OpenRig CLI
openrig
A CLI for persistent teams of Claude Code and Codex agents: the team is described in YAML and started with one command, with roles and monitoring
- 7,413 ★ on the repository
- Last commit
- Apache-2.0
Broad access
Why this level
- Several agents edit project files and run commands in parallel
- rig setup changes ~/.tmux.conf and the npm install runs a post-install script
- The agent asks permission to run rig without repeated confirmations
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add cli/openrigDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewBroad accessThe tool can change data, run commands or handle secrets.
- Several agents edit project files and run commands in parallel
- rig setup changes ~/.tmux.conf and the npm install runs a post-install script
- The agent asks permission to run rig without repeated confirmations
This is third-party code. Review the repository files before installing.
What it does
OpenRig builds a persistent team with roles out of Claude Code and Codex agents: it is described in YAML and started with one command. The utility installs as the npm package `@openrig/cli` version 0.6.5 and provides the `rig` and `openrig-tui` commands, with monitoring and `.rigbundle` packages. Several agents work on one project in parallel. Requirements per the README: Node.js 22 or 24, tmux, macOS or Linux; native Windows is not supported yet, and WSL2 is possible.
Who it is for. For developers who already work with several agents and want to keep them as a persistent team with described roles instead of launching each by hand.
Good fit when
- You need a persistent team of agents with roles and a shared description in YAML
- You need to see the state of several agents in one panel
- You need to move a team description between projects in a rigbundle package
Not a fit when
- You work on native Windows: it is not supported yet
- You are not ready for agents to work in the project in parallel and edit files
Example request
Describe a team of three agents in YAML: an implementer, a reviewer and a tester, and start it on this repositoryLimitations
This is a wide-access tool, and the README itself discloses the side effects of installation: `rig setup` writes a block into `~/.tmux.conf`, on macOS it may install cmux, and the npm post-install script installs components. Before launch the agent asks permission to run rig commands without repeated confirmations, and `rig bundle install` writes the package files into the target folder. Use `rig setup --dry-run` for a preview. Node.js 22 or 24 (Node.js 22 on Apple silicon Macs), tmux and macOS or Linux are required.
How to disable. Remove the package with npm uninstall -g @openrig/cli, take the OpenRig block out of ~/.tmux.conf and stop the running tmux sessions.
FAQ
What does OpenRig do?
It builds a persistent team with roles out of Claude Code and Codex agents, described in YAML and started with one command.
What is needed for installation?
Node.js 22 or 24, tmux and macOS or Linux. Native Windows is not supported yet, and WSL2 is possible.
What does rig setup change?
It writes a block to ~/.tmux.conf and on macOS may install cmux. Preview: rig setup --dry-run.
Is it safe to let agents run rig?
That is the owner's decision: the README describes a question about allowing rig commands without repeated confirmations. Start with a preview and limit access.
Discussion
No questions or reviews yet.
Related
CLI toolsA self-hosted runtime for coding agents: each crew in its own Linux container, wrapped in a control plane with roles and audit
Self-hosted system for a team of AI agents: org chart, tasks, budgets and oversight of Claude Code, Codex and OpenClaw
Multi-agent orchestration for Claude Code: teams, roles, autopilot and task routing across skills and subagents
CLI Agent Orchestrator
CLI Agent Orchestrator (CAO)
A CLI that coordinates several coding agents: a supervisor delegates tasks to specialists in parallel or in sequence across isolated tmux sessions
An open source coding agent for the terminal and desktop with build and plan modes
Orchestrator plugin for OpenCode and Codex CLI: multiple agents, hooks, built-in MCPs, ultrawork mode and hash-anchored edits
README in short
The README describes OpenRig as a system for persistent teams of Claude Code and Codex agents: a YAML description, the rig and openrig-tui commands, monitoring, rigbundle packages, environment requirements and installation side effects. Apache-2.0 license.