Setup Guides

Step-by-step: OpenClaw, Ollama, gateway, and first agent.

Answer a few questions on the home page to get setup suggestions tailored to your budget and goals.

1. Install OpenClaw

Node 22+ required. macOS / Linux:

curl -fsSL https://openclaw.ai/install.sh | bash

Then run the onboarding wizard (auth, gateway, optional channels):

openclaw onboard --install-daemon

2. (Optional) Install Ollama for local models

On your BRAIN or solo Mac:

curl -fsSL https://ollama.com/install.sh | sh
ollama pull llama3.1:8b   # or qwen2.5:14b for better reasoning

Then point OpenClaw at Ollama:

openclaw config set agent.model ollama/llama3.1:8b
openclaw config set agent.baseUrl http://localhost:11434

3. Check the Gateway

openclaw gateway status

If you installed the daemon, it should already be running.

4. Open the Control UI

openclaw dashboard

Open http://127.0.0.1:18789/ in your browser to chat and manage.

Multi-machine (BRAIN + nodes)

On the BRAIN, bind the gateway so other machines can connect:

openclaw config set gateway.bind lan
openclaw gateway restart

On agent machines, configure the gateway URL to the BRAIN’s IP (or Tailscale hostname). Use Tailscale or VPN for remote access; see Architecture.

Full install options and details: docs.openclaw.ai/install · Getting Started