CrewCode

Build your AI team with your existing subscriptions

Transform Claude, Gemini, and Copilot into a collaborative development team. No extra costs—just your existing AI subscriptions working together.

Why CrewCode?

💬 Slack Team Collaboration - Your AI Team in Slack

Bring AI agents directly into your team's workspace:

• Team-wide AI access - Everyone benefits from AI expertise in Slack channels
• Thread-based context - Maintains conversation history automatically
• Multi-agent collaboration - @claude, @gemini, @copilot work together in real-time
• Natural integration - Works like chatting with team members
• Shared knowledge - Team learns from AI interactions, not isolated sessions

✨ Other Benefits

• No additional costs - Use existing Claude Pro, Gemini, or GitHub Copilot subscriptions
• Multi-agent collaboration - Different AI models working on specialized tasks
• Parallel execution - Multiple agents working simultaneously
• Flexible integration - CLI, MCP server, or Slack bot

Quick Start

# Install
npm install -g crewcode

# Initialize
crewcode init

# Check system
crewcode doctor

# Try it out
crewcode query "@claude analyze my code"
crewcode execute "@claude create a login component"

Three Ways to Use

💬 Slack Mode - Team Collaboration (Recommended)

# Start CrewCode in your Slack workspace
crewcode slack

# Your team can now:
# - @mention AI agents in channels
# - Maintain context in threads
# - Share AI insights with the whole team

👉 Complete Slack Setup Guide →

🖥️ CLI Mode - Direct terminal usage

crewcode query "@claude review this code"
crewcode execute "@gemini optimize performance"
crewcode query "@claude @gemini @copilot compare approaches"

🔌 MCP Server Mode - IDE integration

crewcode mcp  # VS Code, Claude Desktop, Cursor

Supported AI Tools

• Claude Code - Advanced reasoning and analysis
• Gemini CLI - Real-time web access
• GitHub Copilot CLI - Specialized coding assistant

Basic Usage

# Read-only analysis
crewcode query "@claude explain this function"

# File creation/modification
crewcode execute "@claude implement user authentication"

# Parallel tasks
crewcode execute "@claude create tests" "@gemini write docs"

# Pipeline workflows
crewcode query "@architect design API" | \
crewcode execute "@backend implement it"

# Thread-based conversations
crewcode query "@claude design login" --thread "auth-feature"
crewcode execute "@claude implement it" --thread "auth-feature"

Create Custom Agents

# Let @crewcode create agents for you
crewcode execute "@crewcode Create a Python expert agent"
crewcode execute "@crewcode Create a React specialist with TypeScript"
crewcode execute "@crewcode Create a DevOps agent for Docker"

# Test your new agent
crewcode query "@python_expert Review my code"

Agent Configuration

Create crewcode.yaml (or agents.yaml for backward compatibility):

agents:
  - id: "frontend_dev"
    name: "React Expert"
    provider: "claude"
    working_directory: "./src"
    inline:
      type: "agent"
      system_prompt: |
        You are a senior React developer.
        Provide detailed examples and best practices.

Note: crewcode.yaml is the preferred configuration file name. The legacy agents.yaml is still supported for backward compatibility. If both files exist, crewcode.yaml takes priority.

Documentation

• 📖 CLI Guide - Complete CLI reference
• 🔌 MCP Integration - IDE setup and MCP servers
• ⚙️ Agent Configuration - Custom agents and advanced config
• 📚 Template System - Knowledge management and dynamic prompts for agents
• 🔧 Tool System - Tool integration and creation guide
• 🔧 Troubleshooting - Common issues and solutions
• 💬 Slack Integration - Slack bot setup

License

Apache-2.0 License - Copyright (c) 2025 SowonLabs

---

Built by SowonLabs