How do I deploy Clawdbot on Railway?

You can deploy Clawdbot on Railway by clicking the "Deploy Now" button on this page. Railway will automatically set up all the necessary services and configurations for you.

What are the system requirements?

Railway handles all the infrastructure requirements. You only need a web browser to deploy and manage your application.

Is this template free to use?

Yes, this template is free to use within your existing Railway account.

Can I customize this template?

Yes, you can fully customize this template. After deployment, you will have full control of what you've deployed in your Railway project.

How do I get support for this template?

You can get support through our community forum: clawdbot-2b2487c1, or click "Get template help" for this template for more assistance.

Deploy and Host Clawdbot on Railway

Clawdbot is a self-hosted AI agent gateway that connects any LLM provider — Anthropic, OpenAI, MiniMax, and more — to a unified web dashboard. It includes chat, agent management, persistent memory, a file workspace, and support for messaging channels like Telegram, Discord, WhatsApp, and Slack.

About Hosting Clawdbot

Clawdbot runs as a Node.js gateway inside a Docker container. This template deploys it with a persistent volume so your config, agent memories, and workspace files survive redeployments. A minimal gateway config is baked into the Docker image and automatically seeded to the volume on first boot. After deploy, you configure your API keys and model provider entirely through the web-based Control UI — no SSH, no manual JSON editing, no environment variable juggling. The gateway supports hot-reloading, so config changes apply without downtime.

Setup After Deploy

Open the Control UI — go to your Railway-generated domain URL
Connect with your token — on the Gateway Access page, enter the CLAWDBOT_GATEWAY_TOKEN from your Railway Variables tab and click Connect
Set your API key — in the Control UI, go to Config and add your Anthropic API key
Set your workspace — in Config, set the agent workspace to /data/clawd so files persist on the volume
Start chatting — go to the Chat tab and send a message

All configuration is done through the Control UI. The default model is Claude Opus 4.5 — no extra setup needed.

Common Use Cases

Run a personal AI assistant accessible from any browser or messaging app
Host a multi-model gateway that routes between Claude, GPT, MiniMax, or any LLM provider
Deploy a persistent AI agent with its own workspace, memory, and file storage
Connect AI to Telegram, Discord, WhatsApp, or Slack from a single gateway

Dependencies for Clawdbot Hosting

An API key from at least one LLM provider (e.g. Anthropic, OpenAI, MiniMax)
A Railway account with a volume for persistent storage

Deployment Dependencies

Implementation Details

The Dockerfile uses an inline ENTRYPOINT to seed config on first boot:

A default gateway config is baked into the image at build time
On container start, the ENTRYPOINT checks if a config file exists on the volume
If not, it copies the baked default to the volume, then starts the gateway
Subsequent deploys reuse the existing volume config, preserving all your settings

The CLAWDBOT_STATE_DIR environment variable points the gateway to the volume-backed directory. The CLAWDBOT_GATEWAY_TOKEN secures access to the Control UI.

Why Deploy Clawdbot 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 Clawdbot 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.