Deploy and Host Hermes Agent on Railway

Hermes Agent is Nous Research's self-improving AI agent: it builds skills from experience, refines them as it works, searches its own past conversations, and keeps a persistent model of you across sessions. This template deploys the official Hermes image with its web dashboard exposed and its memory on a persistent volume.

About Hosting Hermes Agent

The whole premise of Hermes is continuity — it is supposed to remember what it learned and get better at your work over time. All of that lives under HERMES_HOME at /opt/data: learned skills, session history, identity, and configuration. Deploy it without a volume and you get an agent with amnesia that rebuilds nothing and remembers no one. This template mounts a volume there so the agent that exists next week is the one you trained this week.

The dashboard is the part that needs care. Hermes ships an auth gate that engages automatically on any non-loopback bind, and it fails closed: without a registered auth provider the dashboard refuses to start at all. As of the June 2026 hardening, HERMES_DASHBOARD_INSECURE no longer disables that gate — it is accepted and ignored — because unauthenticated public dashboards were the entry point for a real credential-persistence campaign. This template registers the bundled password provider with an admin user and a generated password, so the dashboard comes up properly gated. Reaching it presents a sign-in page rather than the agent.

Hermes runs under s6 supervision inside the container, which is what keeps the dashboard service alive independently of the agent CLI.

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.

• Memory that persists — skills, sessions, and identity on a volume, which is the entire point of a self-improving agent.
• Gated dashboard — a real password provider is registered, not an auth bypass.
• Official image — Nous Research's own published build, not a third-party fork of it.
• Always reachable — the agent runs on infrastructure, so you can talk to it when your laptop is closed.
• Any model you like — Nous Portal, OpenRouter, OpenAI, or your own endpoint; no lock-in.

Common Use Cases

• A personal agent that compounds — it learns your workflows and keeps the skills it builds.
• Long-running background work — hand off research or multi-step tasks and check the dashboard later.
• Always-on assistant — reachable from anywhere rather than tied to a local process.

Dependencies for Hermes Agent Hosting

• A volume mounted at /opt/data for agent memory and configuration (included in this template).
• An API key for a model provider (Nous Portal, OpenRouter, OpenAI, or a compatible endpoint), configured after deploy.

Deployment Dependencies

• Hermes Agent — upstream project by Nous Research
• nousresearch/hermes-agent — the official image this template deploys

Implementation Details

One service with persistent memory:

Open your public domain and sign in with username admin and the generated HERMES_DASHBOARD_BASIC_AUTH_PASSWORD from the service variables. Change that password to your own once you are in.

Then configure a model provider from the dashboard before giving the agent real work — Hermes needs a provider key to do anything beyond starting up.

Do not delete the volume. It holds every skill the agent has learned and every session it remembers; there is nothing to restore it from.