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 → separates the application that carries out work from the language model that guides it. Nous Research’s terminal-based agent can use different model backends; Hermes 3 and Hermes 4 are separate language models from the same organization. OpenRouter’sintegration guide explains how its gateway supplies model access through one account and how auxiliary models can handle side tasks such as conversation titles or compression. This lets an operator choose the main reasoning modelA model trained to think — generating extended internal reasoning before answering — trading time and tokens for accuracy on hard problems.Full definition → and supporting models separately while keeping the agent application.
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.
reasoning model — A model trained to think — generating extended internal reasoning before answering — trading time and tokens for accuracy on hard problems.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
system prompt — The standing instructions a model receives before any user input — defining its role, rules, tools, and tone for the whole conversation.
