> ## Documentation Index
> Fetch the complete documentation index at: https://docs.t0ken.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Memories

> Understanding how memories work in OpenMemoryX

Memories are the core data unit in OpenMemoryX. They represent pieces of information that your AI application wants to remember about users or contexts.

## What is a Memory?

A memory consists of:

* **Content** - The actual text content to remember
* **Project ID** - Which project this memory belongs to
* **Metadata** - Additional structured data (optional)
* **Cognitive Sector** - AI-classified category (auto-assigned)
* **Importance Score** - AI-calculated relevance (0-1)

## Memory Structure

```json theme={null}
{
  "id": "mem_123abc",
  "content": "User prefers dark mode in all applications",
  "project_id": "default",
  "cognitive_sector": "semantic",
  "importance_score": 0.85,
  "metadata": {
    "source": "user_settings",
    "category": "preferences"
  },
  "created_at": "2026-02-13T10:00:00Z"
}
```

## Cognitive Sectors

Every memory is automatically classified into one of five cognitive sectors:

<CardGroup cols={2}>
  <Card title="Episodic" icon="calendar" color="#f59e0b">
    Specific events and experiences

    *Example: "User visited Paris in 2024"*
  </Card>

  <Card title="Semantic" icon="book" color="#3b82f6">
    Facts and general knowledge

    *Example: "User prefers dark mode"*
  </Card>

  <Card title="Procedural" icon="code" color="#10b981">
    Skills and how-to knowledge

    *Example: "User knows Python"*
  </Card>

  <Card title="Emotional" icon="heart" color="#ec4899">
    Feelings and preferences

    *Example: "User enjoys sci-fi movies"*
  </Card>

  <Card title="Reflective" icon="lightbulb" color="#8b5cf6">
    Insights and summaries

    *Example: "User values privacy"*
  </Card>
</CardGroup>

## Async Processing

Memories are processed asynchronously:

1. **Submit** - Send memory content via API
2. **Queue** - Memory enters processing queue
3. **AI Classification** - AI determines sector and importance
4. **Vector Embedding** - Create searchable vector representation
5. **Storage** - Save to database and knowledge graph

This allows your application to continue without waiting for AI processing.

## Best Practices

* **Keep content concise** - 1-2 sentences per memory works best
* **Use consistent project IDs** - Organize by application or user
* **Add relevant metadata** - Helps with filtering and context
* **Don't store PII** - Avoid storing sensitive personal information