Loading page
Loading page

AI
Run the Hermes AI agent from Nous Research on your own server, with a web dashboard and an OpenAI-compatible API.
Hermes Agent is an AI agent from Nous Research. It can chat, run tools, and remember what it learned. After a complex task, it can save the steps as a skill and improve that skill over time. It can also search its own past conversations.
In Docker, Hermes runs a gateway process. That gateway serves an OpenAI-compatible API and connects to chat apps. A web dashboard runs next to it in the same container.
Hermes is for people who want a personal or team AI agent that runs all the time, not only on a laptop. It suits developers who want to reach the agent from Telegram, Slack or their own apps. It also suits researchers, since it can generate training trajectories.
A hosted agent ties you to one vendor's models. With Hermes, you pick the model and can switch later without code changes. Your memory, skills and chat history stay on your own service.
The trade-off is that you manage the keys and costs of the model provider. You also look after updates and backups of the agent's data. The dashboard login in this template uses basic auth, which the Hermes docs describe as fit for trusted networks, so treat the URL with care.
Containers: nousresearch/hermes-agent:v2026.6.19
Step 1
Choose the Starter plan. It costs $20 a month and runs up to 3 apps.
Step 2
Open App templates in the dashboard, choose Hermes, and click Deploy. We set up the containers, secrets and domain.
Step 3
Wait a few minutes for the first deploy, then open your new URL and finish the Hermes setup screen.