Run your coding agents like an engineering team. You're the manager — Squadrant gives you captains who plan and delegate, and crews who write the code.
You
│
├── squadrant launch <project> → Captain (project A)
│ │
│ └── squadrant crew spawn → Crew, Crew, …
│
└── squadrant launch <project-2> → Captain (project B)
└── …
- You — set direction, make the calls only you can make.
- Captain — one per project, lives in cmux, plans and delegates. Your standing project lead.
- Crew — a fresh interactive sub-session the captain spawns to actually write the code, then reports back and signals when it's done or blocked.
One person, operating like an engineering org.
Squadrant is also moving to support every major coding agent — Claude Code, Codex, Cursor, Gemini CLI — not just Claude Code. Claude Code is the reference implementation today; other agents land through the plugin system's driver abstractions and the upcoming cross-agent projection layer (#31). See
docs/specs/2026-04-24-multi-agent-direction.md.
- Run several projects at once — one captain per project, each with its own context, all supervised from the same session.
- Delegate instead of micromanage — hand a task to a crew and let it work; you don't watch every keystroke.
- Agents signal you, not the other way around — crews report CREW DONE / CREW BLOCKED / CREW NEEDS INPUT instead of you polling a pane to see if it's finished.
- Drive it from your phone — optional two-way Telegram bridge, so you can delegate and get notified without being at your desk.
squadrant launch brove
→ Captain boots in cmux
You (in the captain pane): "build the export-to-CSV feature"
→ Captain spawns a crew: squadrant crew spawn brove "build export-to-CSV"
→ Crew works in its own tab, writes the code, runs tests
→ 🎉 CREW DONE — captain reviews, merges or follows up
Full walkthrough, including your first captain and crew, step by step: see QUICKSTART.md.
npm i -g squadrant # global `squadrant` CLI (alias: `squad`)
squadrant init
squadrant doctorSee QUICKSTART.md for prerequisites, the from-source build, and a guided first run.
Squadrant was formerly published/developed as
claude-cockpit; it was rebranded in 0.9.0 as it grew into a multi-agent orchestration layer.
| Agent | Status | Notes |
|---|---|---|
| Claude Code | ✅ Shipping | Reference implementation; reads CLAUDE.md, Skill tool, MCP via settings.json |
| Codex CLI | ✅ projection (skills + roles) | Captain/crew roles inlined into ~/.codex/AGENTS.md (#45). First-class role identity is #35. |
| Cursor | ✅ projection (skills + roles) | Captain/crew roles inlined into ~/.cursor/rules/squadrant-global.mdc (#45). |
| Gemini CLI | ✅ projection (skills + roles) | Captain/crew roles inlined into ~/.gemini/GEMINI.md (#45). |
| opencode | ✅ driver + projection (interactive crew) | opencode run "<prompt>" with --format json / -m <model>; AGENTS.md projects to ~/.config/opencode/AGENTS.md. |
Cross-agent config sync (one canonical source → agent-specific formats) is tracked in #31.
- QUICKSTART.md — hands-on first run: install, first captain, first crew, optional Telegram
- Architecture diagram — visual overview of the monorepo, driver seams, lifecycle sources, and control/captain channel
- docs/reference.md — full command table, monorepo structure, architecture deep-dive, Telegram integration, config schema
- CONTRIBUTING.md — setup, branching, and conventions for contributing
- Andrej Karpathy — coding principles baked into every captain/crew role (
plugin/skills/karpathy-principles/SKILL.md) - forrestchang/andrej-karpathy-skills — reference packaging for the four principles (MIT)
- Multica — validated the multi-agent runtime + skill-compounding direction
- AGENTS.md — convergence point for cross-agent instructions
- OpenSpace — self-improving learnings loop (record → capture → fix → mark-useful)
- ComposioHQ — tool/skill portability across agents
MIT