FAQ
What is Hermes Agent?
Hermes Agent is an open-source autonomous AI agent by Nous Research. Unlike coding copilots or chatbot wrappers, Hermes has a built-in learning loop: it creates skills from experience, improves them during use, and builds a deepening model of who you are.
How is it different from other agents?
Three differences matter most: (1) a closed learning loop that persists knowledge across sessions; (2) a unified messaging gateway across 15+ platforms; (3) six runtime backends so you can pick the right trade-off between isolation, cost, and latency.
Which LLMs are supported?
Any OpenAI-compatible endpoint, plus native adapters for Anthropic, Google, OpenRouter, Nous Portal, AWS Bedrock, DeepSeek, NVIDIA NIM, and others. You're never locked into one provider.
Can I self-host?
Yes — Hermes runs on a $5 VPS, on your laptop, or on serverless infra like Modal and Daytona that costs near zero when idle.
Is it free?
Hermes Agent is MIT-licensed and completely free. You pay only for the LLM API calls you make through your own keys.
Where can I get help?
- GitHub Discussions for questions and ideas.
- Nous Research Discord for realtime chat.
- Official English docs.