Claude Squad
Open-source desktop app for Mac, Windows and Linux. Agents run on your computer.
Product websitesmtg-ai.github.io Compare with others Missing or wrong data?
- Desktop app
- Mac, Windows and Linux
- Browser
- No
- Phone
- No
- Command line
- Yes
- Agents
- Claude Code, Codex, Gemini CLI, OpenCode and Aider
- Your subscription
- Works with your own plan
- Agents run
- On your computer
- Laptop closed
- No
- Isolation
- Worktree
- Parallel agents
- Yes
- Scheduled runs
- No
- Coordinator agent
- No
- Built-in issues
- No
- Pull requests
- No
- Review screen
- Yes
- Team
- No
- Self-hosting
- Yes
- Licence
- AGPL-3.0
- Price from
- Free
- How it charges
- No paid plan and bring your own key
- Paid plans from
- Not listed
Receipts
- Checked
- · oldest answer 2026-11-07
- Findings
- 30 published · 20 cross-checked by a second agent · read them all
- Sources
- 17 public pages on 2 sites: github.com, smtg-ai.github.io
- 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
Claude Squad ships native terminal UI builds for macOS, Linux and Windows. The pinned distribution supplies no product web-session client or native iOS/Android app.
Source and scope for Where you use itAgents it runs
Squad launches configurable terminal agent commands and profiles; the official repository also names OpenCode and Amp.
Source and scope for Agents it runsAccounts and subscriptions
Agent credentials are supplied to the selected CLI.
Source and scope for Accounts and subscriptionsWhere agents run
Squad starts tmux and coding-agent processes on its current host. No vendor-managed agent compute is implemented; tmux detachment does not keep work running when that execution host sleeps or stops.
Source and scope for Where agents runHow work is kept apart
Each task uses a local tmux session and Git worktree. The inspected session/git and tmux implementation has no product-managed container or VM isolation.
Source and scope for How work is kept apartParallel work
Squad documents simultaneous background agent sessions.
Source and scope for Parallel workScheduled runs
New work is initiated from the TUI. The pinned source has no scheduled or external-event starter; periodic app timers monitor sessions, and AutoYes responds within an already-running task.
Source and scope for Scheduled runsGit and pull requests
Squad commits and pushes branches and can open the branch in a browser. The pinned Git action code does not create or manage pull requests.
Source and scope for Git and pull requestsPrice
No price or paid plan is published; Claude Squad is AGPL-3.0 open source and agent/model usage (e.g. an OpenAI API key for Codex) is paid to the provider.
Source and scope for PriceTyped filters
Every value links to its receipt below. Read plan and surface restrictions before using a filter to decide.
| Filter | Value |
|---|---|
| Desktop OS: macOS | Yes |
| Desktop OS: Windows | Yes |
| Desktop OS: Linux | Yes |
| Web client | No |
| Phone access: Native iOS | No |
| Phone access: Native Android | No |
| Phone access: Phone browser | No |
| CLI | Yes |
| Coding agents: Claude Code | Yes cross-checked |
| Coding agents: Codex | Yes cross-checked |
| Coding agents: Cursor Agent | Unknown |
| Coding agents: Gemini CLI | Yes cross-checked |
| Coding agents: OpenCode | Yes cross-checked |
| Coding agents: Pi | Unknown |
| Coding agents: Grok | Unknown |
| Coding agents: Aider | Yes cross-checked |
| Coding agents: Antigravity | Unknown |
| Use my subscription | Yes cross-checked |
| Where agents run: On your computer | Yes |
| Where agents run: On your own server | Unknown |
| Where agents run: In the vendor's cloud | No |
| Workspace isolation: Git worktree | Yes |
| Workspace isolation: Container | No |
| Workspace isolation: VM or microVM | No |
| Parallel runs | Yes cross-checked |
| Coordinator | No |
| Native issue tracking | No |
| Unattended triggers | No |
| Shared prompting | No |
| Team roles | No |
| SSO | No |
| Pull request workflow | No |
| Review interface | Yes cross-checked |
| Product license: Apache-2.0 | No. AGPL-3.0 cross-checked |
| Product license: MIT | No. AGPL-3.0 cross-checked |
| Product license: GPL-3.0 | No. AGPL-3.0 cross-checked |
| Product license: GPL-3.0-or-later | No. AGPL-3.0 cross-checked |
| Product license: AGPL-3.0 | Yes. AGPL-3.0 cross-checked |
| Product license: AGPL-3.0-or-later | No. AGPL-3.0 cross-checked |
| Product license: Elastic License 2.0 | No. AGPL-3.0 cross-checked |
| Product license: Custom terms | No. AGPL-3.0 cross-checked |
| Product license: Proprietary | No. AGPL-3.0 cross-checked |
| Self-hosting | Yes cross-checked |
| Telemetry opt-out | No |
| Free access | Yes cross-checked |
| Starting price: Free | Yes. Free cross-checked |
| Starting price: Up to $20/month | No. Free cross-checked |
| Starting price: $21–40/month | No. Free cross-checked |
| Starting price: $41–100/month | No. Free cross-checked |
| Starting price: Over $100/month | No. Free cross-checked |
| Starting price: Contact for pricing | No. Free cross-checked |
| Pricing model: Free, no paid plan | Yes |
| Pricing model: Free plan | No |
| Pricing model: Subscription | No |
| Pricing model: Per seat | No |
| Pricing model: Usage-based | No |
| Pricing model: Per machine or compute | No |
| Pricing model: Bring your own key | Yes cross-checked |
| Pricing model: One-time purchase | No |
| Paid plans from: No paid plan | Unknown |
| Paid plans from: $10 or less/month | Unknown |
| Paid plans from: $11–20/month | Unknown |
| Paid plans from: $21–40/month | Unknown |
| Paid plans from: $41–100/month | Unknown |
| Paid plans from: Over $100/month | Unknown |
| Paid plans from: Contact sales | Unknown |
| Lifecycle status: Active | Unknown |
| Lifecycle status: Sunsetting | Unknown |
| Keeps going with laptop closed | No |
| Open-source license | Yes. AGPL-3.0 cross-checked |
| Any desktop app | Yes |
| Paid plan up to $20/month | Unknown |
| Paid plan up to $40/month | Unknown |
| Any phone client | No |
Filter receipts
Desktop OS: macOS: Yes
Desktop OS: macOS
Typed value: Yes.
Claude Squad ships native terminal UI builds for macOS, Linux and Windows. The pinned distribution supplies no product web-session client or native iOS/Android app.
- Desktop os: Public release archives include macOS, Linux and Windows on amd64/arm64; terminal UI requires its tmux/git environment.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: The public release provides darwin, linux and windows archives for amd64 and arm64. The application is a terminal UI using tmux and git, not a standalone graphical desktop app.
Desktop OS: Windows: Yes
Desktop OS: Windows
Typed value: Yes.
Claude Squad ships native terminal UI builds for macOS, Linux and Windows. The pinned distribution supplies no product web-session client or native iOS/Android app.
- Desktop os: Public release archives include macOS, Linux and Windows on amd64/arm64; terminal UI requires its tmux/git environment.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: The public release provides darwin, linux and windows archives for amd64 and arm64. The application is a terminal UI using tmux and git, not a standalone graphical desktop app.
Desktop OS: Linux: Yes
Desktop OS: Linux
Typed value: Yes.
Claude Squad ships native terminal UI builds for macOS, Linux and Windows. The pinned distribution supplies no product web-session client or native iOS/Android app.
- Desktop os: Public release archives include macOS, Linux and Windows on amd64/arm64; terminal UI requires its tmux/git environment.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: The public release provides darwin, linux and windows archives for amd64 and arm64. The application is a terminal UI using tmux and git, not a standalone graphical desktop app.
Web client: No
Web client
Typed value: No.
Claude Squad ships native terminal UI builds for macOS, Linux and Windows. The pinned distribution supplies no product web-session client or native iOS/Android app.
- Mobile apps: The Go terminal distribution has no native iOS/Android application.
- Browser: The inspected web directory is website boilerplate and does not implement a released agent-session client.
- Mobile browser: The pinned application has no phone browser session interface.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: The executable is a local Bubble Tea terminal UI that creates and attaches tmux sessions, sends prompts and renders diffs. The repository has no product web-session interface, native phone app, human account/member system, SSO integration or telemetry configuration. The web directory is website boilerplate, not a released session client.
Phone access: Native iOS: No
Phone access: Native iOS
Typed value: No.
Claude Squad ships native terminal UI builds for macOS, Linux and Windows. The pinned distribution supplies no product web-session client or native iOS/Android app.
- Mobile apps: The Go terminal distribution has no native iOS/Android application.
- Browser: The inspected web directory is website boilerplate and does not implement a released agent-session client.
- Mobile browser: The pinned application has no phone browser session interface.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: The executable is a local Bubble Tea terminal UI that creates and attaches tmux sessions, sends prompts and renders diffs. The repository has no product web-session interface, native phone app, human account/member system, SSO integration or telemetry configuration. The web directory is website boilerplate, not a released session client.
Phone access: Native Android: No
Phone access: Native Android
Typed value: No.
Claude Squad ships native terminal UI builds for macOS, Linux and Windows. The pinned distribution supplies no product web-session client or native iOS/Android app.
- Mobile apps: The Go terminal distribution has no native iOS/Android application.
- Browser: The inspected web directory is website boilerplate and does not implement a released agent-session client.
- Mobile browser: The pinned application has no phone browser session interface.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: The executable is a local Bubble Tea terminal UI that creates and attaches tmux sessions, sends prompts and renders diffs. The repository has no product web-session interface, native phone app, human account/member system, SSO integration or telemetry configuration. The web directory is website boilerplate, not a released session client.
Phone access: Phone browser: No
Phone access: Phone browser
Typed value: No.
Claude Squad ships native terminal UI builds for macOS, Linux and Windows. The pinned distribution supplies no product web-session client or native iOS/Android app.
- Mobile apps: The Go terminal distribution has no native iOS/Android application.
- Browser: The inspected web directory is website boilerplate and does not implement a released agent-session client.
- Mobile browser: The pinned application has no phone browser session interface.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: The executable is a local Bubble Tea terminal UI that creates and attaches tmux sessions, sends prompts and renders diffs. The repository has no product web-session interface, native phone app, human account/member system, SSO integration or telemetry configuration. The web directory is website boilerplate, not a released session client.
CLI: Yes
CLI
Typed value: Yes.
Claude Squad ships native terminal UI builds for macOS, Linux and Windows. The pinned distribution supplies no product web-session client or native iOS/Android app.
- Cli: cs terminal UI.
- Task actions: Create, attach, reprompt, pause/check out and resume sessions.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
Coding agents: Claude Code: Yes cross-checked
Coding agents: Claude Code
Typed value: Yes.
Squad launches configurable terminal agent commands and profiles; the official repository also names OpenCode and Amp.
- Harnesses: Claude Code, Codex, Gemini and Aider.
- Custom adapters: Custom -p program and named profiles.
- Session integration: tmux launches the configured command.
- Mixed harness operation: Multiple named profiles are documented; no mixed-harness run was observed.
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
Coding agents: Codex: Yes cross-checked
Coding agents: Codex
Typed value: Yes.
Squad launches configurable terminal agent commands and profiles; the official repository also names OpenCode and Amp.
- Harnesses: Claude Code, Codex, Gemini and Aider.
- Custom adapters: Custom -p program and named profiles.
- Session integration: tmux launches the configured command.
- Mixed harness operation: Multiple named profiles are documented; no mixed-harness run was observed.
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
Coding agents: Gemini CLI: Yes cross-checked
Coding agents: Gemini CLI
Typed value: Yes.
Squad launches configurable terminal agent commands and profiles; the official repository also names OpenCode and Amp.
- Harnesses: Claude Code, Codex, Gemini and Aider.
- Custom adapters: Custom -p program and named profiles.
- Session integration: tmux launches the configured command.
- Mixed harness operation: Multiple named profiles are documented; no mixed-harness run was observed.
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
Coding agents: OpenCode: Yes cross-checked
Coding agents: OpenCode
Typed value: Yes.
Squad launches configurable terminal agent commands and profiles; the official repository also names OpenCode and Amp.
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Claude Squad official repository description
Finding: Official repository describes managing multiple AI terminal agents like Claude Code, Codex, OpenCode and Amp. README separately documents configurable -p commands and named program profiles.
Coding agents: Aider: Yes cross-checked
Coding agents: Aider
Typed value: Yes.
Squad launches configurable terminal agent commands and profiles; the official repository also names OpenCode and Amp.
- Harnesses: Claude Code, Codex, Gemini and Aider.
- Custom adapters: Custom -p program and named profiles.
- Session integration: tmux launches the configured command.
- Mixed harness operation: Multiple named profiles are documented; no mixed-harness run was observed.
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
Use my subscription: Yes cross-checked
Use my subscription
Typed value: Yes.
Agent credentials are supplied to the selected CLI.
- Agent subscriptions: Sessions launch the user's installed agent CLI (default claude) unmodified in tmux, so that CLI's own sign-in, including a subscription login, applies. Not tested; per-provider plan terms not checked.
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Claude Squad tmux session start
Finding: Each session runs the configured program command (default claude) unmodified inside a new tmux session in the task worktree, so the installed agent CLI uses its own stored sign-in.
Where agents run: On your computer: Yes
Where agents run: On your computer
Typed value: Yes.
Squad starts tmux and coding-agent processes on its current host. No vendor-managed agent compute is implemented; tmux detachment does not keep work running when that execution host sleeps or stops.
- Local: Local terminal processes.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
Where agents run: In the vendor's cloud: No
Where agents run: In the vendor's cloud
Typed value: No.
Squad starts tmux and coding-agent processes on its current host. No vendor-managed agent compute is implemented; tmux detachment does not keep work running when that execution host sleeps or stops.
- Managed cloud: No vendor compute provisioner in the pinned native execution paths.
- Client disconnect: Detaching the TUI preserves its local tmux process, but sleeping/stopping the execution host stops useful work.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: The app runs tmux new-session on its current host with a Git worktree as cwd. Built-in execution has no vendor compute provisioner, container runtime or VM launcher. Tmux detachment preserves processes only while that execution host stays running.
Workspace isolation: Git worktree: Yes
Workspace isolation: Git worktree
Typed value: Yes.
Each task uses a local tmux session and Git worktree. The inspected session/git and tmux implementation has no product-managed container or VM isolation.
- Branch: Separate branch.
- Worktree: Separate Git worktree per task.
- Filesystem: Git worktrees separate each session code directory.
- Process: Separate tmux terminal session.
- Code separation: Each session works on its own branch and Git worktree.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
Workspace isolation: Container: No
Workspace isolation: Container
Typed value: No.
Each task uses a local tmux session and Git worktree. The inspected session/git and tmux implementation has no product-managed container or VM isolation.
- Container: The built-in execution path starts tmux on the host, without container provisioning.
- Vm: No VM launcher or per-task VM isolation exists in the inspected runtime.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: The app runs tmux new-session on its current host with a Git worktree as cwd. Built-in execution has no vendor compute provisioner, container runtime or VM launcher. Tmux detachment preserves processes only while that execution host stays running.
Workspace isolation: VM or microVM: No
Workspace isolation: VM or microVM
Typed value: No.
Each task uses a local tmux session and Git worktree. The inspected session/git and tmux implementation has no product-managed container or VM isolation.
- Container: The built-in execution path starts tmux on the host, without container provisioning.
- Vm: No VM launcher or per-task VM isolation exists in the inspected runtime.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: The app runs tmux new-session on its current host with a Git worktree as cwd. Built-in execution has no vendor compute provisioner, container runtime or VM launcher. Tmux detachment preserves processes only while that execution host stays running.
Parallel runs: Yes cross-checked
Parallel runs
Typed value: Yes.
Squad documents simultaneous background agent sessions.
- Concurrent sessions: Multiple tasks at once in separate terminal workspaces.
- Status visibility: Session list, preview and diff tabs; status correctness untested.
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
Coordinator: No
Coordinator
Typed value: No.
The pinned TUI lets a human create and prompt terminal agents. It supplies no coordinator agent role with delegation and communication tools; underlying agent subagents and arbitrary custom commands are separate.
- Orchestration owner: The app manages tmux instances through human UI actions and has no agent-facing delegation/coordinator protocol.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: Persistent InstanceData stores session title, path, branch, status, program, worktree and diff state. Human UI actions create sessions. There is no separate issue/task store, product coordinator role/delegation tool, schedule/webhook starter or team user input transport. AutoYes acknowledges prompts in an existing session rather than starting a new task.
Native issue tracking: No
Native issue tracking
Typed value: No.
Squad persists agent session records, not a separate native issue or task backlog. Inspection of storage, app actions and config found no independent issue entities or state transitions.
- Create: There is no separate native issue/task creation path in the pinned app/storage implementation.
- Task session separation: Stored title/status records are agent instances themselves, not separate tasks.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: Persistent InstanceData stores session title, path, branch, status, program, worktree and diff state. Human UI actions create sessions. There is no separate issue/task store, product coordinator role/delegation tool, schedule/webhook starter or team user input transport. AutoYes acknowledges prompts in an existing session rather than starting a new task.
Unattended triggers: No
Unattended triggers
Typed value: No.
New work is initiated from the TUI. The pinned source has no scheduled or external-event starter; periodic app timers monitor sessions, and AutoYes responds within an already-running task.
- Schedules: No schedule-based work starter in app/cmd/config/session source.
- Events: No external event/webhook work starter in the pinned app.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: Persistent InstanceData stores session title, path, branch, status, program, worktree and diff state. Human UI actions create sessions. There is no separate issue/task store, product coordinator role/delegation tool, schedule/webhook starter or team user input transport. AutoYes acknowledges prompts in an existing session rather than starting a new task.
Shared prompting: No
Shared prompting
Typed value: No.
The pinned local TUI has no product transport or account model for several humans to prompt the same agent work. Sharing a terminal through an external tmux/SSH setup is outside the product collaboration feature.
- Coprompting: The app input path belongs to one local terminal UI; no native multi-user prompt channel is implemented.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: The executable is a local Bubble Tea terminal UI that creates and attaches tmux sessions, sends prompts and renders diffs. The repository has no product web-session interface, native phone app, human account/member system, SSO integration or telemetry configuration. The web directory is website boilerplate, not a released session client.
-
Finding: Persistent InstanceData stores session title, path, branch, status, program, worktree and diff state. Human UI actions create sessions. There is no separate issue/task store, product coordinator role/delegation tool, schedule/webhook starter or team user input transport. AutoYes acknowledges prompts in an existing session rather than starting a new task.
Team roles: No
Team roles
Typed value: No.
Squad stores local configuration and sessions with no human workspace membership, named role model or enterprise SSO in the pinned application.
- Organization roles: No workspace/organization user role model in app/config/session source.
- Sso: No SSO/SAML/OIDC integration in the pinned Go application.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: The executable is a local Bubble Tea terminal UI that creates and attaches tmux sessions, sends prompts and renders diffs. The repository has no product web-session interface, native phone app, human account/member system, SSO integration or telemetry configuration. The web directory is website boilerplate, not a released session client.
SSO: No
SSO
Typed value: No.
Squad stores local configuration and sessions with no human workspace membership, named role model or enterprise SSO in the pinned application.
- Organization roles: No workspace/organization user role model in app/config/session source.
- Sso: No SSO/SAML/OIDC integration in the pinned Go application.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: The executable is a local Bubble Tea terminal UI that creates and attaches tmux sessions, sends prompts and renders diffs. The repository has no product web-session interface, native phone app, human account/member system, SSO integration or telemetry configuration. The web directory is website boilerplate, not a released session client.
Pull request workflow: No
Pull request workflow
Typed value: No.
Squad commits and pushes branches and can open the branch in a browser. The pinned Git action code does not create or manage pull requests.
- Pull requests: PushChanges and OpenBranchURL operate on branches, not PR create/update/review/merge operations.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: PushChanges commits, pushes/syncs the branch with git/gh repo sync and optionally opens gh browse --branch. Bounded inspection of the Git/session action code found no PR create/update/review/merge management call.
Review interface: Yes cross-checked
Review interface
Typed value: Yes.
Claude Squad exposes diffs and stores session diff data; wider artifact retention remains unknown.
- Diffs: Diff tab.
- 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.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
Product license: Apache-2.0: No. AGPL-3.0 cross-checked
Product license: Apache-2.0
Typed value: No. AGPL-3.0.
Squad source is AGPL-3.0.
- Client license: AGPL-3.0, subject to component notices.
- Source visibility: Public repository.
- Source revision: ce1ffb4392b01f38e2c4599c7c84d2a93973b138
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: The cited root license governs this repository distribution, subject to component notices.
Product license: MIT: No. AGPL-3.0 cross-checked
Product license: MIT
Typed value: No. AGPL-3.0.
Squad source is AGPL-3.0.
- Client license: AGPL-3.0, subject to component notices.
- Source visibility: Public repository.
- Source revision: ce1ffb4392b01f38e2c4599c7c84d2a93973b138
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: The cited root license governs this repository distribution, subject to component notices.
Product license: GPL-3.0: No. AGPL-3.0 cross-checked
Product license: GPL-3.0
Typed value: No. AGPL-3.0.
Squad source is AGPL-3.0.
- Client license: AGPL-3.0, subject to component notices.
- Source visibility: Public repository.
- Source revision: ce1ffb4392b01f38e2c4599c7c84d2a93973b138
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: The cited root license governs this repository distribution, subject to component notices.
Product license: GPL-3.0-or-later: No. AGPL-3.0 cross-checked
Product license: GPL-3.0-or-later
Typed value: No. AGPL-3.0.
Squad source is AGPL-3.0.
- Client license: AGPL-3.0, subject to component notices.
- Source visibility: Public repository.
- Source revision: ce1ffb4392b01f38e2c4599c7c84d2a93973b138
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: The cited root license governs this repository distribution, subject to component notices.
Product license: AGPL-3.0: Yes. AGPL-3.0 cross-checked
Product license: AGPL-3.0
Typed value: Yes. AGPL-3.0.
Squad source is AGPL-3.0.
- Client license: AGPL-3.0, subject to component notices.
- Source visibility: Public repository.
- Source revision: ce1ffb4392b01f38e2c4599c7c84d2a93973b138
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: The cited root license governs this repository distribution, subject to component notices.
Product license: AGPL-3.0-or-later: No. AGPL-3.0 cross-checked
Product license: AGPL-3.0-or-later
Typed value: No. AGPL-3.0.
Squad source is AGPL-3.0.
- Client license: AGPL-3.0, subject to component notices.
- Source visibility: Public repository.
- Source revision: ce1ffb4392b01f38e2c4599c7c84d2a93973b138
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: The cited root license governs this repository distribution, subject to component notices.
Product license: Elastic License 2.0: No. AGPL-3.0 cross-checked
Product license: Elastic License 2.0
Typed value: No. AGPL-3.0.
Squad source is AGPL-3.0.
- Client license: AGPL-3.0, subject to component notices.
- Source visibility: Public repository.
- Source revision: ce1ffb4392b01f38e2c4599c7c84d2a93973b138
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: The cited root license governs this repository distribution, subject to component notices.
Product license: Custom terms: No. AGPL-3.0 cross-checked
Product license: Custom terms
Typed value: No. AGPL-3.0.
Squad source is AGPL-3.0.
- Client license: AGPL-3.0, subject to component notices.
- Source visibility: Public repository.
- Source revision: ce1ffb4392b01f38e2c4599c7c84d2a93973b138
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: The cited root license governs this repository distribution, subject to component notices.
Product license: Proprietary: No. AGPL-3.0 cross-checked
Product license: Proprietary
Typed value: No. AGPL-3.0.
Squad source is AGPL-3.0.
- Client license: AGPL-3.0, subject to component notices.
- Source visibility: Public repository.
- Source revision: ce1ffb4392b01f38e2c4599c7c84d2a93973b138
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: The cited root license governs this repository distribution, subject to component notices.
Self-hosting: Yes cross-checked
Self-hosting
Typed value: Yes.
The app runs locally and serializes session metadata as JSON. Portable import/export guarantees remain unknown.
- Self hosting: Local cs binary with tmux and user-installed agent commands.
- 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.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
Telemetry opt-out: No
Telemetry opt-out
Typed value: No.
Squad persists session metadata and diff state locally. The pinned Go application has no product telemetry collector or telemetry-disable setting; model-provider handling is outside this application source.
- Telemetry controls: No product telemetry opt-out setting in the inspected Go app/config/log/session code.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: The executable is a local Bubble Tea terminal UI that creates and attaches tmux sessions, sends prompts and renders diffs. The repository has no product web-session interface, native phone app, human account/member system, SSO integration or telemetry configuration. The web directory is website boilerplate, not a released session client.
Free access: Yes cross-checked
Free access
Typed value: Yes.
Claude Squad is a free AGPL-3.0 download installed through Homebrew or a shell script; no paid plan is shown. Agent and model costs are paid to their providers.
- Ongoing free: The cs binary is a free AGPL-3.0 download from Homebrew or the public install script.
- Self host cost: Runs on the user's machine with tmux and gh; no ADE fee is shown. Agent provider charges remain separate.
- Paid only: Not paid-only: the application is installed free of charge from public channels.
- Free scenarios, usage caps and card requirements for the underlying agents were not checked. No installed-product test was run.
-
Finding: Claude Squad installs as the cs binary through Homebrew or a public install script; the README names no price, account or paid plan.
-
Finding: The homepage gives Homebrew and shell-script installation and states the software is licensed under GNU AGPL v3.0. It shows no pricing or paid plan.
Starting price: Free: Yes. Free cross-checked
Starting price: Free
Typed value: Yes. Free.
Claude Squad is a free AGPL-3.0 download installed through Homebrew or a shell script; no paid plan is shown. Agent and model costs are paid to their providers.
- Ongoing free: The cs binary is a free AGPL-3.0 download from Homebrew or the public install script.
- Self host cost: Runs on the user's machine with tmux and gh; no ADE fee is shown. Agent provider charges remain separate.
- Paid only: Not paid-only: the application is installed free of charge from public channels.
- Free scenarios, usage caps and card requirements for the underlying agents were not checked. No installed-product test was run.
-
Finding: Claude Squad installs as the cs binary through Homebrew or a public install script; the README names no price, account or paid plan.
-
Finding: The homepage gives Homebrew and shell-script installation and states the software is licensed under GNU AGPL v3.0. It shows no pricing or paid plan.
Starting price: Up to $20/month: No. Free cross-checked
Starting price: Up to $20/month
Typed value: No. Free.
Claude Squad is a free AGPL-3.0 download installed through Homebrew or a shell script; no paid plan is shown. Agent and model costs are paid to their providers.
- Ongoing free: The cs binary is a free AGPL-3.0 download from Homebrew or the public install script.
- Self host cost: Runs on the user's machine with tmux and gh; no ADE fee is shown. Agent provider charges remain separate.
- Paid only: Not paid-only: the application is installed free of charge from public channels.
- Free scenarios, usage caps and card requirements for the underlying agents were not checked. No installed-product test was run.
-
Finding: Claude Squad installs as the cs binary through Homebrew or a public install script; the README names no price, account or paid plan.
-
Finding: The homepage gives Homebrew and shell-script installation and states the software is licensed under GNU AGPL v3.0. It shows no pricing or paid plan.
Starting price: $21–40/month: No. Free cross-checked
Starting price: $21–40/month
Typed value: No. Free.
Claude Squad is a free AGPL-3.0 download installed through Homebrew or a shell script; no paid plan is shown. Agent and model costs are paid to their providers.
- Ongoing free: The cs binary is a free AGPL-3.0 download from Homebrew or the public install script.
- Self host cost: Runs on the user's machine with tmux and gh; no ADE fee is shown. Agent provider charges remain separate.
- Paid only: Not paid-only: the application is installed free of charge from public channels.
- Free scenarios, usage caps and card requirements for the underlying agents were not checked. No installed-product test was run.
-
Finding: Claude Squad installs as the cs binary through Homebrew or a public install script; the README names no price, account or paid plan.
-
Finding: The homepage gives Homebrew and shell-script installation and states the software is licensed under GNU AGPL v3.0. It shows no pricing or paid plan.
Starting price: $41–100/month: No. Free cross-checked
Starting price: $41–100/month
Typed value: No. Free.
Claude Squad is a free AGPL-3.0 download installed through Homebrew or a shell script; no paid plan is shown. Agent and model costs are paid to their providers.
- Ongoing free: The cs binary is a free AGPL-3.0 download from Homebrew or the public install script.
- Self host cost: Runs on the user's machine with tmux and gh; no ADE fee is shown. Agent provider charges remain separate.
- Paid only: Not paid-only: the application is installed free of charge from public channels.
- Free scenarios, usage caps and card requirements for the underlying agents were not checked. No installed-product test was run.
-
Finding: Claude Squad installs as the cs binary through Homebrew or a public install script; the README names no price, account or paid plan.
-
Finding: The homepage gives Homebrew and shell-script installation and states the software is licensed under GNU AGPL v3.0. It shows no pricing or paid plan.
Starting price: Over $100/month: No. Free cross-checked
Starting price: Over $100/month
Typed value: No. Free.
Claude Squad is a free AGPL-3.0 download installed through Homebrew or a shell script; no paid plan is shown. Agent and model costs are paid to their providers.
- Ongoing free: The cs binary is a free AGPL-3.0 download from Homebrew or the public install script.
- Self host cost: Runs on the user's machine with tmux and gh; no ADE fee is shown. Agent provider charges remain separate.
- Paid only: Not paid-only: the application is installed free of charge from public channels.
- Free scenarios, usage caps and card requirements for the underlying agents were not checked. No installed-product test was run.
-
Finding: Claude Squad installs as the cs binary through Homebrew or a public install script; the README names no price, account or paid plan.
-
Finding: The homepage gives Homebrew and shell-script installation and states the software is licensed under GNU AGPL v3.0. It shows no pricing or paid plan.
Starting price: Contact for pricing: No. Free cross-checked
Starting price: Contact for pricing
Typed value: No. Free.
Claude Squad is a free AGPL-3.0 download installed through Homebrew or a shell script; no paid plan is shown. Agent and model costs are paid to their providers.
- Ongoing free: The cs binary is a free AGPL-3.0 download from Homebrew or the public install script.
- Self host cost: Runs on the user's machine with tmux and gh; no ADE fee is shown. Agent provider charges remain separate.
- Paid only: Not paid-only: the application is installed free of charge from public channels.
- Free scenarios, usage caps and card requirements for the underlying agents were not checked. No installed-product test was run.
-
Finding: Claude Squad installs as the cs binary through Homebrew or a public install script; the README names no price, account or paid plan.
-
Finding: The homepage gives Homebrew and shell-script installation and states the software is licensed under GNU AGPL v3.0. It shows no pricing or paid plan.
Pricing model: Free, no paid plan: Yes
Pricing model: Free, no paid plan
Typed value: Yes.
No price or paid plan is published; Claude Squad is AGPL-3.0 open source and agent/model usage (e.g. an OpenAI API key for Codex) is paid to the provider.
- Model cost: The user supplies their own provider credentials (e.g. OPENAI_API_KEY for Codex), billed by that provider.
- First-party pricing pages, terms and licences read 2026-11-10; no purchase, billing or authenticated account test.
-
Finding: For Codex the user sets their own OpenAI API key; the README states no price.
Pricing model: Free plan: No
Pricing model: Free plan
Typed value: No.
No price or paid plan is published; Claude Squad is AGPL-3.0 open source and agent/model usage (e.g. an OpenAI API key for Codex) is paid to the provider.
- Model cost: The user supplies their own provider credentials (e.g. OPENAI_API_KEY for Codex), billed by that provider.
- First-party pricing pages, terms and licences read 2026-11-10; no purchase, billing or authenticated account test.
-
Finding: For Codex the user sets their own OpenAI API key; the README states no price.
Pricing model: Subscription: No
Pricing model: Subscription
Typed value: No.
No price or paid plan is published; Claude Squad is AGPL-3.0 open source and agent/model usage (e.g. an OpenAI API key for Codex) is paid to the provider.
- Model cost: The user supplies their own provider credentials (e.g. OPENAI_API_KEY for Codex), billed by that provider.
- First-party pricing pages, terms and licences read 2026-11-10; no purchase, billing or authenticated account test.
-
Finding: For Codex the user sets their own OpenAI API key; the README states no price.
Pricing model: Per seat: No
Pricing model: Per seat
Typed value: No.
No price or paid plan is published; Claude Squad is AGPL-3.0 open source and agent/model usage (e.g. an OpenAI API key for Codex) is paid to the provider.
- Model cost: The user supplies their own provider credentials (e.g. OPENAI_API_KEY for Codex), billed by that provider.
- First-party pricing pages, terms and licences read 2026-11-10; no purchase, billing or authenticated account test.
-
Finding: For Codex the user sets their own OpenAI API key; the README states no price.
Pricing model: Usage-based: No
Pricing model: Usage-based
Typed value: No.
No price or paid plan is published; Claude Squad is AGPL-3.0 open source and agent/model usage (e.g. an OpenAI API key for Codex) is paid to the provider.
- Model cost: The user supplies their own provider credentials (e.g. OPENAI_API_KEY for Codex), billed by that provider.
- First-party pricing pages, terms and licences read 2026-11-10; no purchase, billing or authenticated account test.
-
Finding: For Codex the user sets their own OpenAI API key; the README states no price.
Pricing model: Per machine or compute: No
Pricing model: Per machine or compute
Typed value: No.
No price or paid plan is published; Claude Squad is AGPL-3.0 open source and agent/model usage (e.g. an OpenAI API key for Codex) is paid to the provider.
- Model cost: The user supplies their own provider credentials (e.g. OPENAI_API_KEY for Codex), billed by that provider.
- First-party pricing pages, terms and licences read 2026-11-10; no purchase, billing or authenticated account test.
-
Finding: For Codex the user sets their own OpenAI API key; the README states no price.
Pricing model: Bring your own key: Yes cross-checked
Pricing model: Bring your own key
Typed value: Yes.
No price or paid plan is published; Claude Squad is AGPL-3.0 open source and agent/model usage (e.g. an OpenAI API key for Codex) is paid to the provider.
- Model cost: The user supplies their own provider credentials (e.g. OPENAI_API_KEY for Codex), billed by that provider.
- First-party pricing pages, terms and licences read 2026-11-10; no purchase, billing or authenticated account test.
-
Finding: For Codex the user sets their own OpenAI API key; the README states no price.
Pricing model: One-time purchase: No
Pricing model: One-time purchase
Typed value: No.
No price or paid plan is published; Claude Squad is AGPL-3.0 open source and agent/model usage (e.g. an OpenAI API key for Codex) is paid to the provider.
- Model cost: The user supplies their own provider credentials (e.g. OPENAI_API_KEY for Codex), billed by that provider.
- First-party pricing pages, terms and licences read 2026-11-10; no purchase, billing or authenticated account test.
-
Finding: For Codex the user sets their own OpenAI API key; the README states no price.
Keeps going with laptop closed: No
Keeps going with laptop closed
Typed value: No.
Squad starts tmux and coding-agent processes on its current host. No vendor-managed agent compute is implemented; tmux detachment does not keep work running when that execution host sleeps or stops.
- Managed cloud: No vendor compute provisioner in the pinned native execution paths.
- Client disconnect: Detaching the TUI preserves its local tmux process, but sleeping/stopping the execution host stops useful work.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: The app runs tmux new-session on its current host with a Git worktree as cwd. Built-in execution has no vendor compute provisioner, container runtime or VM launcher. Tmux detachment preserves processes only while that execution host stays running.
Open-source license: Yes. AGPL-3.0 cross-checked
Open-source license
Typed value: Yes. AGPL-3.0.
Squad source is AGPL-3.0.
- Client license: AGPL-3.0, subject to component notices.
- Source visibility: Public repository.
- Source revision: ce1ffb4392b01f38e2c4599c7c84d2a93973b138
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: The cited root license governs this repository distribution, subject to component notices.
Any desktop app: Yes
Any desktop app
Typed value: Yes.
Claude Squad ships native terminal UI builds for macOS, Linux and Windows. The pinned distribution supplies no product web-session client or native iOS/Android app.
- Desktop os: Public release archives include macOS, Linux and Windows on amd64/arm64; terminal UI requires its tmux/git environment.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: The public release provides darwin, linux and windows archives for amd64 and arm64. The application is a terminal UI using tmux and git, not a standalone graphical desktop app.
Any phone client: No
Any phone client
Typed value: No.
Claude Squad ships native terminal UI builds for macOS, Linux and Windows. The pinned distribution supplies no product web-session client or native iOS/Android app.
- Mobile apps: The Go terminal distribution has no native iOS/Android application.
- Browser: The inspected web directory is website boilerplate and does not implement a released agent-session client.
- Mobile browser: The pinned application has no phone browser session interface.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: The executable is a local Bubble Tea terminal UI that creates and attaches tmux sessions, sends prompts and renders diffs. The repository has no product web-session interface, native phone app, human account/member system, SSO integration or telemetry configuration. The web directory is website boilerplate, not a released session client.
All public findings
Findings may summarize a source. They are not presented as verbatim statements.
claude-squad:ACC-01: Claude Squad ships native terminal UI builds for macOS, Linux and Windows. The pinned distribution supplies no product web-session client or native iOS/Android app.
claude-squad:ACC-01
Claude Squad ships native terminal UI builds for macOS, Linux and Windows. The pinned distribution supplies no product web-session client or native iOS/Android app.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
-
Finding: The public release provides darwin, linux and windows archives for amd64 and arm64. The application is a terminal UI using tmux and git, not a standalone graphical desktop app.
-
Finding: The executable is a local Bubble Tea terminal UI that creates and attaches tmux sessions, sends prompts and renders diffs. The repository has no product web-session interface, native phone app, human account/member system, SSO integration or telemetry configuration. The web directory is website boilerplate, not a released session client.
claude-squad:ACC-02: Squad launches configurable terminal agent commands and profiles; the official repository also names OpenCode and Amp. cross-checked
claude-squad:ACC-02
Squad launches configurable terminal agent commands and profiles; the official repository also names OpenCode and Amp.
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
-
Claude Squad official repository description
Finding: Official repository describes managing multiple AI terminal agents like Claude Code, Codex, OpenCode and Amp. README separately documents configurable -p commands and named program profiles.
claude-squad:ACC-03: Agent credentials are supplied to the selected CLI. cross-checked
claude-squad:ACC-03
Agent credentials are supplied to the selected CLI.
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
-
Claude Squad tmux session start
Finding: Each session runs the configured program command (default claude) unmodified inside a new tmux session in the task worktree, so the installed agent CLI uses its own stored sign-in.
claude-squad:ACC-04: Install cs, tmux and gh before creating sessions. cross-checked
claude-squad:ACC-04
Install cs, tmux and gh before creating sessions.
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
claude-squad:ACC-05: cs provides management commands; a general task API is unverified. cross-checked
claude-squad:ACC-05
cs provides management commands; a general task API is unverified.
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
claude-squad:ACC-07: Pinned module identifies a Go terminal UI built on Bubble Tea. cross-checked
claude-squad:ACC-07
Pinned module identifies a Go terminal UI built on Bubble Tea.
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: Pinned build metadata identifies the implementation used by the documented application.
claude-squad:PLAN-01: Sessions can be started with an initial prompt. cross-checked
claude-squad:PLAN-01
Sessions can be started with an initial prompt.
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
claude-squad:PLAN-06: Squad persists agent session records, not a separate native issue or task backlog. Inspection of storage, app actions and config found no independent issue entities or state transitions.
claude-squad:PLAN-06
Squad persists agent session records, not a separate native issue or task backlog. Inspection of storage, app actions and config found no independent issue entities or state transitions.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: Persistent InstanceData stores session title, path, branch, status, program, worktree and diff state. Human UI actions create sessions. There is no separate issue/task store, product coordinator role/delegation tool, schedule/webhook starter or team user input transport. AutoYes acknowledges prompts in an existing session rather than starting a new task.
claude-squad:COORD-01: Squad documents simultaneous background agent sessions. cross-checked
claude-squad:COORD-01
Squad documents simultaneous background agent sessions.
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
claude-squad:COORD-03: The pinned TUI lets a human create and prompt terminal agents. It supplies no coordinator agent role with delegation and communication tools; underlying agent subagents and arbitrary custom commands are separate.
claude-squad:COORD-03
The pinned TUI lets a human create and prompt terminal agents. It supplies no coordinator agent role with delegation and communication tools; underlying agent subagents and arbitrary custom commands are separate.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: Persistent InstanceData stores session title, path, branch, status, program, worktree and diff state. Human UI actions create sessions. There is no separate issue/task store, product coordinator role/delegation tool, schedule/webhook starter or team user input transport. AutoYes acknowledges prompts in an existing session rather than starting a new task.
claude-squad:COORD-04: New work is initiated from the TUI. The pinned source has no scheduled or external-event starter; periodic app timers monitor sessions, and AutoYes responds within an already-running task.
claude-squad:COORD-04
New work is initiated from the TUI. The pinned source has no scheduled or external-event starter; periodic app timers monitor sessions, and AutoYes responds within an already-running task.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: Persistent InstanceData stores session title, path, branch, status, program, worktree and diff state. Human UI actions create sessions. There is no separate issue/task store, product coordinator role/delegation tool, schedule/webhook starter or team user input transport. AutoYes acknowledges prompts in an existing session rather than starting a new task.
claude-squad:COORD-05: Session attach, pause and resume are documented. cross-checked
claude-squad:COORD-05
Session attach, pause and resume are documented.
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
claude-squad:COORD-07: Claude Squad documents quick prompted sessions and configurable program profiles. Epic planning remains unestablished. cross-checked
claude-squad:COORD-07
Claude Squad documents quick prompted sessions and configurable program profiles. Epic planning remains unestablished.
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
claude-squad:RUN-01: Squad starts tmux and coding-agent processes on its current host. No vendor-managed agent compute is implemented; tmux detachment does not keep work running when that execution host sleeps or stops.
claude-squad:RUN-01
Squad starts tmux and coding-agent processes on its current host. No vendor-managed agent compute is implemented; tmux detachment does not keep work running when that execution host sleeps or stops.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
-
Finding: The app runs tmux new-session on its current host with a Git worktree as cwd. Built-in execution has no vendor compute provisioner, container runtime or VM launcher. Tmux detachment preserves processes only while that execution host stays running.
claude-squad:RUN-02: Each task uses a local tmux session and Git worktree. The inspected session/git and tmux implementation has no product-managed container or VM isolation.
claude-squad:RUN-02
Each task uses a local tmux session and Git worktree. The inspected session/git and tmux implementation has no product-managed container or VM isolation.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
-
Finding: The app runs tmux new-session on its current host with a Git worktree as cwd. Built-in execution has no vendor compute provisioner, container runtime or VM launcher. Tmux detachment preserves processes only while that execution host stays running.
claude-squad:RUN-03: Pinned source restores session metadata and reconnects tmux; missing sessions are parked for manual Resume. No recovery test was run. cross-checked
claude-squad:RUN-03
Pinned source restores session metadata and reconnects tmux; missing sessions are parked for manual Resume. No recovery test was run.
- 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.
-
Finding: v1.0.20 records base-commit tracking and recovery for instances whose tmux server/session died.
-
Claude Squad session/instance.go
Finding: Source inspection of the documented pause/resume flow shows restoration of stored instances and tmux connections. Missing tmux sessions become Paused; Resume rebuilds missing worktrees and starts or restores tmux. SendPrompt sends terminal keys; PreviewFullHistory captures tmux scrollback. No recovery fixture was run.
claude-squad:RUN-06: Pinned session storage retains status and diff counts. Status correctness and operational metrics are untested. cross-checked
claude-squad:RUN-06
Pinned session storage retains status and diff counts. Status correctness and operational metrics are untested.
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
-
Claude Squad session/storage.go
Finding: Source inspection links the session UI to JSON persistence of title, path, branch, status, program, worktree identity and diff stats via SaveInstances/LoadInstances. This is session persistence, not a separate issue tracker.
claude-squad:TEAM-01: The pinned local TUI has no product transport or account model for several humans to prompt the same agent work. Sharing a terminal through an external tmux/SSH setup is outside the product collaboration feature.
claude-squad:TEAM-01
The pinned local TUI has no product transport or account model for several humans to prompt the same agent work. Sharing a terminal through an external tmux/SSH setup is outside the product collaboration feature.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: The executable is a local Bubble Tea terminal UI that creates and attaches tmux sessions, sends prompts and renders diffs. The repository has no product web-session interface, native phone app, human account/member system, SSO integration or telemetry configuration. The web directory is website boilerplate, not a released session client.
-
Finding: Persistent InstanceData stores session title, path, branch, status, program, worktree and diff state. Human UI actions create sessions. There is no separate issue/task store, product coordinator role/delegation tool, schedule/webhook starter or team user input transport. AutoYes acknowledges prompts in an existing session rather than starting a new task.
claude-squad:TEAM-02: Squad stores local configuration and sessions with no human workspace membership, named role model or enterprise SSO in the pinned application.
claude-squad:TEAM-02
Squad stores local configuration and sessions with no human workspace membership, named role model or enterprise SSO in the pinned application.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: The executable is a local Bubble Tea terminal UI that creates and attaches tmux sessions, sends prompts and renders diffs. The repository has no product web-session interface, native phone app, human account/member system, SSO integration or telemetry configuration. The web directory is website boilerplate, not a released session client.
claude-squad:TEAM-03: Experimental auto-accept applies to Claude Code and Aider prompts. cross-checked
claude-squad:TEAM-03
Experimental auto-accept applies to Claude Code and Aider prompts.
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
claude-squad:TEAM-04: Claude Squad persists session metadata locally. It does not establish a team decision audit trail. cross-checked
claude-squad:TEAM-04
Claude Squad persists session metadata locally. It does not establish a team decision audit trail.
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
-
Claude Squad session/storage.go
Finding: Source inspection links the session UI to JSON persistence of title, path, branch, status, program, worktree identity and diff stats via SaveInstances/LoadInstances. This is session persistence, not a separate issue tracker.
claude-squad:TEAM-05: Preview/diff tabs and checkout support manual review. cross-checked
claude-squad:TEAM-05
Preview/diff tabs and checkout support manual review.
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
claude-squad:SHIP-01: Claude Squad exposes diffs and stores session diff data; wider artifact retention remains unknown. cross-checked
claude-squad:SHIP-01
Claude Squad exposes diffs and stores session diff data; wider artifact retention remains unknown.
- 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.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
-
Claude Squad session/storage.go
Finding: Source inspection links the session UI to JSON persistence of title, path, branch, status, program, worktree identity and diff stats via SaveInstances/LoadInstances. This is session persistence, not a separate issue tracker.
claude-squad:SHIP-03: Squad commits and pushes branches and can open the branch in a browser. The pinned Git action code does not create or manage pull requests.
claude-squad:SHIP-03
Squad commits and pushes branches and can open the branch in a browser. The pinned Git action code does not create or manage pull requests.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
-
Finding: PushChanges commits, pushes/syncs the branch with git/gh repo sync and optionally opens gh browse --branch. Bounded inspection of the Git/session action code found no PR create/update/review/merge management call.
claude-squad:OWN-01: Squad source is AGPL-3.0. cross-checked
claude-squad:OWN-01
Squad source is AGPL-3.0.
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: The cited root license governs this repository distribution, subject to component notices.
claude-squad:OWN-02: The app runs locally and serializes session metadata as JSON. Portable import/export guarantees remain unknown. cross-checked
claude-squad:OWN-02
The app runs locally and serializes session metadata as JSON. Portable import/export guarantees remain unknown.
- 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.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
-
Claude Squad session/storage.go
Finding: Source inspection links the session UI to JSON persistence of title, path, branch, status, program, worktree identity and diff stats via SaveInstances/LoadInstances. This is session persistence, not a separate issue tracker.
claude-squad:OWN-03: Squad persists session metadata and diff state locally. The pinned Go application has no product telemetry collector or telemetry-disable setting; model-provider handling is outside this application source.
claude-squad:OWN-03
Squad persists session metadata and diff state locally. The pinned Go application has no product telemetry collector or telemetry-disable setting; model-provider handling is outside this application source.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Claude Squad session/storage.go
Finding: Source inspection links the session UI to JSON persistence of title, path, branch, status, program, worktree identity and diff stats via SaveInstances/LoadInstances. This is session persistence, not a separate issue tracker.
-
Finding: The executable is a local Bubble Tea terminal UI that creates and attaches tmux sessions, sends prompts and renders diffs. The repository has no product web-session interface, native phone app, human account/member system, SSO integration or telemetry configuration. The web directory is website boilerplate, not a released session client.
claude-squad:OWN-04: No price or paid plan is published; Claude Squad is AGPL-3.0 open source and agent/model usage (e.g. an OpenAI API key for Codex) is paid to the provider. cross-checked
claude-squad:OWN-04
No price or paid plan is published; Claude Squad is AGPL-3.0 open source and agent/model usage (e.g. an OpenAI API key for Codex) is paid to the provider.
- First-party pricing pages, terms and licences read 2026-11-10; no purchase, billing or authenticated account test.
-
Finding: For Codex the user sets their own OpenAI API key; the README states no price.
claude-squad:OWN-06: The latest listed release is v1.0.20 with public issue support. cross-checked
claude-squad:OWN-06
The latest listed release is v1.0.20 with public issue support.
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
-
Finding: cs launches configurable Claude/Codex/Gemini/Aider commands in tmux sessions and Git worktrees. Keyboard actions create, attach, review diff, commit/push, check out/pause and resume; experimental auto-accept is opt-in.
-
Finding: v1.0.20 records base-commit tracking and recovery for instances whose tmux server/session died.
claude-squad:OWN-08: Claude Squad is a free AGPL-3.0 download installed through Homebrew or a shell script; no paid plan is shown. Agent and model costs are paid to their providers. cross-checked
claude-squad:OWN-08
Claude Squad is a free AGPL-3.0 download installed through Homebrew or a shell script; no paid plan is shown. Agent and model costs are paid to their providers.
- Free scenarios, usage caps and card requirements for the underlying agents were not checked. No installed-product test was run.
-
Finding: The repository is licensed under the GNU Affero General Public License version 3.
-
Finding: Claude Squad installs as the cs binary through Homebrew or a public install script; the README names no price, account or paid plan.
-
Finding: The homepage gives Homebrew and shell-script installation and states the software is licensed under GNU AGPL v3.0. It shows no pricing or paid plan.