A personal coding & work buddy on Reachy Mini Wireless.

This is a fork of tomrikert/clawbody extending it into a full personal assistant. Upstream gives Clawson a body, OpenClaw brain, voice, and face tracking. This fork adds focus modes, snoozes, GitHub + Vercel monitoring, gesture-mapped notifications, a morning standup briefing, and a desktop widget.

See plan.md for the full v1 design.

Clawson combines OpenClaw's AI intelligence with Reachy Mini's expressive robot body, using OpenAI's Realtime API for ultra-responsive voice conversation. Your OpenClaw assistant (Clawson) can see, hear, speak, and move in the physical world — and now reacts in real time to your work surfaces too.

The robot looks at you when you speak!

ClawBody now includes real-time face tracking that makes conversations feel natural and engaging:

• Automatic Face Detection: Uses MediaPipe or YOLO to detect faces at 25Hz
• Smooth Head Tracking: Robot smoothly follows your face as you move
• Natural Eye Contact: Maintains engagement during conversation
• Graceful Fallback: Smoothly returns to neutral position when you leave

# Face tracking is enabled by default
clawbody

# Choose your tracker (MediaPipe is lighter, YOLO is more accurate)
clawbody --head-tracker mediapipe
clawbody --head-tracker yolo

# Disable if needed
clawbody --no-face-tracking

You don't need a physical Reachy Mini robot to use ClawBody!

ClawBody works with the Reachy Mini Simulator, a MuJoCo-based physics simulation that runs on your computer. Watch Clawson move and express emotions on screen while you talk to your OpenClaw agent.

# Install simulator support
pip install "reachy-mini[mujoco]"

# Start the simulator (opens a 3D window)
reachy-mini-daemon --sim

# In another terminal, run ClawBody
clawbody --gradio

🍎 Mac Users: Use mjpython -m reachy_mini.daemon.app.main --sim instead.

• 👁️ Face Tracking: Robot tracks your face and maintains eye contact during conversation
• 🎤 Real-time Voice Conversation: OpenAI Realtime API for sub-second response latency
• 🧠 OpenClaw Intelligence: Your responses come from OpenClaw with full tool access
• 👀 Vision: See through the robot's camera and describe the environment
• 💃 Expressive Movements: Natural head movements, emotions, dances, and audio-driven wobble
• 🦞 Clawson Embodied: Your friendly space lobster AI assistant, now with a body!
• 🖥️ Simulator Support: Works with or without physical hardware

┌─────────────────────────────────────────────────────────────────┐
│                     Your Voice / Microphone                      │
└─────────────────────────────┬───────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────┐
│              Reachy Mini Robot (or Simulator)                    │
│  ┌─────────────┐  ┌─────────────┐  ┌─────────────────────────┐  │
│  │ Microphone  │  │   Camera    │  │   Movement System       │  │
│  │  (input)    │  │  (vision)   │  │ (head, antennas, body)  │  │
│  └──────┬──────┘  └──────┬──────┘  └────────────▲────────────┘  │
└─────────┼────────────────┼──────────────────────┼───────────────┘
          │                │                      │
          ▼                ▼                      │
┌─────────────────────────────────────────────────┼───────────────┐
│                      ClawBody                   │               │
│  ┌─────────────────────────────────────────────┼────────────┐  │
│  │         OpenAI Realtime API Handler         │            │  │
│  │  • Speech recognition (Whisper)             │            │  │
│  │  • Text-to-speech (voices)                 ─┘            │  │
│  │  • Audio analysis → head wobble                          │  │
│  └─────────────────────────────────────────────────────────┘  │
│                           │                                     │
│                           ▼                                     │
│  ┌─────────────────────────────────────────────────────────┐  │
│  │              OpenClaw Gateway Bridge                     │  │
│  │  • AI responses from Clawson                            │  │
│  │  • Full OpenClaw tool access                            │  │
│  │  • Conversation memory & context                        │  │
│  └─────────────────────────────────────────────────────────┘  │
└─────────────────────────────────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────┐
│                    OpenClaw Gateway                              │
│  • Web browsing  • Calendar  • Smart home  • Memory  • Tools    │
└─────────────────────────────────────────────────────────────────┘

• Reachy Mini robot (Wireless or Lite)

• Any computer with Python 3.11+
• Install: pip install "reachy-mini[mujoco]"
• Simulation Setup Guide

• Python 3.11+
• Reachy Mini SDK installed
• OpenClaw gateway running
• OpenAI API key with Realtime API access

# Clone ClawBody
git clone https://github.com/tomrikert/clawbody
cd clawbody

# Create virtual environment
python -m venv .venv
source .venv/bin/activate

# Install ClawBody + simulator support + face tracking
pip install -e ".[mediapipe_vision]"
pip install "reachy-mini[mujoco]"

# Or for more accurate face tracking (requires more resources)
# pip install -e ".[yolo_vision]"

# Configure (see Configuration section)
cp .env.example .env
# Edit .env with your keys

# Terminal 1: Start the simulator
reachy-mini-daemon --sim

# Terminal 2: Run ClawBody
clawbody --gradio

# SSH into the robot
ssh pollen@reachy-mini.local

# Clone the repository
git clone https://github.com/tomrikert/clawbody
cd clawbody

# Install in the apps virtual environment
/venvs/apps_venv/bin/pip install -e .

1. Copy the example environment file:

cp .env.example .env

2. Edit .env with your configuration:

# Required
OPENAI_API_KEY=sk-...your-key...

# OpenClaw Gateway (required for AI responses)
OPENCLAW_GATEWAY_URL=http://localhost:18789  # or your host IP
OPENCLAW_TOKEN=your-gateway-token
OPENCLAW_AGENT_ID=main

# Optional - Customize voice
OPENAI_VOICE=cedar

# Optional - Face tracking (enabled by default)
ENABLE_FACE_TRACKING=true
HEAD_TRACKER_TYPE=mediapipe  # or "yolo" for more accuracy

# Terminal 1: Start simulator
reachy-mini-daemon --sim

# Terminal 2: Run ClawBody with web UI (recommended for simulator)
clawbody --gradio

The simulator opens a 3D window where you can watch the robot move. The Gradio web UI at http://localhost:7860 lets you interact via your browser's microphone.

# Basic usage
clawbody

# With debug logging
clawbody --debug

# With specific robot
clawbody --robot-name my-reachy

ClawBody gives Clawson these physical abilities:

When running with the simulator:

• 3D Visualization: Watch Clawson's movements in real-time
• Scene Options: Use --scene minimal to add objects (apple, duck, croissant)
• Full SDK Compatibility: The simulator behaves exactly like a real robot
• Dashboard Access: Visit http://localhost:8000 to see the robot dashboard

# Start simulator with objects on a table
reachy-mini-daemon --sim --scene minimal

This project is licensed under the Apache 2.0 License - see the LICENSE file for details.

ClawBody builds on:

• Pollen Robotics - Reachy Mini robot, SDK, and simulator
• OpenClaw - AI assistant framework (Clawson!)
• OpenAI - Realtime API for voice I/O
• MuJoCo - Physics simulation engine
• pollen-robotics/reachy_mini_conversation_app - Movement and audio systems

Contributions are welcome! Please feel free to submit a Pull Request.

• This project: GitHub Issues
• OpenClaw Skills: Submit ClawBody as a skill to ClawHub
• Reachy Mini Apps: Submit to Pollen Robotics