OpenClaw Gateway and Dashboard: Run and Control Your AI Gateway

OpenClaw Gateway and Dashboard: Run and Control Your AI Gateway

The OpenClaw gateway is the core service that connects your channels (WhatsApp, Telegram, Slack, Discord) and the Control UI to your configured AI providers. Here is how to run it and use the dashboard.

Running the Gateway

After installation and onboarding, the gateway often runs as a service (e.g., via `openclaw onboard --install-daemon`). Check status with:

```bash

openclaw gateway status

```

To run it in the foreground (useful for debugging or quick tests):

```bash

openclaw gateway --port 18789

```

The gateway listens on the port you set (default 18789). It serves the Control UI and handles API requests from channels and the CLI.

Local API

The gateway exposes a local API (e.g., at http://localhost:3000 when using `openclaw gateway start` in some setups, or on the port you specify). You can use this API to send messages, trigger workflows, or integrate OpenClaw with other tools. See the OpenClaw docs for the exact base URL and endpoints in your version.

Dashboard (Control UI)

The Control UI is the web interface for chatting with OpenClaw without setting up a channel:

```bash

openclaw dashboard

```

This opens the dashboard in your browser (e.g., http://127.0.0.1:18789/). From there you can:

The dashboard is the fastest way to try OpenClaw after installation.

Useful Environment Variables

If you run OpenClaw as a service or need custom paths:

Next Steps

Once the gateway and dashboard are running, add channels, configure AI providers, and explore skills and automation to get the most out of OpenClaw.