Setup
Getting Started with OpenClaw
Install OpenClaw, configure your first instance, and verify everything works end to end.
8 min readLast updated Feb 10, 2026
Stuck?Check the troubleshooting index or ask in Discord.
Prerequisites
Before installing OpenClaw, make sure your system meets the minimum requirements.
- 64-bit Linux, macOS, or WSL2 on Windows
- 4 GB RAM minimum (8 GB recommended)
- Node.js 20+ or Docker 24+
- A supported model backend (Ollama, vLLM, or compatible API)
Check your Node version
OpenClaw requires Node.js 20 or later. Run
node --version to verify. Older versions will fail silently during startup.Installation
Choose your platform below for the appropriate install commands.
terminal
# Clone the repository
git clone https://github.com/openclaw/openclaw.git
cd openclaw
# Install dependencies
npm install
# Copy the example environment file
cp .env.example .env
# Start in development mode
npm run devFirst Run
1
Configure your environment
Open the .env file and set the required values. At minimum, you need MODEL_BACKEND_URL pointing to your model server.
.env
MODEL_BACKEND_URL=http://localhost:11434
PORT=3000
LOG_LEVEL=info2
Start the server
Run the start command. The server will initialize the database on first boot.
bash
npm run start3
Open the dashboard
Navigate to http://localhost:3000 in your browser. You should see the OpenClaw dashboard with model selection available.
Verify Installation
Run the built-in health check to confirm everything is connected:
terminal
curl http://localhost:3000/api/health
# Expected output:
# {"status":"ok","version":"1.4.2","models":3,"uptime":"12s"}Tip
If the health endpoint returns
models: 0, your model backend is likely not running. Check the troubleshooting guide for common errors.Next Steps
- Set up a reverse proxy for production access (Caddy or Nginx)
- Configure model routing and context window settings
- Review the performance tuning guide for high-traffic deployments
- Join the Discord community for support and config sharing