Open Source • MIT LicenseOpen Source · MIT License
Nous Research
Nous Research is a pioneer in open AI training and research. We created Hermes Agent, the most widely used open source agent harness in the world.
We are on a mission to create and proliferate open access to intelligence.
Leading the American Open Source Movement
We train models, build agents, and develop infrastructure to accelerate adoption of open intelligence globally.
Advancing Human Rights and Freedoms
We believe that powerful AI should be in the hands of the many rather than the privileged few. Our aim is to create and democratize access to the world's best intelligence.
Understanding the Intelligence Frontier
Our primary research focus areas include agents, model architecture, data synthesis, fine-tuning, and reasoning, all aimed at advancing our understanding of models and how they can benefit humanity.
Elevate your soul.md
Hermes Agent
The self-improving AI agent built by Nous Research. The only agent with a built-in learning loop — creates skills from experience,The self-improving AI agent built by Nous Research. The only agent with a built-in learning loop: creates skills from experience,
improves them during use, nudges itself to persist knowledge, and builds a deepening model of who you are across sessions.improves them during use, nudges itself to persist knowledge, and builds a deepening model of who you are across sessions.
Using an agent that can change its models or code at any time without telling you is like building on quicksand
hermes-agent.nousresearch.com/marketplace/he…
Hermes Agent can now review your codebase for security bugs with the new official Security plugin by @mark_s. Hermes first maps what an attacker could reach and which inputs it trusts. It splits the code across parallel subagents, checks every candidate finding against the code, and traces whether an attacker can actually exploit it. Turn on test confirmation and Hermes writes a small reproduction for each finding and runs it in a temporary copy of the repo. Each report records the evidence and the findings Hermes ruled out, and exports to SARIF for your existing tools. Run it from chat, the CLI, or the Security page in Hermes Desktop.
Eval: huggingface.co/datasets/NousR… Weights: huggingface.co/NousResearch/A… Training data: huggingface.co/datasets/NousR…
nousresearch.com/arete
Introducing Arete-27B: Qwen3.8-27B, post-trained to reinforce Western values. Chinese open models are currently the strongest available, but they ship with state-aligned behavior in the weights. We built an 803-prompt eval across seven value categories, including freedom of expression, democracy, and privacy, and measured how often a model adopts China’s party line. After fine-tuning on roughly 53 million tokens, Arete-27B's propaganda rate fell from 22% to 1%, in line with the Western models we tested. Its Hermes Bench score shows no significant performance tradeoffs. The values in an open model are one fine-tune away. Our eval, weights, and training data are available now along with the full blog post: https://t.co/iAOANQTVZ6
Get more out of your Hermes Bots with free and discounted models exclusive to portal.nousresearch.com
LongCat-2.5, the new multimodal model from @Meituan_LongCat, is free in Nous Portal for one week. Try it free today at portal.nousresearch.com x.com/Meituan_LongCa…
That's hilarious but you should probably try Hermes which doesn't do that x.com/liamzebedee/st…
Full release notes: github.com/NousResearch/h…
