ClawBody
Voice conversation · OpenClaw AI · Expressive motion
Reachy Mini App

Give OpenClaw a physical body.

Connect your OpenClaw AI assistant (Clawson) to a Reachy Mini robot. Ultra-responsive voice conversation through OpenAI Realtime API, intelligent responses from OpenClaw, and expressive robot movements.

🖥️ Try with Simulator See features
🎙️ OpenAI Realtime 🦞 OpenClaw Gateway 💃 Expressive movement 🖥️ No robot required! 
  You speak → Reachy Mini 🎤
          (or Simulator 🖥️)
                  ↓
         OpenAI Realtime API
      (speech recognition + TTS)
                  ↓
          OpenClaw Gateway
        (Clawson's brain 🦞)
                  ↓
     Robot speaks & moves 🤖💃

Works with physical robot OR MuJoCo simulator!

🖥️ No Robot? No Problem!

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 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

📚 Simulator Setup Guide

What's inside

ClawBody combines real-time voice conversation, OpenClaw intelligence, and expressive robot motion.

🎤

Real-time voice

Sub-second latency using OpenAI's Realtime API for natural, responsive conversation.

🦞

OpenClaw brain

Full Clawson capabilities—tools, memory, personality—through the OpenClaw gateway.

👀

Vision

See through the robot's camera. Ask Clawson what it sees and get visual descriptions.

💃

Expressive motion

Audio-driven head wobble, emotions, dances, and natural movements while speaking.

🖥️

Simulator support

No robot? Run with MuJoCo simulator and watch Clawson move in a 3D window.

⚡

Hybrid architecture

Best of both worlds: OpenAI's voice tech + OpenClaw's full AI capabilities.

How it works

From speech to response in under a second

  1. 🎤 Robot (or simulator) captures your voice
  2. 🔇 Voice Activity Detection identifies when you stop speaking
  3. 📝 OpenAI Realtime transcribes your speech instantly
  4. 🦞 OpenClaw processes your message with full AI capabilities
  5. 🔊 OpenAI Realtime speaks the response naturally
  6. 🤖 Robot moves expressively while speaking

Prerequisites

Choose your setup:

🦞 OpenClaw Gateway 🔑 OpenAI API Key 🐍 Python 3.11+

Option A: 🤖 Physical Reachy Mini robot
Option B: 🖥️ MuJoCo Simulator (free, no hardware!)

View installation guide

Quick start

Get ClawBody running with the simulator

# 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
pip install -e .
pip install "reachy-mini[mujoco]"

# Configure (edit with your OpenClaw URL and OpenAI key)
cp .env.example .env
nano .env

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

# Terminal 2: Run ClawBody
clawbody --gradio