# Memory

What each agent learns from conversations and the team's corrections.

<https://agentes.chat/docs/memory> · [agentes.chat docs](https://agentes.chat/docs.md)

## How agents learn

Agents learn from conversations and from the team's corrections. What an agent knows enters its context when relevant. On its **Memory** tab, edit, pin or archive what's wrong or stale.

## Memory grants no permission

Nothing in memory lets an agent do more. What it can do stays in its **Tools and access**, and sensitive actions always ask for approval.

## Proposed changes

When a lesson repeats, the agent may propose changing its own instructions or the workspace's context. Nothing changes until someone accepts, and the text can be adjusted first. The previous version stays in the history. A refused proposal is kept as a lesson, so it isn't proposed again.