OpenRig
Define a team of Claude Code and Codex agents in YAML and run it as one system
What it is
OpenRig runs persistent teams of coding agents (Claude Code, Codex, Pi) in tmux, defined in YAML with roles and shared context. A lead operator agent coordinates the team; a TUI shows each seat's runtime, model and context. It installs through a rigs skill added to your agent.
Good for
- Run a lead agent with specialist coding seats
- Keep agent teams alive across sessions
- Mix Claude Code and Codex on one repo
Install or run
npx skills add https://github.com/mvschwarz/openrig/tree/v0.7.12/skills/rigs --skill rigs --agent claude-codeCommand as given in the project README. Read the repository before you run anything on your machine.
What you need
Node.js 22 or 24; tmux; macOS or Linux (WSL2); Claude Code or Codex
Sources
- https://github.com/mvschwarz/openrig (project README, read 13 Nov 2026)
- https://api.github.com/repos/mvschwarz/openrig (GitHub API, read 13 Nov 2026)
The summary is ours, written from the README. Spotted an error? See how we work.