---
title: "Deploy Hermes Agent | Curated Setup | Self-improving option for OpenClaw, Claude Code, Codex and more"
description: "The simplest curated setup for an Hermes Agent. Curated by impacte.tech"
category: "AI/ML"
url: https://railway.com/deploy/impacte-hermes-agent
---

# Deploy Hermes Agent | Curated Setup | Self-improving option for OpenClaw, Claude Code, Codex and more

The simplest curated setup for an Hermes Agent. Curated by impacte.tech

**[Deploy Hermes Agent | Curated Setup | Self-improving option for OpenClaw, Claude Code, Codex and more on Railway](https://railway.com/template/impacte-hermes-agent)**

- **Creator:** Gabriel Amazonas's Projects
- **Category:** AI/ML
- **Total deploys:** 15

## Template content

### Hermes Agent https://raw.githubusercontent.com/NousResearch/hermes-agent/refs/heads/main/website/static/img/apple-touch-icon.png

- **Source:** https://github.com/impacte-tech/hermes-agent-template
- **Public domain:** Yes

## Documentation

# Hermes Agent — Railway Template

# Deploy and Host
Deploy [Hermes Agent](https://github.com/NousResearch/hermes-agent) on [Railway](https://railway.app) with a web-based admin dashboard for configuration, gateway management, and user pairing.

 ## Why Deploy
> Hermes Agent is an autonomous AI agent by [Nous Research](https://nousresearch.com/) that lives on your server, connects to your messaging channels (Telegram, Discord, Slack, etc.), and gets more capable the longer it runs.





## Features

- **Admin Dashboard** — dark-themed UI to configure providers, channels, tools, and manage the gateway
- **One-Page Setup** — provider dropdown, checkbox-based channel/tool toggles — no config files to edit
- **Gateway Management** — start, stop, restart the Hermes gateway from the browser
- **Live Status** — stat cards for gateway state, uptime, model, and pending pairing requests
- **Live Logs** — streaming gateway log viewer
- **User Pairing** — approve or deny users who message your bot, revoke access anytime
- **Basic Auth** — password-protected admin panel
- **Reset Config** — one-click reset to start fresh

## Getting Started

The easiest way to get started:

### 1. Get an LLM Provider Key (free)

1. Register for free at [OpenRouter](https://openrouter.ai/)
2. Create an API key from your [OpenRouter dashboard](https://openrouter.ai/keys)
3. Pick a free model from the [model list sorted by price](https://openrouter.ai/models?order=pricing-low-to-high) (e.g. `google/gemma-3-1b-it:free`, `meta-llama/llama-3.1-8b-instruct:free`)

### 2. Set Up a Telegram Bot (fastest channel)

Hermes Agent interacts entirely through messaging channels — there is no chat UI like ChatGPT. Telegram is the quickest to set up:

1. Open Telegram and message [@BotFather](https://t.me/BotFather)
2. Send `/newbot`, follow the prompts, and copy the **Bot Token**
3. Send a message to your new bot — it will appear as a pairing request in the admin dashboard
4. To find your Telegram user ID, message [@userinfobot](https://t.me/userinfobot)

### 3. Deploy to Railway

1. Click the **Deploy on Railway** button above
2. Set the `ADMIN_PASSWORD` environment variable (or a random one will be generated and printed to deploy logs)
3. Attach a **volume** mounted at `/data` (persists config across redeploys)
4. Open your app URL — log in with username `admin` and your password

### 4. Configure in the Admin Dashboard

1. **LLM Provider** — select OpenRouter from the dropdown, paste your API key, enter the model name
2. **Messaging Channel** — check Telegram, paste the Bot Token from BotFather
3. Click **Save & Start** — the gateway will start and your bot goes live

### 5. Start Chatting

Message your Telegram bot. If you're a new user, a pairing request will appear in the admin dashboard under **Users** — click **Approve**, and you're in.




## Environment Variables

| Variable | Default | Description |
|----------|---------|-------------|
| `PORT` | `8080` | Web server port (set automatically by Railway) |
| `ADMIN_USERNAME` | `admin` | Basic auth username |
| `ADMIN_PASSWORD` | *(auto-generated)* | Basic auth password — if unset, a random password is printed to logs |

All other configuration (LLM provider, model, channels, tools) is managed through the admin dashboard.

## Supported Providers

OpenRouter, DeepSeek, DashScope, GLM / Z.AI, Kimi, MiniMax, HuggingFace

## Supported Channels

Telegram, Discord, Slack, WhatsApp, Email, Mattermost, Matrix

## Supported Tool Integrations

Parallel (search), Firecrawl (scraping), Tavily (search), FAL (image gen), Browserbase, GitHub, OpenAI Voice (Whisper/TTS), Honcho (memory)

## About Hosting

We recommend Railway as infrastructure provider


## Architecture

```
Railway Container
├── Python Admin Server (Starlette + Uvicorn)
│   ├── /            — Admin dashboard (Basic Auth)
│   ├── /health      — Health check (no auth)
│   └── /api/*       — Config, status, logs, gateway, pairing
└── hermes gateway   — Managed as async subprocess
```

 ### Deployment Dependencies

The admin server runs on `$PORT` and manages the Hermes gateway as a child process. Config is stored in `/data/.hermes/.env` and `/data/.hermes/config.yaml`. Gateway stdout/stderr is captured into a ring buffer and streamed to the Logs panel.

## Running Locally

```bash
docker build -t hermes-agent .
docker run --rm -it -p 8080:8080 -e PORT=8080 -e ADMIN_PASSWORD=changeme -v hermes-data:/data hermes-agent
```

Open `http://localhost:8080` and log in with `admin` / `changeme`.

 ## Dependencies for
None

## Common Use Cases
Research Autonomous Agents, Personal Automations

## Credits

- [Hermes Agent](https://github.com/NousResearch/hermes-agent) by [Nous Research](https://nousresearch.com/)
- UI inspired by [OpenClaw](https://github.com/praveen-ks-2001/openclaw-railway) admin template


## 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/impacte-hermes-agent