Skip to main content
Back to trending

openrig

Build your own network of agents from Claude Code, Codex and Pi: persistent teams with roles, shared context and owned work.

  • agent-harness
  • agent-orchestration
  • agent-skills
  • ai-coding
  • claude-code
  • cli
  • codex-cli
  • multi-agent
  • multi-agent-systems
  • tmux
  • typescript
View on GitHub
Stars
3,649
Forks
244
+ today
+16
Created
6mo

Ranking data as of October 1, 2026 (UTC).

Overview

Build your own network of agents from Claude Code, Codex and Pi: persistent teams with roles, shared context and owned work. It ranks #23 on GitTiger, gaining +16 stars on October 1, 2026 (UTC).

The project is written in TypeScript and has 244 forks. It was created 6mo ago.

AI-generated summary of the repository README — may contain errors.

What it is

OpenRig is a TypeScript project for developers interested in coordinating AI coding agents. The project description says developers can build a network of agents from Claude Code, Codex, and Pi, organized as persistent teams with roles, shared context, and owned work.

Capabilities described

The stated focus is connecting those named agent tools and structuring their work through team roles, shared context, and ownership. The available details do not explain how these pieces operate or what commands are available, so the description is a high-level guide rather than implementation documentation.

Getting started

The supplied README preview contains no setup instructions. Read the project README at github.com/mvschwarz/openrig for getting-started guidance; no installation command was supplied.

Installation
git clone https://github.com/mvschwarz/openrig.git
cd openrig
# see README for setup

Frequently Asked Questions

Which agent tools does OpenRig name?

The project description names Claude Code, Codex, and Pi.

What language is OpenRig written in?

The supplied metadata lists TypeScript.

How do I get started?

Setup steps were not supplied. Consult the README at https://github.com/mvschwarz/openrig.