# openrig

> Run a persistent team of Claude Code and Codex agents from one YAML file

- Repository: https://github.com/mvschwarz/openrig
- Category: Coding agents & dev tools
- Stars: 8,097 · Forks: 655 · Language: TypeScript · License: Apache-2.0
- Experience: Some experience
- Page: https://ir.adyog.com/repos/mvschwarz/openrig/

Running several AI coding agents usually means a pile of terminal windows with no shared memory and no clear owner for each task. OpenRig treats the agents as a team. You describe the team in YAML, and it starts each agent in a tmux session with a role.

You talk to a lead agent about the outcome you want. The lead can hand work to specialists such as a builder, a reviewer or QA, and tasks are tracked in a queue. A terminal dashboard shows each agent's model, state and context. After install, a built-in operator agent helps you pick a first team.

The README describes three ready-made teams. Starter pairs a Claude Code builder with a Codex reviewer. Workshop adds a lead and QA. Factory has seven agents for longer product work. Setup writes provider hooks and trust settings on your machine, and the README lists these changes in detail.

## What it does

- **Agent teams defined in YAML**: Describe your agents and their roles in YAML, then boot them with rig up. Claude Code and Codex can sit in the same rig.
- **Ready-made teams**: Three starting teams: starter (builder and reviewer), workshop (lead, builder, QA, reviewer) and factory (seven agents).
- **Messaging and a task queue**: You send a message to an agent with rig send. Agents record tasks in a queue you can list with rig queue list.
- **Terminal dashboard**: A TUI shows agents as a graph or table with runtime, model, context and state. It uses Herdr when installed, otherwise plain tmux.
- **Previews before changes**: rig setup --dry-run and rig up --plan show what will happen first. The README also documents what OpenRig changes on your machine.

## What you could build

- Hand a bounded change in your repository to a Claude Code builder and have a Codex agent review it.
- Run a lead, builder, QA and reviewer team for ongoing work in one codebase.
- Watch several coding agents at once in a single terminal dashboard.
- Define your own multi-agent team in YAML and reuse it across projects.
- Track which agent owns which task through a shared queue.

## Who it's for

Developers already using Claude Code or Codex who want several agents working together; you should be comfortable with the terminal, tmux and npm.

## Get started

You need Node.js 22 or 24 and tmux on macOS or Linux (WSL2 on Windows), plus a signed-in Claude Code or Codex account. Install the CLI, preview the setup, then run rig setup and talk to the operator agent to choose a first team. Read the section on what OpenRig changes on your machine first, since it writes hooks and trust settings.

```
npm install -g @openrig/cli
```
```
rig setup --dry-run
```

Tags: multi-agent, claude-code, codex, tmux, orchestration