Deploy Hermes Agent

Self-hosted Hermes Agent by Nous Research: AI agent with web dashboard

Deploy Hermes Agent

Just deployed

/opt/data

Deploy and Host Hermes Agent on Railway

Hermes Agent is an open-source, self-improving AI agent by Nous Research (MIT license). It remembers across sessions, writes and refines its own skills, runs scheduled jobs, and talks to you through a web dashboard or chat apps such as Telegram, Discord and Slack. It works with OpenRouter, Anthropic, OpenAI, Nous Portal and other model providers.

About Hosting Hermes Agent

This template runs the official nousresearch/hermes-agent image (v0.23.1, pinned by digest) as one service, built from a public GitHub repo. The image's own supervisor runs the Hermes gateway (messaging platforms and the cron scheduler) next to the web dashboard, and restarts either one if it crashes. The dashboard is the public URL. It needs a login: the username is admin and the password is generated at deploy, so there's no default password. All state (config, API keys, sessions, memory, skills, logs) is kept on a volume at /opt/data. After deploying, sign in and add a model provider key on the API Keys page.

Common Use Cases

  • A personal AI assistant that remembers you and is reachable from Telegram, Discord, Slack or the browser
  • Scheduled agent jobs: daily briefings, monitoring, research digests and reminders
  • An always-on coding and research agent with web, browser and MCP tools

Dependencies for Hermes Agent Hosting

  • An API key for at least one model provider (OpenRouter, Anthropic, OpenAI, Nous Portal or another supported provider), added in the dashboard after deploying
  • A Railway volume for /opt/data (included in the template)

Deployment Dependencies

Implementation Details

  • Login: read the generated password in the service's Variables tab (HERMES_DASHBOARD_BASIC_AUTH_PASSWORD). Hermes refuses to serve its dashboard on a public address without a login. Upstream recommends Nous Portal OAuth (HERMES_DASHBOARD_OAUTH_CLIENT_ID) or your own OIDC provider for internet-facing dashboards. The public URL is set from your Railway domain automatically.
  • Chat platforms: connect Telegram, Discord, Slack and others on the dashboard's Channels page. They run inside the same service.
  • OpenAI-compatible API (optional): set API_SERVER_ENABLED=true, API_SERVER_HOST=0.0.0.0 and an API_SERVER_KEY to reach it on port 8642 from other services over Railway's private network.
  • Updates: new Hermes releases arrive as an "update available" notice on your project. Your /opt/data volume is kept.

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.


Template Content

More templates in this category

View Template
Chat Chat
Chat Chat, your own unified chat and search to AI platform.

okisdev
117
View Template
Weaviate
Vector database with hybrid search and an API key-protected API

GitHub Locker
1
View Template
Möbius Personal AI OS
Self-hosted AI agent that builds and runs apps for you, with memory.

bento
1