---
title: "Deploy OpenClaw (Clawdbot / Moltbot) [Nov'26]"
description: "Self-hosted AI assistant (Clawdbot) for Telegram, WhatsApp, Slack, Discord"
category: "AI/ML"
url: https://railway.com/deploy/openclaw-jun26
---

# Deploy OpenClaw (Clawdbot / Moltbot) [Nov'26]

Self-hosted AI assistant (Clawdbot) for Telegram, WhatsApp, Slack, Discord

**[Deploy OpenClaw (Clawdbot / Moltbot) [Nov'26] on Railway](https://railway.com/template/openclaw-jun26)**

Machine-readable deploy manifest (JSON, validated by TemplateCI): https://railway.com/deploy/openclaw-jun26/manifest.json

- **Creator:** Tasha
- **Category:** AI/ML
- **Total deploys:** 7

## Template content

### openclaw-railway-template

- **Source:** Amritasha/openclaw-railway-template
- **Health check:** /healthz
- **Public domain:** Yes

## Documentation

# Deploy and Host OpenClaw (Clawdbot) on Railway

**OpenClaw** is an open-source, **self-hosted personal AI assistant** that connects to the chat apps you already use — **Telegram, WhatsApp, Slack, Discord**, and more. It runs your own AI agent on your own infrastructure, keeping your data private and under your control.

> **Formerly Clawdbot / Moltbot.** If you used the project under either of those earlier names, this is the same OpenClaw — the Railway template and env vars below are current for the OpenClaw release.

## About Hosting OpenClaw on Railway

Hosting OpenClaw on Railway involves running the **OpenClaw gateway** inside a Docker container alongside a lightweight setup wizard for configuration. The gateway acts as a bridge between your chosen AI provider (**Anthropic, OpenAI, or Gemini**) and your connected chat channels. Railway handles SSL, networking, and uptime automatically. All configuration, credentials, and workspace files are persisted to a **Railway Volume** mounted at `/data`, so nothing is lost between redeploys. After deployment, you configure your AI provider and onboard channels through a password-protected web UI — no command line required.

## Common Use Cases for Self-Hosted OpenClaw

- **Personal AI assistant**: Connect OpenClaw to WhatsApp or Telegram and chat with your AI model from your phone, on channels you already use daily.
- **Team bot**: Hook OpenClaw into Slack or Discord to give your team a shared AI assistant with persistent context and workspace files.
- **Private AI deployment**: Self-host your AI agent so API keys and conversation data never pass through third-party servers.

## Dependencies for OpenClaw Hosting

- **Railway Volume** — mounted at `/data` (minimum 5 GB recommended) for persisting OpenClaw config, credentials, and workspace files across redeploys
- **AI Provider API Key** — from Anthropic, OpenAI, Google Gemini, or any OpenAI-compatible endpoint; configured after deployment via the `/setup` wizard

### Deployment Dependencies

- [OpenClaw — GitHub](https://github.com/openclaw/openclaw)
- [OpenClaw Documentation](https://docs.openclaw.ai)
- [OpenClaw Railway Install Guide](https://docs.openclaw.ai/install/railway)
- [Supported Channels](https://docs.openclaw.ai/channels)

### Implementation Details

The template wraps the official `openclaw` npm package with a small Express server that:

1. Spawns the OpenClaw gateway on an internal port (`18789`)
2. Serves a password-protected setup wizard at `/setup`
3. Proxies all other traffic (including WebSockets) to the gateway
4. Exposes a health check at `/healthz` for Railway's health monitoring

**Key environment variables:**

\`\`\`env
SETUP_PASSWORD=your-secure-password     # protects the /setup wizard
OPENCLAW_GATEWAY_TOKEN=     # stable admin token for the gateway
OPENCLAW_STATE_DIR=/data/.openclaw      # persisted config directory
OPENCLAW_WORKSPACE_DIR=/data/workspace  # persisted workspace directory
\`\`\`

After deployment, visit `https://.up.railway.app/setup` to configure your AI provider and onboard your first channel.

## 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.

## Similar templates

- [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform.
- [Weaviate](https://railway.com/deploy/weaviate-1) — Vector database with hybrid search and an API key-protected API
- [Möbius v0.1 Personal AI OS](https://railway.com/deploy/mobius-v01-personal-ai-os) — Self-hosted AI agent that builds and runs apps for you, with memory.

Open this page in a browser: https://railway.com/deploy/openclaw-jun26