Oh My Claude Code 🤖 Agent Open source
Multi-AI orchestration plugin coordinating Claude, Gemini and Codex workers inside Claude Code
- GitHub stars
- 40k
- Stars this week
- +177
- Forks
- 3.5k
- Licence
- MIT
- Last push
- 2026-10-02
- Maintainer
- Yeachan-Heo
git clone https://github.com/Yeachan-Heo/oh-my-claudecode && cp oh-my-claudecode/*.md ~/.claude/agents/Third-party subagents & agents run with your permissions. Read the source before installing, and prefer pinned versions.
Works with
About Oh My Claude Code
What it does
Oh My Claude Code is a Claude Code plugin that turns Claude into a conductor for a small team of AI workers. It launches Claude, Gemini and Codex CLI processes in parallel tmux panes and coordinates them through 19 specialized agents, dozens of skills and MCP-backed tools, aiming for "no manual intervention required" runs from a stated goal to tested code.
Tools it gives your agent
- 19 agents grouped into build & analysis, review & quality, and domain specialists
- Multiple execution modes: Autopilot, a persistence mode called Ralph, Execute, Deep Interview, Team and Planning workflows
- MCP-powered tools: language server integration, AST-Grep for structural code search, a Python REPL and persistent state management
- Remote approval gates with workspace checkpoints and rollback for staged changes that need sign-off before landing
Works with
This is a Claude Code plugin specifically; it shells out to Gemini and Codex CLIs as additional workers, but Claude Code is the environment it installs into and the one it's built and tested against.
How to install or connect
/plugin marketplace add https://github.com/Yeachan-Heo/oh-my-claudecode
/plugin install oh-my-claudecode
Or via npm:
npm install -g @yeachan-heo/oh-my-claudecode
Then run /oh-my-claudecode:omc-setup to finish configuration.
Maintenance and safety
Very active and fast-growing (39,000+ stars, weekly commits, MIT licensed). Because it runs multiple CLI agents with shell and file access in parallel, review its approval-gate settings before pointing it at a repo you care about.
Who should use it
Claude Code users who want to run larger, multi-step jobs (architecture review, security analysis, multi-file refactors) across several models at once instead of a single linear session.
Pros
- Coordinates multiple CLI agents (Claude, Gemini, Codex) in parallel rather than just one
- Ships a large set of ready-made specialist agents and MCP tools out of the box
- Adds checkpoints/rollback for staged changes needing approval
Cons
- Tightly coupled to Claude Code plus tmux, so it's not usable from other editors or agents
- Running several CLI agents concurrently increases the blast radius if a step goes wrong; worth testing on a disposable branch first
Similar subagents & agents
All agent workflows & frameworks →Spec Kit 🤖 AgentFree
GitHub's toolkit for spec-driven development with AI coding agents
Task Master 🤖 AgentFree
AI task management that turns a PRD into tasks your coding agent works through
Fast Agent 🤖 AgentOpen source
Python framework for building, orchestrating and evaluating MCP-native AI agents
OpenSpec 🤖 AgentFree
Lightweight spec-driven development: agree on changes before the agent codes
CC Safety Net 🤖 AgentOpen source
Pre-execution guard that blocks destructive commands and secret access for coding agents
BMAD Method 🤖 AgentFree
Agile AI-driven development with analyst, PM, architect, developer and UX agents