, vendor-runtime provisioner, or human workspace-role/SSO system.

Workspace isolation: Container: No

Workspace isolation: Container

Typed value: No.

The scoped formation launches separate tmux processes in host directories. It does not create Git worktrees or per-agent containers/VMs. Coding-harness sandbox modes are separate from formation isolation.

  • Worktree: The inspected formation launcher and script/lib runtime do not provision worktree isolation.
  • Container: The inspected formation launcher and script/lib runtime do not provision container isolation.
  • Vm: The inspected formation launcher and script/lib runtime do not provision vm isolation.
  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
  1. Shogun formation launcher

    Finding: The scoped launcher creates detached tmux sessions/panes and starts installed coding CLIs in the host working directory. Inspection of launcher, lib and scripts found no product-created worktrees, per-agent containers or VMs, vendor-runtime provisioner, or human workspace-role/SSO system.

Workspace isolation: VM or microVM: No

Workspace isolation: VM or microVM

Typed value: No.

The scoped formation launches separate tmux processes in host directories. It does not create Git worktrees or per-agent containers/VMs. Coding-harness sandbox modes are separate from formation isolation.

  • Worktree: The inspected formation launcher and script/lib runtime do not provision worktree isolation.
  • Container: The inspected formation launcher and script/lib runtime do not provision container isolation.
  • Vm: The inspected formation launcher and script/lib runtime do not provision vm isolation.
  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
  1. Shogun formation launcher

    Finding: The scoped launcher creates detached tmux sessions/panes and starts installed coding CLIs in the host working directory. Inspection of launcher, lib and scripts found no product-created worktrees, per-agent containers or VMs, vendor-runtime provisioner, or human workspace-role/SSO system.

Parallel runs: Yes cross-checked

Parallel runs

Typed value: Yes.

Multiple independent coding CLIs work concurrently in visible tmux panes.

  • Concurrent sessions: Formation includes seven workers, strategist and coordinating roles.
  • Status visibility: Live panes, status command and dashboard show progress.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Coordinator: Yes cross-checked

Coordinator

Typed value: Yes.

Product scripts and role instructions coordinate independent CLIs through durable YAML mailboxes.

  • Roles: Shogun, Karo, Ashigaru and Gunshi.
  • Messages: YAML mailbox with inotify events and short tmux nudges.
  • Results return: Reports aggregate in dashboard.md.
  • Cross harness: Configured per-role coding CLIs.
  • Orchestration owner: Shogun shell scripts and generated role instructions, not provider-native children.
  • Live progress: Visible tmux panes and status summaries.
  • Retained results: Task/report YAML survives restarts.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Native issue tracking: Yes cross-checked

Native issue tracking

Typed value: Yes.

Native YAML tasks persist separately from CLI sessions; UI is terminal/Markdown rather than a rich tracker.

  • Create: Shogun/Karo generate local tasks.
  • Prioritize: SayTask parses dates/priorities for personal tasks; separate from coding dispatch.
  • Task session separation: Stable subtask records are assigned to worker panes.
  • Durable states: YAML task status and dashboard aggregation.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Team roles: No

Team roles

Typed value: No.

The scoped formation is operated through the host OS, terminal/SSH and optional ntfy credentials. Agent hierarchy roles are prompts for agents; the formation has no named human workspace roles or enterprise SSO implementation.

  • Organization roles: No human organization roles system is implemented in the scoped launcher, configuration or communication scripts.
  • Project roles: No human project roles system is implemented in the scoped launcher, configuration or communication scripts.
  • Task roles: No human task roles system is implemented in the scoped launcher, configuration or communication scripts.
  • Sso: No human sso system is implemented in the scoped launcher, configuration or communication scripts.
  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
  1. Shogun formation launcher

    Finding: The scoped launcher creates detached tmux sessions/panes and starts installed coding CLIs in the host working directory. Inspection of launcher, lib and scripts found no product-created worktrees, per-agent containers or VMs, vendor-runtime provisioner, or human workspace-role/SSO system.

  2. Shogun configuration and outbound communication

    Finding: Bounded inspection found no product telemetry emitter/disable setting or enterprise SSO implementation. Optional ntfy sends task notifications or receives commands using topic token/basic authentication; coding-harness/provider telemetry remains separate.

SSO: No

SSO

Typed value: No.

The scoped formation is operated through the host OS, terminal/SSH and optional ntfy credentials. Agent hierarchy roles are prompts for agents; the formation has no named human workspace roles or enterprise SSO implementation.

  • Organization roles: No human organization roles system is implemented in the scoped launcher, configuration or communication scripts.
  • Project roles: No human project roles system is implemented in the scoped launcher, configuration or communication scripts.
  • Task roles: No human task roles system is implemented in the scoped launcher, configuration or communication scripts.
  • Sso: No human sso system is implemented in the scoped launcher, configuration or communication scripts.
  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
  1. Shogun configuration and outbound communication

    Finding: Bounded inspection found no product telemetry emitter/disable setting or enterprise SSO implementation. Optional ntfy sends task notifications or receives commands using topic token/basic authentication; coding-harness/provider telemetry remains separate.

Pull request workflow: No

Pull request workflow

Typed value: No.

The formation supplies Git branch-policy and short-lived branch auto-merge helpers. The inspected scripts have no native pull-request creation or management; agent guidance can discuss external PR review.

  • Branches: Branch policy lists monitored repositories and allowed long-lived branches.
  • Pull requests: The supplied branch scripts use Git merge/push without a PR API or PR management interface.
  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
  1. Shogun branch merge helper

    Finding: The product supplies Git branch policy and short-lived branch merge helpers. The inspected scripts do not create or manage pull requests; pull-request review appears as agent prompt guidance, not a product PR integration.

Review interface: No

Review interface

Typed value: No.

Task reports and artifacts remain in local files. The supplied browser dashboard displays Markdown task/report status, without a proposed-code diff review interface.

  • Diffs: The scoped dashboard renders dashboard.md and refresh status, without a code-diff review component.
  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
  1. Shogun browser dashboard

    Finding: The supplied Python HTTP server renders dashboard.md in a browser with auto-refresh and a device-width viewport. It is a read-only task/report dashboard; its scoped routes and rendering do not provide proposed-code diff review or prompt submission.

Product license: Apache-2.0: No. MIT cross-checked

Product license: Apache-2.0

Typed value: No. MIT.

Repository source is MIT licensed.

  • Client license: MIT.
  • Source visibility: Public source.
  • Source revision: aff8dc8495da26a2aad582257457655fa953b57e
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun LICENSE

    Finding: MIT grant covers the repository at pinned revision.

Product license: MIT: Yes. MIT cross-checked

Product license: MIT

Typed value: Yes. MIT.

Repository source is MIT licensed.

  • Client license: MIT.
  • Source visibility: Public source.
  • Source revision: aff8dc8495da26a2aad582257457655fa953b57e
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun LICENSE

    Finding: MIT grant covers the repository at pinned revision.

Product license: GPL-3.0: No. MIT cross-checked

Product license: GPL-3.0

Typed value: No. MIT.

Repository source is MIT licensed.

  • Client license: MIT.
  • Source visibility: Public source.
  • Source revision: aff8dc8495da26a2aad582257457655fa953b57e
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun LICENSE

    Finding: MIT grant covers the repository at pinned revision.

Product license: GPL-3.0-or-later: No. MIT cross-checked

Product license: GPL-3.0-or-later

Typed value: No. MIT.

Repository source is MIT licensed.

  • Client license: MIT.
  • Source visibility: Public source.
  • Source revision: aff8dc8495da26a2aad582257457655fa953b57e
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun LICENSE

    Finding: MIT grant covers the repository at pinned revision.

Product license: AGPL-3.0: No. MIT cross-checked

Product license: AGPL-3.0

Typed value: No. MIT.

Repository source is MIT licensed.

  • Client license: MIT.
  • Source visibility: Public source.
  • Source revision: aff8dc8495da26a2aad582257457655fa953b57e
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun LICENSE

    Finding: MIT grant covers the repository at pinned revision.

Product license: AGPL-3.0-or-later: No. MIT cross-checked

Product license: AGPL-3.0-or-later

Typed value: No. MIT.

Repository source is MIT licensed.

  • Client license: MIT.
  • Source visibility: Public source.
  • Source revision: aff8dc8495da26a2aad582257457655fa953b57e
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun LICENSE

    Finding: MIT grant covers the repository at pinned revision.

Product license: Elastic License 2.0: No. MIT cross-checked

Product license: Elastic License 2.0

Typed value: No. MIT.

Repository source is MIT licensed.

  • Client license: MIT.
  • Source visibility: Public source.
  • Source revision: aff8dc8495da26a2aad582257457655fa953b57e
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun LICENSE

    Finding: MIT grant covers the repository at pinned revision.

Product license: Custom terms: No. MIT cross-checked

Product license: Custom terms

Typed value: No. MIT.

Repository source is MIT licensed.

  • Client license: MIT.
  • Source visibility: Public source.
  • Source revision: aff8dc8495da26a2aad582257457655fa953b57e
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun LICENSE

    Finding: MIT grant covers the repository at pinned revision.

Product license: Proprietary: No. MIT cross-checked

Product license: Proprietary

Typed value: No. MIT.

Repository source is MIT licensed.

  • Client license: MIT.
  • Source visibility: Public source.
  • Source revision: aff8dc8495da26a2aad582257457655fa953b57e
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun LICENSE

    Finding: MIT grant covers the repository at pinned revision.

Self-hosting: Yes cross-checked

Self-hosting

Typed value: Yes.

Shell/tmux formation and Android SSH companion run on user-controlled infrastructure.

  • Self hosting: Clone/run on Linux/macOS/WSL2 or Linux server.
  • Vendor dependencies: Model-provider account and optional ntfy/Google speech services are separate.
  • Formats: Tasks/reports in YAML and Markdown.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Telemetry opt-out: No

Telemetry opt-out

Typed value: No.

The scoped configuration and runtime scripts expose no product telemetry emitter or telemetry-disable setting. Optional ntfy traffic is task notification/command transport; coding-harness privacy and telemetry remain separate.

  • Telemetry defaults: No product telemetry emitter was found in the bounded configuration/lib/scripts inspection.
  • Telemetry controls: No documented product telemetry-disable control is implemented in the inspected configuration and runtime.
  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
  1. Shogun configuration and outbound communication

    Finding: Bounded inspection found no product telemetry emitter/disable setting or enterprise SSO implementation. Optional ntfy sends task notifications or receives commands using topic token/basic authentication; coding-harness/provider telemetry remains separate.

Free access: Yes cross-checked

Free access

Typed value: Yes.

Free source and Android companion support local evaluation; agent accounts are separate.

  • Ongoing free: README explicitly says everything is free and open source.
  • Self host cost: User machine/server and coding-agent costs remain separate.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Starting price: Free: Yes. Free cross-checked

Starting price: Free

Typed value: Yes. Free.

Software is free; existing coding-agent subscriptions/API usage and compute remain separate.

  • Included usage: Free open-source formation and companion.
  • Model cost: Coding-agent subscription or API charges remain external.
  • Compute cost: User host/remote server.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Starting price: Up to $20/month: No. Free cross-checked

Starting price: Up to $20/month

Typed value: No. Free.

Software is free; existing coding-agent subscriptions/API usage and compute remain separate.

  • Included usage: Free open-source formation and companion.
  • Model cost: Coding-agent subscription or API charges remain external.
  • Compute cost: User host/remote server.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Starting price: $21–40/month: No. Free cross-checked

Starting price: $21–40/month

Typed value: No. Free.

Software is free; existing coding-agent subscriptions/API usage and compute remain separate.

  • Included usage: Free open-source formation and companion.
  • Model cost: Coding-agent subscription or API charges remain external.
  • Compute cost: User host/remote server.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Starting price: $41–100/month: No. Free cross-checked

Starting price: $41–100/month

Typed value: No. Free.

Software is free; existing coding-agent subscriptions/API usage and compute remain separate.

  • Included usage: Free open-source formation and companion.
  • Model cost: Coding-agent subscription or API charges remain external.
  • Compute cost: User host/remote server.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Starting price: Over $100/month: No. Free cross-checked

Starting price: Over $100/month

Typed value: No. Free.

Software is free; existing coding-agent subscriptions/API usage and compute remain separate.

  • Included usage: Free open-source formation and companion.
  • Model cost: Coding-agent subscription or API charges remain external.
  • Compute cost: User host/remote server.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Starting price: Contact for pricing: No. Free cross-checked

Starting price: Contact for pricing

Typed value: No. Free.

Software is free; existing coding-agent subscriptions/API usage and compute remain separate.

  • Included usage: Free open-source formation and companion.
  • Model cost: Coding-agent subscription or API charges remain external.
  • Compute cost: User host/remote server.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Pricing model: Free, no paid plan: Yes cross-checked

Pricing model: Free, no paid plan

Typed value: Yes.

Software is free; existing coding-agent subscriptions/API usage and compute remain separate.

  • Included usage: Free open-source formation and companion.
  • Model cost: Coding-agent subscription or API charges remain external.
  • Compute cost: User host/remote server.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Pricing model: Free plan: No

Pricing model: Free plan

Typed value: No.

Software is free; existing coding-agent subscriptions/API usage and compute remain separate.

  • Included usage: Free open-source formation and companion.
  • Model cost: Coding-agent subscription or API charges remain external.
  • Compute cost: User host/remote server.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Pricing model: Subscription: No

Pricing model: Subscription

Typed value: No.

Software is free; existing coding-agent subscriptions/API usage and compute remain separate.

  • Included usage: Free open-source formation and companion.
  • Model cost: Coding-agent subscription or API charges remain external.
  • Compute cost: User host/remote server.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Pricing model: Per seat: No

Pricing model: Per seat

Typed value: No.

Software is free; existing coding-agent subscriptions/API usage and compute remain separate.

  • Included usage: Free open-source formation and companion.
  • Model cost: Coding-agent subscription or API charges remain external.
  • Compute cost: User host/remote server.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Pricing model: Usage-based: No

Pricing model: Usage-based

Typed value: No.

Software is free; existing coding-agent subscriptions/API usage and compute remain separate.

  • Included usage: Free open-source formation and companion.
  • Model cost: Coding-agent subscription or API charges remain external.
  • Compute cost: User host/remote server.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Pricing model: Per machine or compute: No

Pricing model: Per machine or compute

Typed value: No.

Software is free; existing coding-agent subscriptions/API usage and compute remain separate.

  • Included usage: Free open-source formation and companion.
  • Model cost: Coding-agent subscription or API charges remain external.
  • Compute cost: User host/remote server.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Pricing model: Bring your own key: Yes

Pricing model: Bring your own key

Typed value: Yes.

Software is free; existing coding-agent subscriptions/API usage and compute remain separate.

  • Included usage: Free open-source formation and companion.
  • Model cost: Coding-agent subscription or API charges remain external.
  • Compute cost: User host/remote server.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Pricing model: One-time purchase: No

Pricing model: One-time purchase

Typed value: No.

Software is free; existing coding-agent subscriptions/API usage and compute remain separate.

  • Included usage: Free open-source formation and companion.
  • Model cost: Coding-agent subscription or API charges remain external.
  • Compute cost: User host/remote server.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Keeps going with laptop closed: Yes

Keeps going with laptop closed

Typed value: Yes.

Formation runs on a user host; Android reaches a Linux/WSL server over SSH.

  • Local: tmux and agent CLIs run on local host.
  • Byo remote: Android prerequisites explicitly include a Linux server with SSH.
  • Other device continuation: Phone monitors and commands server tmux sessions.
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Open-source license: Yes. MIT cross-checked

Open-source license

Typed value: Yes. MIT.

Repository source is MIT licensed.

  • Client license: MIT.
  • Source visibility: Public source.
  • Source revision: aff8dc8495da26a2aad582257457655fa953b57e
  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun LICENSE

    Finding: MIT grant covers the repository at pinned revision.

Any desktop app: Yes

Any desktop app

Typed value: Yes.

Terminal workflow runs on Linux/macOS and WSL2; Android companion monitors and commands the remote formation. A supplied Python browser dashboard renders dashboard.md, including a phone-sized viewport. Windows execution requires WSL2 rather than a native Windows build.

  • Mobile apps: Android companion APK via SSH; no iOS app.
  • Cli: Bash scripts and tmux terminal clients.
  • Task actions: Android terminal, agent grid and dashboard can monitor and send commands.
  • Notifications: ntfy progress notifications and incoming command listener.
  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

Any phone client: Yes

Any phone client

Typed value: Yes.

Terminal workflow runs on Linux/macOS and WSL2; Android companion monitors and commands the remote formation. A supplied Python browser dashboard renders dashboard.md, including a phone-sized viewport. Windows execution requires WSL2 rather than a native Windows build.

  • Mobile apps: Android companion APK via SSH; no iOS app.
  • Cli: Bash scripts and tmux terminal clients.
  • Task actions: Android terminal, agent grid and dashboard can monitor and send commands.
  • Notifications: ntfy progress notifications and incoming command listener.
  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

All public findings

Findings may summarize a source. They are not presented as verbatim statements.

multi-agent-shogun:ACC-01: Terminal workflow runs on Linux/macOS and WSL2; Android companion monitors and commands the remote formation. A supplied Python browser dashboard renders dashboard.md, including a phone-sized viewport. Windows execution requires WSL2 rather than a native Windows build.

multi-agent-shogun:ACC-01

Terminal workflow runs on Linux/macOS and WSL2; Android companion monitors and commands the remote formation. A supplied Python browser dashboard renders dashboard.md, including a phone-sized viewport. Windows execution requires WSL2 rather than a native Windows build.

  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

  2. Shogun browser dashboard

    Finding: The supplied Python HTTP server renders dashboard.md in a browser with auto-refresh and a device-width viewport. It is a read-only task/report dashboard; its scoped routes and rendering do not provide proposed-code diff review or prompt submission.

multi-agent-shogun:ACC-02: The v5.1.0 release supports five named coding CLIs in formation roles. Antigravity and Cursor appear in newer main-branch documentation; a released integration was not established. cross-checked

multi-agent-shogun:ACC-02

The v5.1.0 release supports five named coding CLIs in formation roles. Antigravity and Cursor appear in newer main-branch documentation; a released integration was not established.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  • Antigravity and Cursor are main-branch additions in the checked documentation; their released harness support remains unknown.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

  2. multi-agent-shogun Antigravity support at v5.1.0

    Finding: The latest release v5.1.0 documents Claude Code, Codex, Copilot, Kimi and OpenCode. Antigravity appears in newer main-branch documentation, but was not established in this released snapshot.

multi-agent-shogun:ACC-03: CLI subscriptions are an explicit billing route; provider credentials stay with the CLI. cross-checked

multi-agent-shogun:ACC-03

CLI subscriptions are an explicit billing route; provider credentials stay with the CLI.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:ACC-04: Setup requires tmux, Bash 4+ and at least one authenticated coding CLI. cross-checked

multi-agent-shogun:ACC-04

Setup requires tmux, Bash 4+ and at least one authenticated coding CLI.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:ACC-05: Shell scripts and YAML files expose formation control and status. cross-checked

multi-agent-shogun:ACC-05

Shell scripts and YAML files expose formation control and status.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:ACC-06: Memory MCP and generated instruction files extend the formation. cross-checked

multi-agent-shogun:ACC-06

Memory MCP and generated instruction files extend the formation.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:PLAN-01: Human commands become local YAML queue records and dashboard summaries. cross-checked

multi-agent-shogun:PLAN-01

Human commands become local YAML queue records and dashboard summaries.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:PLAN-02: Tasks and reports are structured local files; plan revision guarantees remain untested. cross-checked

multi-agent-shogun:PLAN-02

Tasks and reports are structured local files; plan revision guarantees remain untested.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:PLAN-03: Task blockedBy dependencies and role hierarchy are documented. cross-checked

multi-agent-shogun:PLAN-03

Task blockedBy dependencies and role hierarchy are documented.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:PLAN-04: Layered file context and Memory MCP persist across clear/new sessions. cross-checked

multi-agent-shogun:PLAN-04

Layered file context and Memory MCP persist across clear/new sessions.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:PLAN-06: Native YAML tasks persist separately from CLI sessions; UI is terminal/Markdown rather than a rich tracker. cross-checked

multi-agent-shogun:PLAN-06

Native YAML tasks persist separately from CLI sessions; UI is terminal/Markdown rather than a rich tracker.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:PLAN-07: Agents write shared YAML task and report records, with serialized mailbox writes. cross-checked

multi-agent-shogun:PLAN-07

Agents write shared YAML task and report records, with serialized mailbox writes.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:COORD-01: Multiple independent coding CLIs work concurrently in visible tmux panes. cross-checked

multi-agent-shogun:COORD-01

Multiple independent coding CLIs work concurrently in visible tmux panes.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:COORD-02: Karo routes tasks and owns dashboard aggregation; routing is not a verified exclusive work claim. cross-checked

multi-agent-shogun:COORD-02

Karo routes tasks and owns dashboard aggregation; routing is not a verified exclusive work claim.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:COORD-03: Product scripts and role instructions coordinate independent CLIs through durable YAML mailboxes. cross-checked

multi-agent-shogun:COORD-03

Product scripts and role instructions coordinate independent CLIs through durable YAML mailboxes.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:COORD-04: Incoming ntfy commands can trigger agent work through a background listener. cross-checked

multi-agent-shogun:COORD-04

Incoming ntfy commands can trigger agent work through a background listener.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:COORD-05: Human commands and phone notifications support intervention; a pause/resume fixture was not run. cross-checked

multi-agent-shogun:COORD-05

Human commands and phone notifications support intervention; a pause/resume fixture was not run.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:COORD-06: Live panes, Markdown dashboard and Android grid show formation work. cross-checked

multi-agent-shogun:COORD-06

Live panes, Markdown dashboard and Android grid show formation work.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:COORD-07: Formation and per-agent CLI/model selection are configurable. cross-checked

multi-agent-shogun:COORD-07

Formation and per-agent CLI/model selection are configurable.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:RUN-01: Formation runs on a user host; Android reaches a Linux/WSL server over SSH. cross-checked

multi-agent-shogun:RUN-01

Formation runs on a user host; Android reaches a Linux/WSL server over SSH.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:RUN-02: The scoped formation launches separate tmux processes in host directories. It does not create Git worktrees or per-agent containers/VMs. Coding-harness sandbox modes are separate from formation isolation.

multi-agent-shogun:RUN-02

The scoped formation launches separate tmux processes in host directories. It does not create Git worktrees or per-agent containers/VMs. Coding-harness sandbox modes are separate from formation isolation.

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

    Finding: The scoped launcher creates detached tmux sessions/panes and starts installed coding CLIs in the host working directory. Inspection of launcher, lib and scripts found no product-created worktrees, per-agent containers or VMs, vendor-runtime provisioner, or human workspace-role/SSO system.

multi-agent-shogun:RUN-03: Task/mailbox/context files persist independently of agent session memory. cross-checked

multi-agent-shogun:RUN-03

Task/mailbox/context files persist independently of agent session memory.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:RUN-06: Status script and dashboard expose worker, task and inbox state. cross-checked

multi-agent-shogun:RUN-06

Status script and dashboard expose worker, task and inbox state.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:TEAM-01: The scoped formation has a single human Lord workflow and local terminal/SSH or ntfy command input. It supplies no native multi-user workspace, per-human membership or shared-prompting interface.

multi-agent-shogun:TEAM-01

The scoped formation has a single human Lord workflow and local terminal/SSH or ntfy command input. It supplies no native multi-user workspace, per-human membership or shared-prompting interface.

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

    Finding: The scoped launcher creates detached tmux sessions/panes and starts installed coding CLIs in the host working directory. Inspection of launcher, lib and scripts found no product-created worktrees, per-agent containers or VMs, vendor-runtime provisioner, or human workspace-role/SSO system.

  2. Shogun browser dashboard

    Finding: The supplied Python HTTP server renders dashboard.md in a browser with auto-refresh and a device-width viewport. It is a read-only task/report dashboard; its scoped routes and rendering do not provide proposed-code diff review or prompt submission.

multi-agent-shogun:TEAM-02: The scoped formation is operated through the host OS, terminal/SSH and optional ntfy credentials. Agent hierarchy roles are prompts for agents; the formation has no named human workspace roles or enterprise SSO implementation.

multi-agent-shogun:TEAM-02

The scoped formation is operated through the host OS, terminal/SSH and optional ntfy credentials. Agent hierarchy roles are prompts for agents; the formation has no named human workspace roles or enterprise SSO implementation.

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

    Finding: The scoped launcher creates detached tmux sessions/panes and starts installed coding CLIs in the host working directory. Inspection of launcher, lib and scripts found no product-created worktrees, per-agent containers or VMs, vendor-runtime provisioner, or human workspace-role/SSO system.

  2. Shogun configuration and outbound communication

    Finding: Bounded inspection found no product telemetry emitter/disable setting or enterprise SSO implementation. Optional ntfy sends task notifications or receives commands using topic token/basic authentication; coding-harness/provider telemetry remains separate.

multi-agent-shogun:TEAM-03: Quick start explicitly launches Claude in bypass-permissions mode; role files are not a complete security sandbox. cross-checked

multi-agent-shogun:TEAM-03

Quick start explicitly launches Claude in bypass-permissions mode; role files are not a complete security sandbox.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:TEAM-04: Instructions and reports remain plain files available for inspection and Git history. cross-checked

multi-agent-shogun:TEAM-04

Instructions and reports remain plain files available for inspection and Git history.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:SHIP-01: Task reports and artifacts remain in local files. The supplied browser dashboard displays Markdown task/report status, without a proposed-code diff review interface.

multi-agent-shogun:SHIP-01

Task reports and artifacts remain in local files. The supplied browser dashboard displays Markdown task/report status, without a proposed-code diff review interface.

  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

  2. Shogun browser dashboard

    Finding: The supplied Python HTTP server renders dashboard.md in a browser with auto-refresh and a device-width viewport. It is a read-only task/report dashboard; its scoped routes and rendering do not provide proposed-code diff review or prompt submission.

multi-agent-shogun:SHIP-02: Role guidance routes quality review to Gunshi and final judgment to Karo. cross-checked

multi-agent-shogun:SHIP-02

Role guidance routes quality review to Gunshi and final judgment to Karo.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:SHIP-03: The formation supplies Git branch-policy and short-lived branch auto-merge helpers. The inspected scripts have no native pull-request creation or management; agent guidance can discuss external PR review.

multi-agent-shogun:SHIP-03

The formation supplies Git branch-policy and short-lived branch auto-merge helpers. The inspected scripts have no native pull-request creation or management; agent guidance can discuss external PR review.

  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
  1. Shogun branch merge helper

    Finding: The product supplies Git branch policy and short-lived branch merge helpers. The inspected scripts do not create or manage pull requests; pull-request review appears as agent prompt guidance, not a product PR integration.

multi-agent-shogun:OWN-01: Repository source is MIT licensed. cross-checked

multi-agent-shogun:OWN-01

Repository source is MIT licensed.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun LICENSE

    Finding: MIT grant covers the repository at pinned revision.

multi-agent-shogun:OWN-02: Shell/tmux formation and Android SSH companion run on user-controlled infrastructure. cross-checked

multi-agent-shogun:OWN-02

Shell/tmux formation and Android SSH companion run on user-controlled infrastructure.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:OWN-03: The scoped configuration and runtime scripts expose no product telemetry emitter or telemetry-disable setting. Optional ntfy traffic is task notification/command transport; coding-harness privacy and telemetry remain separate.

multi-agent-shogun:OWN-03

The scoped configuration and runtime scripts expose no product telemetry emitter or telemetry-disable setting. Optional ntfy traffic is task notification/command transport; coding-harness privacy and telemetry remain separate.

  • Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.
  1. Shogun configuration and outbound communication

    Finding: Bounded inspection found no product telemetry emitter/disable setting or enterprise SSO implementation. Optional ntfy sends task notifications or receives commands using topic token/basic authentication; coding-harness/provider telemetry remains separate.

multi-agent-shogun:OWN-04: Software is free; existing coding-agent subscriptions/API usage and compute remain separate. cross-checked

multi-agent-shogun:OWN-04

Software is free; existing coding-agent subscriptions/API usage and compute remain separate.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

multi-agent-shogun:OWN-06: Author names a successor but explicitly says this project continues to work as-is. cross-checked

multi-agent-shogun:OWN-06

Author names a successor but explicitly says this project continues to work as-is.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.

  2. multi-agent-shogun v5.1.0 release

    Finding: Release published 23 May 2026. August README note points to kagemusha while saying multi-agent-shogun continues to work as-is.

multi-agent-shogun:OWN-08: Free source and Android companion support local evaluation; agent accounts are separate. cross-checked

multi-agent-shogun:OWN-08

Free source and Android companion support local evaluation; agent accounts are separate.

  • Documentation establishes only the named facts. Unknown atomic questions and unrun scenarios remain open.
  1. multi-agent-shogun README.md

    Finding: Shell/tmux agents coordinate through YAML queues and mailbox events. Shogun delegates to Karo, seven Ashigaru workers and Gunshi strategist. Android app connects over SSH; Windows needs WSL2.