OpenRig is an open-source multi-agent harness that runs Claude Code and Codex together as one coordinated development system. Each agent occupies a persistent seat with its own identity, work queue, lessons, and terminal session. Work can be assigned between agents instead of forcing every task through one model. The system runs on the user’s own infrastructure and keeps its orchestration visible through tmux. A command-line interface manages setup, health checks, queues, and workstation configuration. OpenRig also includes skills, evidence tracking, reusable packages, and support for persistent team workflows. It is aimed at developers who want several coding agents collaborating as a stable group rather than operating as isolated assistants.
Features
- Persistent Claude Code and Codex agent seats
- Shared multi-agent work queues
- Saved lessons and agent identity
- tmux-based observable terminal sessions
- CLI setup and diagnostics
- Skills and evidence tracking