Hermes Agent #hermes

Hermes Agent, the open-source agent runtime from Nous Research, ships four distinct mechanisms for running more than one agent — each at a different weight class. Knowing which primitive fits which...

Hermes Kanban is a feature of Hermes Agent — shipped in v0.13.0 — that gives the runtime a durable multi-agent board where parallel workers claim tasks, send heartbeats, and recover from crashes...

Hermes Agent is an open-source autonomous AI agent framework from Nous Research, released February 25, 2026 and built around a closed learning loop — it creates skills from experience, improves them...

Skills Hub is the discovery and installation layer of Hermes Agent — a unified interface for searching, inspecting, and installing modular, community-contributed skills, all security-scanned and...

The Hermes Glossary is a collection of terms used in Hermes Agent, Nous Research's open-source self-improving autonomous agent — spanning its runtime architecture, learning loop, skills system,...

Hermes Dashboard is a feature of Hermes Agent that exposes a local browser-based interface for managing settings, sessions, skills, and the gateway — with a plugin system for custom tabs and live...

A sandbox backend in Hermes Agent is the execution environment for terminal commands and code — local process, Docker container, remote SSH host, or a third-party managed runtime — chosen per agent...

Hermes Gateway is a feature of Hermes Agent that runs every messaging integration as a single process — hermes gateway — so one agent stays continuously addressable across more than 20 platforms. The...

A subagent in Hermes Agent is an isolated agent spawn with its own conversation, terminal, and tools, dispatched for delegation or parallel work. A subagent is launched by a parent agent — sometimes...

A self-improving skill is a skill document the agent patches in place during use when reality contradicts or extends what's written — refinement woven into operation rather than reserved for a...

The closed learning loop is Hermes Agent's core architectural pattern — solve, document, retrieve, improve, repeat — executed across sessions without human prompting. Coined by Nous Research, the...