---
title: "Deploy OpenClaw | (Just Updated) Personal AI Agent Gateway, Token Set, Data Survives Redeploys"
description: "Personal AI agent gateway. Token preset, proxy-ready, data on a volume."
category: "AI/ML"
url: https://railway.com/deploy/openclaw-or-just-updated-personal-ai-age
---

# Deploy OpenClaw | (Just Updated) Personal AI Agent Gateway, Token Set, Data Survives Redeploys

Personal AI agent gateway. Token preset, proxy-ready, data on a volume.

**[Deploy OpenClaw | (Just Updated) Personal AI Agent Gateway, Token Set, Data Survives Redeploys on Railway](https://railway.com/template/openclaw-or-just-updated-personal-ai-age)**

Machine-readable deploy manifest (JSON, validated by TemplateCI): https://railway.com/deploy/openclaw-or-just-updated-personal-ai-age/manifest.json

- **Creator:** SuperSlowSloth
- **Category:** AI/ML

## Template content

### openclaw

- **Image:** ghcr.io/openclaw/openclaw:2026.10.1@sha256:9001e8a880d6ca028b590932b83b9335a26225e86c2a8a7aa9af7c59d6842953
- **Start command:** `/bin/sh -c 'export HOME=/data OPENCLAW_STATE_DIR=/data/.openclaw OPENCLAW_DISABLE_BONJOUR=1 NODE_OPTIONS=--max-old-space-size=1536; mkdir -p "$OPENCLAW_STATE_DIR"; if [ ! -f "$OPENCLAW_STATE_DIR/openclaw.json" ]; then (cd /app; node openclaw.mjs config set gateway.trustedProxies "[\"100.64.0.0/10\"]" --strict-json; node openclaw.mjs config set gateway.controlUi.allowedOrigins "[\"https://$RAILWAY_PUBLIC_DOMAIN\"]" --strict-json) || echo "[railway] config seed failed"; fi; echo "[railway] uid=$(id -u) owner=$(stat -c %u:%g /data) writable=$(test -w /data && echo yes || echo NO) port=${PORT:-8080}"; exec tini -s -- node /app/docker-entrypoint.mjs node openclaw.mjs gateway --allow-unconfigured --bind lan --port ${PORT:-8080}'`
- **Health check:** /healthz
- **Public domain:** Yes

## Documentation

# Deploy and Host OpenClaw on Railway

OpenClaw is an open-source personal AI agent gateway: one always-on server that connects your chat apps, models and tools, with a web Control UI to manage it. This template runs the official OpenClaw image with a gateway token already generated, so the Control UI is reachable and authenticated the moment the deploy finishes.

## About Hosting OpenClaw

This template deploys the official `ghcr.io/openclaw/openclaw` image, pinned by digest, as a single service with a volume at `/data`. OpenClaw's state directory (`/data/.openclaw`) lives on that volume, so configuration, sessions and credentials survive redeploys. On first boot the start command seeds the gateway config it needs to work behind Railway's proxy (trusted proxy range and the allowed Control UI origin) and then starts the gateway on Railway's injected port. Without that seed the gateway answers 403 `proxy_attribution_required` to every request. The `OPENCLAW_GATEWAY_TOKEN` variable is generated per deploy; use it to sign in to the Control UI and to call the gateway API.

## 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.

- **Works on first boot** — proxy trust and allowed origin are pre-seeded; no 403 on the public URL.
- **Token already set** — `OPENCLAW_GATEWAY_TOKEN` is auto-generated, not left blank.
- **Data survives redeploys** — state is on a volume at `/data`.
- **Nothing to fill in** — the deploy form is empty.

## Common Use Cases

- **Personal assistant** — one always-on agent reachable from your chat apps.
- **Tool and automation hub** — run agent tools through the authenticated gateway API.
- **Private AI front door** — keep model keys and conversations on infrastructure you control.

## Dependencies for OpenClaw Hosting

- A volume mounted at `/data` (included in this template).
- An API key for the model provider you want to use, added in the Control UI after sign-in.

### Deployment Dependencies

- [OpenClaw](https://github.com/openclaw/openclaw) — upstream project
- [OpenClaw image on GHCR](https://github.com/openclaw/openclaw/pkgs/container/openclaw) — the image this template deploys

### Implementation Details

Open the service's public domain and sign in with the value of `OPENCLAW_GATEWAY_TOKEN` (service Variables tab). Call the gateway API with the same token:

```bash
curl -X POST https:///tools/invoke \
  -H "Authorization: Bearer $OPENCLAW_GATEWAY_TOKEN" \
  -H "Content-Type: application/json" -d '{"tool":"sessions_list","args":{}}'
```


## Similar templates

- [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform.
- [stella](https://railway.com/deploy/stella) — Self-host stella with web, API, Postgres, Redis, and object storage.
- [Hermes Agent | OpenClaw Alternative with Dashboard](https://railway.com/deploy/hermes-agent-or-openclaw-alternative-wit) — Self-Hosted Hermes AI Agent for Telegram, Discord & Slack

Open this page in a browser: https://railway.com/deploy/openclaw-or-just-updated-personal-ai-age