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.
@WSJ @nvidia @M12vc @SamsungNext @robotventures @usv @ycombinator @MenloVentures Join us at NousCon to celebrate and perhaps catch some sneak peeks x.com/NousResearch/s… Or come work for us! nousresearch.com/careers
As reported in the @WSJ, we have raised a Series B to bring Hermes Agent to new frontiers (and, yes, build a mobile app) Thank you to our investors including @nvidia @M12vc @SamsungNext @robotventures @usv @ycombinator @MenloVentures, among others wsj.com/pro/venture-ca… x.com/dillonrolnick/…
x.com/witcheer/statu…
Claude Opus 5.5 leads at 63.31 and $4.99 per task. GPT 6 Astra is second at 56.25 and $11.61. Sonnet 5.5 follows at 53.14 and $2.82. At the other end, DeepSeek V4.1 Flash scores 36.91 at $0.26 and Ling 3.0 Flash scores 21.56 at $0.054.
Every model runs the same harness, with reasoning set high where offered. The index reports the mean score and the mean cost per task across the four suites. Hermes Bench info:
We do this using an index of four benchmarks. One is our new benchmark, Hermes Bench. The others are Terminal-Bench 4.0, Terminal-Bench-Science, and SkillsBench.
Introducing Hermes Index: an average of benchmarks measuring model performance in Hermes Agent. Our goal with Hermes Index is to better inform users choosing between models and to show labs how they perform in Hermes. portal.nousresearch.com/bench
Hey Hermes book me a flight to nyc and find the cheapest hotel available and social engineer the person approving rsvps make no mistakes x.com/nousresearch/s…
Evergreen x.com/sounddobad/sta…
You should be able to use smarter models in your agent. You should be able to use cheaper models in your agent. You should be able to use local models in your agent. You should be able to use a different model for every job. You should be able to switch models in the middle of a conversation. You should be able to choose what data your agent has. You should be able to choose what it remembers and what it forgets. You should be able to choose what computer your agent runs on. You should be able to run it on a machine that never touches the internet. You should be able to run it while your laptop is closed. You should be able to reach it from the apps you already use. You should be able to choose how your agent thinks. You should be able to read the prompt it runs on. You should be able to see every tool it has, and turn off the ones you don't want. You should be able to teach it something once and never explain it again. You should be able to know what it did, and when, and why. You should be able to export your agent. You should be able to read the code. You should be able to change the code. Your agent should be yours.
