How to Run the OpenClaw Gateway Locally

Use the local gateway mode, verify the RPC probe, and only open the dashboard after the service is responding cleanly on your machine.

Running the gateway locally is the standard OpenClaw workflow. The main thing that trips people up is trying to debug channels or models before they have confirmed the gateway process is healthy.

Quick answer

Run onboarding in local mode, confirm openclaw gateway status --require-rpc, and only then open the dashboard or attach channels.

Command line steps

1. Write the local-mode config

Onboarding or setup should set gateway.mode=local. If it does not, repair that first.

2. Start or restart the gateway

If the service already exists, restart it instead of launching duplicate foreground processes.

3. Open the control surface only after the probe is green

A working dashboard is a confirmation step, not the first diagnostic step.

What to check if it still fails

• If the gateway refuses to start because gateway.mode is missing, treat that as config damage and run openclaw doctor --fix.
• If the RPC probe fails, read live logs with openclaw logs --follow before you touch model settings.
• If you need a foreground debug session, openclaw gateway --verbose is better than repeatedly restarting blind.