Deploy OpenClaw (aka Moltbot & Clawdbot)
The AI that actually does things
Just deployed
/data
Deploy and Host OpenClaw on Railway
OpenClaw is the AI that actually does things. It clears your inbox, sends emails, manages your calendar, and checks you in for flights—all from WhatsApp, Telegram, or any chat app you already use. Self-host your own AI personal assistant with full control over your data.
FAQ
Q: How do I access the setup page?
A: Go to /setup on your deployed instance. When prompted for credentials, use the generated SETUP_PASSWORD from your Railway Variables as the password. The username field is ignored—you can leave it empty or enter anything.
Q: I see "gateway disconnected" or authentication errors in the Control UI. What should I do?
A: Go back to /setup and click the "Open OpenClaw UI" button from there. The setup page passes the required auth token to the UI. Accessing the UI directly without the token will cause connection errors.
Q: I don't see the TUI option on the setup page.
A: Make sure ENABLE_WEB_TUI=true is set in your Railway Variables and redeploy. The web terminal is disabled by default.
Q: How do I approve pairing for Telegram or Discord?
A: Go to /setup and use the "Approve Pairing" dialog to approve pending pairing requests from your chat channels.
Q: How do I change the AI model after setup?
A: Use the OpenClaw CLI to switch models. Access the web terminal at /tui (if enabled) or SSH into your container and run:
openclaw models set provider/model-id
For example: openclaw models set anthropic/claude-sonnet-4-20250514 or openclaw models set openai/gpt-4-turbo.
Q: My config seems broken or I'm getting strange errors. How do I fix it?
A: Go to /setup and click the "Run Doctor" button. This runs openclaw doctor --repair which performs health checks on your gateway and channels, creates a backup of your config, and removes any unrecognized or corrupted configuration keys.
About Hosting OpenClaw
Hosting OpenClaw requires building from source, configuring authentication with your preferred LLM provider, and managing persistent state for configurations and workspaces. This Railway template simplifies the entire process with a one-click deployment that includes a web-based setup wizard at /setup. The wizard handles onboarding, API key configuration, and optional messaging channel setup—no command-line experience required. All state is persisted to a Railway Volume, ensuring your configuration survives redeploys. The template also provides automatic reverse proxying with authentication injection and one-click backup exports.
Common Use Cases
- Automate email management: triage your inbox, draft replies, send messages on your behalf
- Calendar and scheduling: create events, check availability, manage appointments via chat
- Travel assistance: check in for flights, get boarding passes, and manage itineraries
Dependencies for OpenClaw Hosting
- Railway Volume mounted at
/datafor persistent storage - API key from a supported LLM provider (OpenAI, Anthropic, Google, etc.)
Deployment Dependencies
Why Deploy OpenClaw on Railway?
Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.
By deploying OpenClaw on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.
Template Content

