crewly

Crewly

Website: crewlyai.com

Crewly is an open-source multi-agent orchestration platform that coordinates AI coding agents (Claude Code, Gemini CLI, Codex) to work together as a team. It provides a web dashboard for real-time monitoring, task management, and team coordination — all running locally on your machine.

Features

• Multi-agent teams — Create teams with different roles (developer, QA, PM, orchestrator) and watch them collaborate
• Multi-runtime support — Use Claude Code, Gemini CLI, or OpenAI Codex — mix and match per agent
• Real-time dashboard — Monitor all agents through live terminal streams, task boards, and activity feeds
• Skill system — Agents coordinate through bash skills (report status, delegate tasks, manage memory)
• Agent memory — Persistent knowledge that agents build and share across sessions
• Slack integration — Optional two-way Slack bridge for team notifications
• Local-first — Everything runs on your machine. No data leaves your environment.

Quick Start

# Initialize Crewly in your project (no global install needed)
npx crewly init

# Or install globally first
npm install -g crewly
crewly init

# Start the platform
crewly start

The init command walks you through provider selection, installs agent skills, and scaffolds a .crewly/ directory. Then crewly start launches the backend server and opens the web dashboard. From there:

• Create a team with agents assigned to roles
• Assign the team to a project (any local code directory)
• Watch agents work in real time through live terminal streams

Prerequisites

• Node.js v20+ and npm v9+
• At least one AI coding CLI installed:

Runtime	Install	Verify
Claude Code (default)	npm install -g @anthropic-ai/claude-code	claude --version
Gemini CLI	npm install -g @google/gemini-cli	gemini --version
Codex (OpenAI)	npm install -g @openai/codex	codex --version

API keys: Gemini CLI requires GEMINI_API_KEY. Codex requires an OpenAI API key. Claude Code authenticates through its own login flow.

Architecture

┌─────────────────────────────────────────────────────┐
│                   Web Dashboard                      │
│              (React + xterm.js + WebSocket)          │
└───────────────────────┬─────────────────────────────┘
                        │
┌───────────────────────▼─────────────────────────────┐
│                 Backend Server                       │
│           (Express + Socket.IO + PTY)                │
│                                                      │
│  ┌──────────┐ ┌──────────┐ ┌───────────────────┐   │
│  │ Services │ │ Scheduler│ │ Agent Registration │   │
│  │ (Storage,│ │ (Check-  │ │ (Heartbeat, Idle   │   │
│  │  Memory) │ │  ins)    │ │  Detection, Resume)│   │
│  └──────────┘ └──────────┘ └───────────────────┘   │
└───────────────────────┬─────────────────────────────┘
                        │
        ┌───────────────┼───────────────┐
        ▼               ▼               ▼
┌──────────────┐ ┌─────────────┐ ┌─────────────┐
│  Agent PTY   │ │  Agent PTY  │ │  Agent PTY  │
│  (Claude)    │ │  (Gemini)   │ │  (Codex)    │
│              │ │             │ │             │
│  Skills ◄────┤ │  Skills ◄───┤ │  Skills ◄───┤
│  Memory ◄────┤ │  Memory ◄───┤ │  Memory ◄───┤
└──────────────┘ └─────────────┘ └─────────────┘

Storage: ~/.crewly/ (global) + project/.crewly/ (per-project)

How It Works

• You create a team in the dashboard with agents assigned to roles
• You assign the team to a project (any local code directory)
• Crewly launches each agent as a CLI process in its own PTY session
• Agents receive role-specific prompts and use skills (bash scripts) to communicate, report progress, and manage tasks
• You monitor everything in real time through the web dashboard

Agent Runtimes

Runtime	Default Command	Notes
Claude Code	claude --dangerously-skip-permissions	Default runtime
Gemini CLI	gemini --yolo	Requires GEMINI_API_KEY
Codex (OpenAI)	codex --full-auto	Requires OpenAI API key

You can change the default runtime or customize launch commands in Settings.

CLI Commands

crewly init          # Interactive setup wizard (alias: onboard)
crewly start         # Start backend + open dashboard
crewly stop          # Stop all services and sessions
crewly status        # Show running services
crewly logs          # View aggregated logs
crewly upgrade       # Upgrade to latest version
crewly install [id]  # Install a skill from marketplace
crewly search [q]    # Search skill marketplace

Configuration

Optional environment variables (.env file or shell):

GEMINI_API_KEY=your_key_here       # Required for Gemini CLI runtime

SLACK_BOT_TOKEN=xoxb-...           # Optional: Slack integration
SLACK_APP_TOKEN=xapp-...
SLACK_SIGNING_SECRET=...

LOG_LEVEL=info                     # debug, info, warn, error
WEB_PORT=8787                      # Dashboard port (default: 8787)

Docker

Run Crewly with a single command using Docker:

# 1. Clone the repo
git clone https://github.com/stevehuang0115/crewly.git
cd crewly

# 2. Add your API keys to .env
cp .env.example .env
# Edit .env and add ANTHROPIC_API_KEY, GEMINI_API_KEY, etc.

# 3. Start Crewly
docker compose up

# Dashboard available at http://localhost:8787

To mount a project directory for agents to work on, edit docker-compose.yml and uncomment the volume mount:

volumes:
  - crewly_data:/home/node/.crewly
  - /path/to/your/project:/home/node/project  # <-- uncomment and edit

Build the image manually:

# On Apple Silicon, use --platform linux/amd64
docker build --platform linux/amd64 -t crewly .
docker run -p 8787:8787 --env-file .env crewly

Development

# Clone the repository
git clone https://github.com/stevehuang0115/crewly.git
cd crewly

# Install dependencies
npm install

# Build all components (backend + frontend + CLI)
npm run build

# Start in dev mode (backend + frontend with hot-reload)
npm run dev

# Run tests
npm run test:unit

See CONTRIBUTING.md for detailed development guidelines.

Demo

Screenshots and demo video coming soon. Star the repo to get notified!

Community

• Bug reports & feature requests — GitHub Issues
• Questions & discussions — GitHub Discussions
• Contributing — See CONTRIBUTING.md

License

MIT