Skip to main content
A personal AI assistant with a control panel, messaging channels and an optional browser. The template runs OpenClaw 2026.10.7 with headless Chromium inside the container. You bring the model key: Vertra Cloud does not host a model.

Step-by-step guide: OpenClaw from the key to your channels

Provider and model, the gateway token, approving devices, Telegram, Discord, Slack and WhatsApp, and the browser.

What it creates

One app (image) with the panel at the app address. Memory: 3 GB minimum with the browser (4 GB recommended) or 2 GB without it (3 GB recommended). It needs a plan with Docker images and one free image slot; see Plans and limits.

What the wizard asks

What you get

The app address, the gateway token (shown once) and the next step. WhatsApp is paired by QR code in the panel.

Variables

Resources and limits

  • Port 18789. First boot 30 to 45 seconds, and 1 to 3 minutes with Discord or Slack.
  • State in /app/.openclaw; channel plugins from npm add about 240 MB.
  • Zero-downtime deploy is off; rollback returns the data too.
  • The agent browser blocks private and local networks.

License

OpenClaw is distributed under the MIT license. The Chromium in the image follows the Chromium project’s license. This template is a Vertra Cloud packaging and is not affiliated with the project. See also the public page and the other official templates.
Last modified on October 28, 2026