Skip to main content

Setup

Install Ollama​

  • go to ollama.com
  • download and install ollama
  • then open terminal and pull a model
ollama pull gemma4

Install Openclaw​

  • go to openclaw.ai and follow the instruction to install through terminal
curl -fsSL https://openclaw.ai/install.sh | bash
  • model/auth provider: ollama
  • ollama base URL: http://127.0.0.1:11434
  • ollama mode: local
  • default model: gemma4
  • How do you want to hatch your bot? Open the Web UI

Launch Openclaw​

ollama launch openclaw --model gemma4

Check status​

openclaw gateway status
openclaw status
launchctl list | grep openclaw
curl http://localhost:18789
  • By default, OpenClaw listens on port 18789

Start or Restart​

openclaw gateway run        //Start interactively       
openclaw daemon start       //Start as daemon
openclaw gateway restart    //restart service

Change the model used by OpenClaw​

  1. Pull your model in Ollama: ollama pull llama3.2
  2. Run the onboard wizard: openclaw onboard
  3. Select Ollama → Local
  4. Set it in chat or CLI: /model ollama/llama3.2

Delete Openclaw​

openclaw uninstall --all --yes