whereismyai
OpenRig
OpenRig is an open source agent coordination platform that lets Claude Code, Codex and Pi work together as a persistent team.
OpenRig coordinates Claude Code, Codex and Pi as a persistent team for projects that span weeks or months. You talk to a lead agent that delegates tasks to specialists, tracks their progress, and returns answers to you. Specialists can coordinate with teammates, claim assignments, and use temporary subagents for smaller jobs. The platform includes a terminal user interface to view agent organization and work status. It runs as a self-hosted tool requiring Node 22 or 24, tmux and a Codex login. Coordinate multiple coding agents as a persistent team. Delegate project tasks from a lead agent to specialists. Track work assignments with owner and progress data.
OpenRig at a glance
- Best for: Software engineer
- Runs on: Self-hosted, Open source
- Pricing: Free
- Released: April 2026
- Category: AI agent tool
- Website: openrig.dev
Key features
- Coordinate multiple coding agents as a persistent team
- Delegate project tasks from a lead agent to specialists
- Track work assignments with owner and progress data
- Send direct messages to specialists without creating new tasks
- Use temporary native subagents for bounded inspection
- View agent organization and activity in a terminal interface
- Scale agent operations across different uses
Use it for
- Coordinate long-term software projects across multiple AI agents
- Split large projects among specialist coding agents
- Manage persistent agent teams with assigned roles and shared context
- Track work assignments and ownership across team members
Companions
Tools that articles about OpenRig recommend using with it, each with its job.
- Claude Code — Built to work with Claude Code.
- Codex — Built to work with Codex.
- Context7 — Provides up-to-date documentation for AI agents and code editors.
- Superpowers — Brainstorm, plan and execute skills for bigger tasks.
- Playwright MCP — Enables LLMs to interact with web pages using structured accessibility snapshots.
- GitHub MCP Server — Reads pull requests, issues and code search on GitHub.
Alternatives to OpenRig
- OpenCode — Works with 75+ model providers, local models, and existing subscriptions
- OpenHarness — Manages Claude Code, Codex, and Hermes from a single command center.
- OpenViking — Unifies agent memory, knowledge RAG, and skills into a single directory structure.
- Orca — Runs multiple AI coding agents simultaneously in isolated workspaces.
- Ret — Manage multiple AI coding agents across projects from one unified desktop interface.
- Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
- OpenAgentsControl — Generates code matching your patterns and requires approval before execution.
- OpenBot — Runs AI agents locally using existing subscriptions or local models.
- OpenBot — Runs entirely on your own infrastructure with strict document permissions and custom.
- OpenChamber — Run and review multi-model AI coding agents from desktop, browser, and mobile devices.
- Open Agents Template — Spawn autonomous coding agents with full sandboxes and durable workflows.
- Oh My OpenAgent — Executes complex coding and research tasks independently using a keyword.
All OpenRig alternatives