How-To Series · 8: Provider Plumbing

Run Hermes with Ollama

Zero API costs. Full functionality. Run Hermes entirely on your own machine with Ollama and open-weight models like Gemma 4.

After this videoYou can run Hermes entirely on your own machine with zero API costs.

This tutorial shows you how to set up Hermes Agent running entirely on your own hardware using Ollama as the model backend. No API keys, no subscriptions, no data leaving your machine. Once configured, Hermes works exactly like it does with OpenRouter or Anthropic — terminal commands, file editing, web browsing, delegation — but the model runs locally.

About these resources. This guide walks you through setting up Hermes with Ollama. The Sources block names every Hermes docs page that backs a claim in the script. For more information on running Hermes with different providers, see the related guides.

Sources · What this video distills

3 docs pages · every command below traces to one of them
Primary · local Ollama setup guide
Run Hermes Locally with Ollama
Read ↗
Ollama installation and configuration
Ollama Documentation
Read ↗
Hermes configuration with custom endpoints
Hermes Configuration Guide
Read ↗

Commands shown · Copy and paste

each shows the source doc it came from
Install Ollamafrom source ↗
curl -fsSL https://ollama.com/install.sh | sh
Verify Ollama installationfrom source ↗
ollama --version curl http://localhost:11434/api/tags
Pull Gemma 4 31B modelfrom source ↗
ollama pull gemma4:31b
Verify model worksfrom source ↗
curl http://localhost:11434/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{ "model": "gemma4:31b", "messages": [{"role": "user", "content": "Say hello"}], "max_tokens": 50 }'
Run Hermes setupfrom source ↗
hermes setup
Start Hermesfrom source ↗
hermes

Going deeper · Related Hermes docs

further reading · not sources of facts shown above

Next in the series · Episodes that build on this