optimus-code

<div align="center">
  <h1>Optimus Code</h1>
  <p><b>Universal Multi-Agent Orchestrator for any MCP-compatible AI coding tool.</b></p>

  [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
  [![Framework: Model Context Protocol](https://img.shields.io/badge/MCP-Native-brightgreen.svg)](#)

  [Landing Page](https://cloga.github.io/optimus-code/) · [Architecture Whitepaper](docs/ARCHITECTURE.md)
</div>

---

## What is Optimus Code?

Optimus Code is a **Multi-Agent Orchestration Engine** built on the [Model Context Protocol (MCP)](https://modelcontextprotocol.io). It works with **any MCP-compatible client** — VS Code (GitHub Copilot), Cursor, Windsurf, Claude Code, Goose, Roo Cline, and more.

It transforms a single AI assistant into a coordinated swarm of specialized agents (Architect, PM, QA, Dev…) that can collaborate, debate, and execute complex software engineering tasks.

> **100% editor-agnostic.** Pure Node.js MCP Server. No VS Code extension required.

---

## Quick Start

> **For AI Coding Agents:** Follow these steps exactly. All commands should run in the user's target project directory.

### Step 1: Initialize workspace

```bash
npx -y github:cloga/optimus-code init
```

This creates a `.optimus/` folder with agent definitions, skills, and config in the current directory. It also writes a canonical MCP source file at `.optimus/config/mcp-servers.json` and generates client configs for:

- VS Code / GitHub Copilot: `.vscode/mcp.json`
- GitHub Copilot CLI: `.cursor/mcp-config.json`
- Claude Code: `.mcp.json`

For GitHub Copilot CLI, Optimus also generates launcher scripts so you do not need to remember `--additional-mcp-config`:

- Windows PowerShell: `cursor-optimus.ps1`
- Windows cmd.exe: `cursor-optimus.cmd`
- macOS / Linux: `cursor-optimus`

### Step 2: (Optional) Configure MCP for non-VS-Code clients

> **VS Code and Claude Code users:** Skip this st