Skip to main content

What is Hermes?

Hermes is an open-source, self-hosted autonomous Agent from Nous Research, officially positioned as “the Agent that grows with you.” Its most distinctive feature is the built-in learning loop: it automatically creates skills from the experience of completing tasks, improves itself through use, and recalls past sessions using full-text search plus LLM summaries, allowing it to remember projects and user preferences across sessions. It provides a full terminal TUI and also includes a built-in messaging gateway, so the same Agent can be connected to Telegram, Discord, Slack, WhatsApp, Signal, and email, all sharing the same memory. Hermes comes with a built-in cron scheduler that lets you set up unattended tasks such as daily reports and nightly backups in natural language, and it also supports dispatching isolated sub-Agents to work in parallel. The execution environment can be switched between local, Docker, SSH, Modal, Daytona, and Vercel Sandbox, so it can run on a cheap VPS or in the cloud. On the model side, it is not locked to any vendor, supporting Nous Portal, OpenRouter, OpenAI, and custom endpoints. Website: https://hermes-agent.nousresearch.com/ GitHub: https://github.com/NousResearch/hermes-agent

How to connect Interface AI to Hermes?

Get an API Key

  1. Log in to the official website jiekou.ai to register.
  2. Go to the admin console, click “My” in the upper right corner, and select “API Key Management” from the dropdown list.
  3. Click “Create” and enter a key name. It is recommended to use an easily recognizable name so you can later distinguish keys for different purposes in the console.
  4. Click to copy and record the generated Key. It cannot be viewed again in the console, so please store it safely for future use.

Connect Interface AI to Hermes

  1. After installing Hermes, open a terminal and run:
  1. In the options that appear, select “Custom Endpoint”
  2. Enter the Interface AI URL
  1. Enter the Key you just copied
  2. Select the API protocol supported by the model; after pressing Enter, the Interface AI model list will appear
  3. Select the model you want to call by entering its number
  4. Enter the context length supported by the model, and name the provider
  5. After selecting the reasoning depth, you can use the model services provided by Interface AI in Hermes
Last modified on November 5, 2026