Spaces:
Running
Running
| <html lang="en"> | |
| <head> | |
| <meta charset="UTF-8"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> | |
| <title>ReachyClaw - Reachy Mini App</title> | |
| <link rel="preconnect" href="https://fonts.googleapis.com"> | |
| <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> | |
| <link href="https://fonts.googleapis.com/css2?family=Space+Grotesk:wght@400;500;700&display=swap" rel="stylesheet"> | |
| <link rel="stylesheet" href="style.css"> | |
| </head> | |
| <body> | |
| <section class="hero"> | |
| <div class="topline"> | |
| <div class="brand"> | |
| <span class="logo">🤖</span> | |
| <span class="brand-name">ReachyClaw</span> | |
| </div> | |
| <div class="pill">Voice conversation · OpenClaw brain · Full body control</div> | |
| </div> | |
| <div class="hero-grid"> | |
| <div class="hero-copy"> | |
| <div class="eyebrow">Reachy Mini App</div> | |
| <h1>Your OpenClaw agent, embodied.</h1> | |
| <p class="lede"> | |
| Give your OpenClaw AI agent a Reachy Mini robot body. | |
| OpenClaw is the brain — it controls what the robot says, | |
| how it moves, and what it sees. OpenAI Realtime API handles voice I/O. | |
| </p> | |
| <div class="hero-actions"> | |
| <a href="#simulator" class="btn primary">🖥️ Try with Simulator</a> | |
| <a href="#features" class="btn ghost">See features</a> | |
| </div> | |
| <div class="hero-badges"> | |
| <span>🧠 OpenClaw brain</span> | |
| <span>🎙️ OpenAI Realtime voice</span> | |
| <span>💃 Full body control</span> | |
| <span>🖥️ No robot required!</span> | |
| </div> | |
| </div> | |
| <div class="hero-visual"> | |
| <div class="glass-card"> | |
| <img src="https://huggingface.co/spaces/pollen-robotics/reachy_mini_conversation_app/resolve/main/docs/assets/reachy_mini_dance.gif" | |
| alt="Reachy Mini Robot Dancing" | |
| class="hero-gif"> | |
| <p class="caption">Works with physical robot OR MuJoCo simulator!</p> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <section class="section simulator-callout" id="simulator"> | |
| <div class="story-card highlight"> | |
| <h2>🖥️ No Robot? No Problem!</h2> | |
| <p class="story-text" style="font-size: 1.1rem;"> | |
| <strong>You don't need a physical Reachy Mini robot to use ReachyClaw!</strong><br><br> | |
| ReachyClaw works with the Reachy Mini Simulator, a MuJoCo-based physics simulation | |
| that runs on your computer. Watch your agent move and express emotions on screen | |
| while you talk. | |
| </p> | |
| <div class="architecture-preview" style="margin: 1.5rem 0;"> | |
| <pre> | |
| # Install simulator support | |
| pip install "reachy-mini[mujoco]" | |
| # Start the simulator (opens 3D window) | |
| reachy-mini-daemon --sim | |
| # In another terminal, run ReachyClaw | |
| reachyclaw --gradio | |
| </pre> | |
| </div> | |
| <p class="caption">🍎 Mac Users: Use <code>mjpython -m reachy_mini.daemon.app.main --sim</code> instead</p> | |
| <a href="https://huggingface.co/docs/reachy_mini/platforms/simulation/get_started" class="btn primary" style="margin-top: 1rem;" target="_blank"> | |
| 📚 Simulator Setup Guide | |
| </a> | |
| </div> | |
| </section> | |
| <section class="section" id="features"> | |
| <div class="section-header"> | |
| <h2>What's inside</h2> | |
| <p class="intro"> | |
| ReachyClaw makes OpenClaw the actual brain — every message, every movement, every decision. | |
| </p> | |
| </div> | |
| <div class="feature-grid"> | |
| <div class="feature-card"> | |
| <div class="icon">🧠</div> | |
| <h3>OpenClaw is the brain</h3> | |
| <p>Every user message goes through your OpenClaw agent. No GPT-4o guessing — real responses with full tool access.</p> | |
| </div> | |
| <div class="feature-card"> | |
| <div class="icon">🎤</div> | |
| <h3>Real-time voice</h3> | |
| <p>OpenAI Realtime API for low-latency speech-to-text and text-to-speech. Voice I/O only — no GPT-4o brain.</p> | |
| </div> | |
| <div class="feature-card"> | |
| <div class="icon">🤖</div> | |
| <h3>Full body control</h3> | |
| <p>OpenClaw controls the robot body via action tags — head movement, emotions, dances, camera, face tracking.</p> | |
| </div> | |
| <div class="feature-card"> | |
| <div class="icon">👀</div> | |
| <h3>Vision</h3> | |
| <p>See through the robot's camera. Your agent can look around and describe what it sees.</p> | |
| </div> | |
| <div class="feature-card"> | |
| <div class="icon">🖥️</div> | |
| <h3>Simulator support</h3> | |
| <p>No robot? Run with MuJoCo simulator and watch your agent move in a 3D window.</p> | |
| </div> | |
| <div class="feature-card"> | |
| <div class="icon">⚡</div> | |
| <h3>Instant startup</h3> | |
| <p>No 30-second context fetch. GPT-4o is just a relay — the session starts immediately.</p> | |
| </div> | |
| </div> | |
| </section> | |
| <section class="section story" id="how-it-works"> | |
| <div class="story-grid"> | |
| <div class="story-card"> | |
| <h3>How it works</h3> | |
| <p class="story-text">OpenClaw controls everything</p> | |
| <ol class="story-list"> | |
| <li><span>🎤</span> Robot captures your voice</li> | |
| <li><span>📝</span> OpenAI Realtime transcribes your speech</li> | |
| <li><span>🧠</span> Your message goes to OpenClaw (the real brain)</li> | |
| <li><span>🤖</span> OpenClaw responds with text + action tags like [EMOTION:happy]</li> | |
| <li><span>💃</span> ReachyClaw executes the actions on the robot</li> | |
| <li><span>🔊</span> Clean text goes to TTS — robot speaks while moving</li> | |
| </ol> | |
| </div> | |
| <div class="story-card secondary"> | |
| <h3>Prerequisites</h3> | |
| <p class="story-text">Choose your setup:</p> | |
| <div class="chips"> | |
| <span class="chip">🧠 OpenClaw Gateway</span> | |
| <span class="chip">🔑 OpenAI API Key</span> | |
| <span class="chip">🐍 Python 3.11+</span> | |
| </div> | |
| <p class="story-text" style="margin-top: 1rem;"> | |
| <strong>Option A:</strong> 🤖 Physical Reachy Mini robot<br> | |
| <strong>Option B:</strong> 🖥️ MuJoCo Simulator (free, no hardware!) | |
| </p> | |
| <a href="https://github.com/EdLuxAI/reachyclaw#readme" class="btn ghost wide" style="margin-top: 1rem;"> | |
| View installation guide | |
| </a> | |
| </div> | |
| </div> | |
| </section> | |
| <section class="section"> | |
| <div class="section-header"> | |
| <h2>Quick start</h2> | |
| <p class="intro">Get ReachyClaw running with the simulator</p> | |
| </div> | |
| <div class="story-card"> | |
| <div class="architecture-preview"> | |
| <pre> | |
| # Clone ReachyClaw | |
| git clone https://github.com/EdLuxAI/reachyclaw | |
| cd reachyclaw | |
| # Create virtual environment | |
| python -m venv .venv | |
| source .venv/bin/activate | |
| # Install ReachyClaw + 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 ReachyClaw | |
| reachyclaw --gradio | |
| </pre> | |
| </div> | |
| </div> | |
| </section> | |
| <footer class="footer"> | |
| <p> | |
| ReachyClaw — your OpenClaw agent, embodied in Reachy Mini.<br> | |
| <strong>Works with physical robot OR simulator!</strong><br><br> | |
| Learn more about <a href="https://github.com/openclaw/openclaw">OpenClaw</a>, | |
| <a href="https://github.com/pollen-robotics/reachy_mini">Reachy Mini</a>, and | |
| <a href="https://huggingface.co/docs/reachy_mini/platforms/simulation/get_started">the Simulator</a>. | |
| </p> | |
| </footer> | |
| </body> | |
| </html> | |