Nous Research is an AI research group that trains and releases open models, whose models include the Hermes series, and which builds the open-source Hermes Agent.
In plain words
Its Hermes language models are designed to follow the user closely, giving users strong control over the model's behaviour. Later Hermes versions added better function calling, structured output, reasoning and long conversations. Nous also makes Hermes Agent, an MIT-licensed agent harness that it says learns new skills from experience.
A quick example
Imagine a developer who wants an open model that follows a strict JSON format for tool calls. They download a Hermes model from Hugging Face and use the prompt format its model card describes for function calling.
Where you'll meet it
- Open fine-tuned models on Hugging Face.
- Open-source AI agents.
Related
Sources
- DocsNous Research, Nous Research · read 29 Sept 2026
- DocsHermes 3 - Llama-3.1 8B, Nous Research (Hugging Face) · read 29 Sept 2026
Checked by WhatIsAI against the sources above · 29 Sept 2026. Spotted an error? Report it.