Technical users who want a self-hosted agent that builds its own skills can run it free under MIT, paying only for models.
Kenning's take
What it does
Hermes Agent is a free, open-source autonomous agent from Nous Research that keeps a memory of projects and writes its own reusable skills. It can be reached from the terminal, a desktop app for Mac, Windows and Linux, or messaging apps such as Telegram, Slack and WhatsApp. Users plug in their own model provider or buy credits through Nous Portal.
- Persistent memory and self-written skills
- Works in Telegram, Discord, Slack, WhatsApp, Signal and email
- Scheduled tasks in plain language
- Subagents and sandboxed execution
- Hermes Desktop app for macOS, Windows and Linux
Who it suits. Developers and technical users who want a self-hosted agent that learns over time.
Key facts
- Category
- Developer tools
- Made by
- Nous Research
- Launched
- 2025
- How to get it
- free download (desktop app or terminal install); optional Nous Portal account and cloud hosting
- Works on
- macos, Windows, Linux, cli
- In the UK
- Yes
- Free plan
- yes, free and open source
- API price
- none: pay your chosen model provider or Nous Portal
FAQ
Is Hermes Agent free?
Yes. It is open source under the MIT licence; model use is paid to your provider or through Nous Portal.
What is Hermes Desktop?
The same Hermes Agent as a native app for macOS 12+, Windows 10/11 and Linux.
How do I install Hermes Agent?
Download the desktop app or run the install script from the terminal, then connect a model provider.
Facts from the maker's own pages and the sources listed. Checked 2026-10-11.
Similar tools

Claude Keychain
A free Mac menu bar app that keeps API keys in the macOS Keychain so Claude Code can use them without seeing them.
OpenAI Agent Builder
OpenAI's visual canvas for building multi-agent workflows, being withdrawn on 30 November 2026.
ElevenLabs Agent Workflows
Visual editor in ElevenLabs' agent platform for designing branching conversation flows for voice and chat agents.

AgentOps
Monitoring and debugging platform that records what AI agents do, what they cost and where they fail.