openrig vs squad
Define a team of Claude Code, Codex and Pi agents in YAML and boot it with one command: persistent tmux-backed seats with roles, shared context and owned work, steered via a lead agent. — versus — Multi-agent terminal collaboration for AI CLIs: a manager, workers and an inspector — Claude Code, Gemini, Codex, OpenCode — coordinating through one-shot shell commands and SQLite. No daemon.
Both run a manager plus worker coding-CLI agents as a terminal team; OpenRig adds YAML-defined, persistent rigs with roles and owned work.
| openrig | squad | |
|---|---|---|
| Stars | 8.7k | 841 |
| Forks | 722 | 95 |
| Language | TypeScript | Rust |
| License | Apache-2.0 | MIT |
| Last activity | yesterday | 5 months ago |
| Topics | orchestration, coding, agents | coding, orchestration |
| Curated connections | 6 | 9 |
openrig — the curator's take
Use it when you already live in Claude Code/Codex and want a standing team — lead agent, specialists, stable addresses — rather than one-off sessions. Skip it if you want a hosted platform or Windows-native setup (tmux, macOS/Linux/WSL2 only), and read the permissions section first: the kernel operator runs with broad, prompt-free access by default.
squad — the curator's take
The unix-philosophy take on multi-agent coding: no daemon, no server, no framework — each agent is a terminal running the CLI you already use, coordinating through /squad slash commands backed by SQLite. Assign a manager, spin workers, add an inspector, watch them divide the work. Radically simpler to reason about than orchestration platforms, and it dies clean (every command is one-shot). NOT for production pipelines or unattended fleets — it's built for a human watching terminals; young (~600 stars) and quiet for weeks at review time, so kick the tires before making it a habit.