LLM WORLD
NR

Hermes Agent

Nous Research · · Agent

Nous Research released an open-source, model-agnostic agent that runs as a persistent daemon on the user's own infrastructure, keeps memory across sessions and writes reusable skill files from its own experience.

Why it matters

The self-improving open-source harness: it made the agent's accumulated memory and skills, rather than the model behind it, the thing that got better over time. It became the fastest-growing open-source agent project of 2026.

This is LLM World's historical reading, not a claim by Nous Research. The facts above and the sources below are what it rests on.

Sources

Record status: partly verified · confidence 60/100

The day comes from a third-party timeline that quotes Nous Research's announcement post; the launch is independently corroborated by MarkTechPost coverage dated 26 February 2026, the day after. Nous Research's own site states only 'released in February 2026' and I could not retrieve the dated announcement post itself (x.com blocks automated fetches). This is an agent harness, distinct from the Hermes 1-4 model family of the same name; the models belong in the release dataset, not here.