Hermes AI Agent

Hermes is an autonomous AI agent that runs on your machine or server and
becomes more capable over time through persistent memory and auto-generated
skills.

It connects to 20+ messaging platforms (Telegram, Discord, Slack, WhatsApp,
Teams, and more) and executes tasks using 60+ built-in tools: web browsing,
browser automation, code execution, file operations, scheduled jobs, and more.

Compatible with any OpenAI-compatible LLM — locally via Lemonade, Ollama,
or a Canonical inference snap, or via cloud APIs such as OpenAI and Anthropic.

LOCAL AI

Run 'hermes-agent.inference-snap' to detect a Canonical inference snap
(gemma4, gemma3, deepseek-r1, and others) and configure it as Hermes's
default model in one step — fully offline, no API key required.

SETUP

Run the setup wizard on first launch:

hermes-agent setup

The background gateway service starts automatically the first time you run
any hermes-agent command and is managed as a standard systemd user unit:

systemctl --user status hermes-agent
systemctl --user stop hermes-agent

SECURITY NOTE

This tool is capable of executing code, accessing files, and interacting
with external services on your behalf. Due to the nature of autonomous
AI agents, we recommend installing and running this snap inside an LXD
container as best practice. A container provides an extra layer of
confinement, limiting the agent's reach to the container environment
and reducing exposure to your host system and personal data.

lxc launch ubuntu:24.04 my-agent
lxc exec my-agent -- snap install --classic hermes-agent