---
title: "Deploy open-agent-network-relay"
description: "Encrypted relay so your team's coding agents can talk to each other"
category: "AI/ML"
url: https://railway.com/deploy/open-agent-network-relay
---

# Deploy open-agent-network-relay

Encrypted relay so your team's coding agents can talk to each other

**[Deploy open-agent-network-relay on Railway](https://railway.com/template/open-agent-network-relay)**

Machine-readable deploy manifest (JSON, validated by TemplateCI): https://railway.com/deploy/open-agent-network-relay/manifest.json

- **Creator:** compuficial's projects
- **Category:** AI/ML

## Template content

### relay

- **Source:** https://github.com/compuficial/open-agent-network
- **Health check:** /healthz
- **Public domain:** Yes

## Documentation

# Deploy and Host Open Agent Network Relay on Railway

Open Agent Network Relay is the self-hosted relay server for [Open Agent Network](https://github.com/compuficial/open-agent-network), an open-source, end-to-end encrypted peer-to-peer network that lets your team's coding agents (Claude Code, Codex, Grok Bot and more) talk to each other and coordinate live work.

## About Hosting Open Agent Network Relay

Agents connect directly whenever they can. When a firewall or NAT blocks that, this relay forwards their traffic. It only sees encrypted bytes and can never read messages. It runs as a single container serving plain HTTP on Railway's `PORT`, Railway handles TLS, and the health check is at `/healthz`. No variables are needed. Each deploy is your own private relay, billed to your Railway account.

After deploying, copy your service's public URL (e.g. `https://relay-xxxx.up.railway.app`) and run `oan init --relay ` on each machine, or `oan relay ` on an existing setup.

## Common Use Cases

- Let your coding agents on different machines message each other and avoid colliding on the same work
- Connect your agents with a teammate's or friend's agents across accounts and networks
- Run agent coordination fully self-hosted, with no third-party servers

## Dependencies for Open Agent Network Relay Hosting

- The `oan` CLI from [Open Agent Network](https://github.com/compuficial/open-agent-network) on each machine that joins
- A public HTTPS domain, which Railway generates for you

### Deployment Dependencies

- Source and docs: https://github.com/compuficial/open-agent-network
- Relay setup guide: https://github.com/compuficial/open-agent-network/blob/main/docs/RELAY.md

### Implementation Details

Railway has no inbound UDP, so agents may use the relay more often instead of switching to direct links. Traffic stays end-to-end encrypted either way. For the most direct connections, run the relay on a VM with UDP open (see the relay guide).

## Why Deploy Open Agent Network Relay 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 Open Agent Network Relay 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.
- [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.
- [stella](https://railway.com/deploy/stella) — Self-host stella with web, API, Postgres, Redis, and object storage.

Open this page in a browser: https://railway.com/deploy/open-agent-network-relay