Agents Squads
June 11, 2026 · View on GitHub
Agents Squads
Your AI ops teams.
Autonomous AI agents for engineering, marketing, finance, and operations. You make the decisions. They do the work.
A squad is a team of AI agents — different models, different roles — working toward a shared goal with persistent memory. A lead briefs the team, workers execute, a verifier checks the output, and feedback from each cycle is injected into the next. Everything is a markdown file in a git repo: no database, no server, no DSL.
npm install -g squads-cli
squads init # creates .agents/ with 4 starter squads
squads status
squads run research/analyst
How it works
.agents/
├── BUSINESS_BRIEF.md # Your business context — every agent reads it
├── config/SYSTEM.md # Immutable rules shared by all agents
├── squads/ # Identity: SQUAD.md + one .md file per agent
│ ├── intelligence/
│ ├── research/
│ ├── product/
│ └── company/ # Evaluates outputs, closes the feedback loop
└── memory/ # State: learnings, priorities, feedback
Before every run, an agent loads a context cascade — squad identity, current priorities, feedback from the last cycle, active work across the team — tuned by role so scanners stay lightweight and leads get the full picture. Agents that know what's been done don't duplicate work; agents that see their own feedback stop producing noise.
Squads shells out to native AI CLIs (claude, gemini, aider, …), so
mixed-model teams work out of the box: a cheap model scans, a deep
reasoning model builds, a mid-tier model verifies.
squads run research --parallel # squad conversation
squads run intelligence --task "Scan X" # directed run
squads autopilot --interval 30 --budget 50 # autonomous dispatch
Documentation
| Philosophy | Why squads, why CLI-first, skills + tools |
| Architecture | Context cascade, roles, phases, the feedback loop |
| Configuration | Starter squads, building your own, secrets |
| Running Agents | Execution modes, local limits, scaling |
| Commands | Reference for humans and for agents |
| Providers | Claude, Gemini, DeepSeek, and per-agent routing |
Requirements
Node.js >= 20, Git, and
Claude Code (default
provider — others optional). squads doctor checks your machine.
Everything runs locally: your machine, your API keys, your data. No login, no cloud, no telemetry surprises.
Development
git clone https://github.com/agents-squads/squads-cli.git
cd squads-cli
npm install
npm run build && npm link
npm test
TypeScript (strict mode), Commander.js, Vitest, tsup.
Contributing
Contributions welcome — open an issue first to discuss changes. See CONTRIBUTING.md for guidelines, and GitHub Discussions for questions and ideas. We'd love to see what you build — share your squads and skills.