# Memory

> What an agent remembers between conversations, and how that memory is scoped.

Source: https://docs.runbear.io/agents/memory

Last updated: 2026-08-26

Your agent automatically builds long-term memory from conversations, so it can recall relevant context in future interactions. Memory is enabled by default and requires no configuration.

## How it works

As the agent converses with users, it extracts factual information — such as which team owns a service, where a document lives, or what tool is used for a specific workflow. These facts are stored and recalled in future conversations to provide more contextual responses.

The agent extracts **"resource → location" style facts only** — concrete, referenceable information. It does not store tasks, opinions, or personal data.

## Memory types

Memory is scoped based on where the conversation happens:

### Shared memory (public channels)

When the agent is mentioned in a **public channel**, extracted facts are stored as shared memory. This memory is available to the agent across all conversations — any user interacting with the agent benefits from it.

For example, if someone mentions in a public channel that "the design system lives in the `ui-kit` repo," the agent remembers this for everyone.

### Personal memory (private DMs)

When a user sends a **direct message** to the agent, extracted facts are stored as personal memory tied to that specific user. Only conversations with that same user can access this memory.

For example, if a user tells the agent "I work on the billing team," only that user's future conversations will include this context.

## Settings

Memory is controlled by a single toggle: **Enable long-term memory**, found in your agent's settings. It is on by default.

When disabled, the agent stops extracting and recalling memories but does not delete existing ones.