---
title: "Deploy OpenFang"
description: "A template for OpenFang: The Agent Operating System."
category: "AI/ML"
url: https://railway.com/deploy/openfang
---

# Deploy OpenFang

A template for OpenFang: The Agent Operating System.

**[Deploy OpenFang on Railway](https://railway.com/template/openfang)**

- **Creator:** Nazih Kalo's Projects
- **Category:** AI/ML
- **Total deploys:** 23

## Template content

### openfang-railway-template

- **Source:** nazihkalo/openfang-railway-template

## Documentation

# Deploy and Host OpenFang on Railway
![](https://www.openfang.sh/assets/openfang-logo.png)
OpenFang is an open-source Agent Operating System built in Rust. It runs autonomous AI agents — called Hands — that work on schedules, build knowledge graphs, generate leads, manage social media, and report results to a dashboard. One binary, 27 LLM providers, 40 channel adapters.

## About Hosting OpenFang

OpenFang ships as a single Rust binary with a built-in web dashboard. This template wraps it in a lightweight Node.js proxy that handles Railway-specific concerns: a password-protected `/setup` page, automatic API key injection into the dashboard, a stable healthcheck endpoint, and generated config backed by a persistent volume at `/data`. Set three environment variables (`SETUP_PASSWORD`, `OPENFANG_API_KEY`, and one LLM provider key), attach a volume, and you're running.

## Common Use Cases

- **Autonomous research and OSINT** — activate the Researcher or Collector Hands to continuously monitor topics, companies, or competitors and deliver cited reports
- **Lead generation** — run the Lead Hand on a daily schedule to discover, enrich, and score prospects matching your ICP
- **Chat agents over messaging platforms** — connect agents to Telegram, Discord, Slack, WhatsApp, or any of the 40 built-in channel adapters
- **AI-powered content pipelines** — use the Clip Hand to turn YouTube videos into captioned vertical shorts, or the Twitter Hand to manage an autonomous posting schedule

## Dependencies for OpenFang Hosting

- **Railway volume** mounted at `/data` for persistent config, secrets, and SQLite state
- **One LLM provider API key** — Anthropic, OpenAI, Groq, Gemini, or any of the 27 supported providers

### Deployment Dependencies

- [OpenFang Documentation](https://www.openfang.sh/docs/getting-started)
- [OpenFang Configuration Reference](https://www.openfang.sh/docs/configuration)
- [OpenFang GitHub Repository](https://github.com/RightNow-AI/openfang)
- [Template Source](https://github.com/nazihkalo/openfang-railway-template)

## Why Deploy OpenFang 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 OpenFang 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.
- [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/openfang