Skip to content
BENIBIX Learn

Hermes Learning Loop

AI🪽 Hermes AgentHermes Memory

Also known as Hermes background review, Hermes self-improvement

The way Hermes looks back after a turn and saves what it learned.

Think of it like

It is like a diary you write each night.

Example

Leo corrects Hermes twice on how he wants commit messages. The review saves the rule, and the next day it writes them his way.

Why it matters

An agent that learns from corrections needs fewer of them as time goes on.

Definition

The learning loop is how Hermes Agent gets better from use. After a turn, a background review looks back at the chat in a separate copy of the agent. It saves small facts to memory and longer ways of working as skills. A short Memory updated line tells you when it saved something. The next session starts with what it saved.
From a session to memory and skills, and back.

Common mistake

Expecting the new fact to work in the same session. It loads at the start of the next one.

Key takeaways

  1. 1
    Runs after a turn. In the background.
  2. 2
    Facts and procedures. Memory and skills.
  3. 3
    Shows in the next session. Not this one.