Check out the blog for a walkthrough on setting up the Hermes Agent powered by Trinity-Large-Thinking across Linux, macOS, and Windows.
https://t.co/um9H1Mga2j
Nous Research and Arcee AI announced that Hermes AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition →, Nous's existing agent tool, now runs on Arcee's open weightsA model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.Full definition → Trinity-Large-reasoning modelA model trained to think — generating extended internal reasoning before answering — trading time and tokens for accuracy on hard problems.Full definition →, according to the joint post, which points to a blog walkthrough for setting it up across Linux, macOS and Windows. The announcement itself is brief and the setup steps in that linked blog were not independently reviewed here; the supported fact is that the pairing exists and is documented as cross-platform.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
reasoning model — A model trained to think — generating extended internal reasoning before answering — trading time and tokens for accuracy on hard problems.
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
