Everything you need to set up, connect and run your Hermes Agent, written in plain words.
A freshly built server runs the agent, and the agent waits for an AI model. Until a model answers one test request, every chat stays quiet. This guide shows where that one step lives for the crab (OpenClaw) and for Hermes, where an API key comes from, and what to check when the silence stays.
OpenClaw and Hermes Agent both need an AI model to think with. This guide lists twelve ways to connect one, by API key, by subscription sign-in or on your own machine with Ollama, with what each costs in a month.
Three checks in order when Hermes Agent stops working after an update: the version, the built-in doctor and the gateway, plus how to read the common warnings and get back to a working version.
Install Hermes Agent, connect a model, verify your first chat and add Telegram when you want to message it away from your computer.
The docs have no system requirements page (issue 73754). From measured reports and our production fleet: 1 GB is a demo, 2 GB is the always-on floor, 4 GB is comfortable, local models start at 8 GB, 2 cores suffice, and 20 GB of disk keeps it boring.
How to run Hermes Desktop as a thin client against a Hermes on an always-on server, using the remote mode documented in issue 38602: HERMES_DESKTOP_REMOTE_URL and HERMES_DESKTOP_REMOTE_TOKEN set before first launch, plus the three recorded traps.
Looking for the other agent? OpenClaw guides
