The OpenRig TUI: the build rig as a graph, then as a table of seats with runtime, model, context and state, then one seat in detail (real recording, 10 seconds)

Picture published by the creator on GitHub.

Run Claude Code and Codex together as one agent team

Made by Mike Schwarz

OpenRig turns a pile of AI coding-assistant windows into an organized team: you describe the team in a short YAML settings file, start it with one command, and it runs Claude Code, Codex and Pi with roles, shared context and owned tasks.

You talk to a lead agent about the outcome you want while specialists work in parallel, and the team’s work persists at the same addresses between sessions instead of evaporating when you close a window. It needs Node.js and tmux on Mac or Linux; Windows is not supported yet. The creator presents it as the open-source system behind his AI civilization experiments — long-running simulations of agent societies.

Can I use this?

Command-line tool on Mac or Linux

You'll need Mac or Linux with Node.js 22/24 and tmux, plus Claude Code and/or Codex accounts · Setup needed

Worth knowing No native Windows support and WSL2 is untested. It organizes agents you already pay for — it is not itself an AI model, so you still need those subscriptions. BuildTube has not run or verified this software.

Why it's here

4,251 people starred it on GitHub this week — 5,099 in total.

Numbers from the snapshot taken 5 October 2026; not refreshed since.

Behind it

See the code on GitHub

BuildTube has not run or verified this project. Everything above is written from what the creator published.

Made this?