---
title: "Deploy Hermes Agent"
description: "Self-hosted Nous Research Hermes Agent: memory, skills, cron & API"
category: "AI/ML"
url: https://railway.com/deploy/hermes-agent-6
---

# Deploy Hermes Agent

Self-hosted Nous Research Hermes Agent: memory, skills, cron & API

**[Deploy Hermes Agent on Railway](https://railway.com/template/hermes-agent-6)**

- **Creator:** Nick K's Projects
- **Category:** AI/ML

## Template content

### nousresearch/hermes-agent:latest

- **Image:** nousresearch/hermes-agent:latest
- **Start command:** `gateway run`
- **Health check:** /health
- **Public domain:** Yes

## Documentation

# Deploy and Host Hermes Agent on Railway

Hermes Agent is an open-source, self-improving AI agent from Nous Research. It has persistent memory, a skill system, cron-based scheduling, and an OpenAI-compatible API — usable from a web dashboard, terminal, Telegram, Discord, or Slack. This template runs the official `nousresearch/hermes-agent` image with a persistent volume, so your memory, skills, and config survive every redeploy.

## About Hosting Hermes Agent

This template deploys the official Hermes Agent Docker image and starts the gateway (`gateway run`), which exposes an OpenAI-compatible API on port 8642 with a public `/health` endpoint plus the web dashboard on port 9119. All state — configuration, API keys, sessions, memory, and skills — is stored in a volume mounted at `/opt/data`, so nothing is lost between deploys. You supply one LLM provider key (OpenRouter by default) and a bearer key is auto-generated to protect the API. No external database is required.

## Common Use Cases

- An always-on personal AI agent with long-term memory and scheduled (cron) tasks
- A self-hosted, OpenAI-compatible API endpoint you can point other apps and tools at
- A Telegram, Discord, or Slack bot backed by a self-improving agent

## Dependencies for Hermes Agent Hosting

- An LLM provider API key (OpenRouter, OpenAI, Anthropic, Google, Groq, etc.)
- A Railway volume (included, mounted at `/opt/data`)

### Deployment Dependencies

- Hermes Agent source: https://github.com/NousResearch/hermes-agent
- Documentation: https://hermes-agent.nousresearch.com/docs

### Implementation Details

The API is protected by a bearer token in `API_SERVER_KEY` (auto-generated per deploy). After deploying, set your `OPENROUTER_API_KEY` and call the gateway:

```
curl https://.up.railway.app/health
```

## Why Deploy Hermes Agent 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 Hermes Agent 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/hermes-agent-6