> ## Documentation Index
> Fetch the complete documentation index at: https://docs.evermind.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Memory Types

> Understand the four memory types in EverOS and how each one is used in retrieval.

EverOS categorizes memories into four types so you can retrieve the **right** information for the **right** task. Each type captures a different signal: identity, narrative context, atomic facts, or future intent.

## Overview

<CardGroup cols={2}>
  <Card title="Profile" icon="user">
    **The "Who"**
    Long-term identity and stable preferences.
  </Card>

  <Card title="Episodic" icon="book-open">
    **The "Story"**
    Narrative summaries of past sessions and context.
  </Card>

  <Card title="EventLog" icon="list-check">
    **The "Facts"**
    Atomic facts and actions extracted from conversations.
  </Card>

  <Card title="Foresight" icon="crystal-ball">
    **The "Future"**
    Future needs, plans, and time-based intent.
  </Card>
</CardGroup>

## Profile Memory (The "Who")

Profile memory stores stable attributes that define a user's identity.

* **Definition**: Name, role, background, and long-term preferences.
* **Best for**: Personalizing tone, style, and responses based on who the user is.
* **Example**: "The user is a Senior Python Developer who prefers concise code snippets."

<Warning>
  Profile memory currently supports **Fetch by user\_id/key only**. Semantic search is not supported yet.
</Warning>

## Episodic Memory (The "Story")

Episodic memory captures the narrative flow of a session rather than raw logs.

* **Definition**: Narrative summaries of past sessions.
* **Best for**: High-level context, rationale, and project progression.
* **Example**: "What did we discuss about the marketing plan yesterday?"

## EventLog Memory (The "Facts")

EventLog memory stores discrete facts without narrative context.

* **Definition**: Atomic facts (actions taken, files uploaded, numbers agreed).
* **Best for**: Precise factual queries where details matter.
* **Example**: "What was the exact budget figure mentioned for Q3?"

## Foresight Memory (The "Future")

Memory is not only about the past. [Foresight](/cloud/foresight-memory) stores future-oriented signals.

* **Definition**: Predictions about future events, needs, or tasks.
* **Best for**: Planning, proactive assistance, and time-sensitive queries.
* **Example**: "Do I have any upcoming deadlines?"

***

## How the system chooses a type

In most cases, **Episodic** is the default for broad context, and the system selects other types based on query intent.

Use this mental model:

* **"Who am I?"** → **Profile**
* **"What happened last week?"** → **Episodic**
* **"What was the file name?"** → **EventLog**
* **"What's next?"** → **Foresight**

The orchestration layer can route to the best type or search multiple types in parallel to build a complete answer.