FAQ
Frequently asked questions about Hermes Agent.
What is Hermes Agent?
Hermes Agent is an open-source autonomous AI agent built by Nous Research. It runs on your own server, remembers what it learns, creates its own skills, and integrates with Telegram, Discord, Slack, WhatsApp, Signal, Email, and CLI — all from a single unified process.
How do I install Hermes Agent?
Installation is a single command: curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash. The installer auto-detects your OS and handles all dependencies. Detailed step-by-step instructions are available on our Install page.
Which platforms and operating systems are supported?
Hermes Agent runs on Linux, macOS, WSL2, and Windows. It supports 6 terminal backends: Local, Docker, SSH, Daytona, Singularity, and Modal. You can run it on anything from a $5 VPS to a GPU cluster.
Is Hermes Agent really free and open source?
Yes. Hermes Agent is 100% free and open source under the MIT license. It is fully self-hosted with zero telemetry — your data never leaves your machine. There are no paid tiers, no enterprise-only features, and no vendor lock-in.
How does the memory system work?
Hermes Agent uses FTS5 (full-text search) for cross-session recall combined with LLM-powered summarization. It builds a dialectic user model (Honcho) that grows more accurate the longer you use it. Your agent remembers projects, preferences, and conversation context across sessions.
How can I contribute to the Hermes Agent ecosystem?
There are many ways to contribute: submit pull requests on GitHub, create and share skills on agentskills.io, write documentation, report bugs, or join the community discussions. The project welcomes contributions of all kinds — from code to documentation to skill creation.
Still have questions?
Check out the official documentation or join the community discussions.