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

# Memories

> Extracted facts and context from conversations

## What are Memories?

Memories are discrete pieces of information extracted from user conversations. They complement traits by storing:

* Specific facts that don't fit trait schemas
* Events and experiences mentioned
* Contextual information for future conversations

## Memory Structure

```typescript theme={null}
interface Memory {
  id: string;
  profileId: string;
  content: string;          // The extracted information
  type: 'fact' | 'preference' | 'event' | 'context';
  importance: number;       // 0.0 - 1.0
  decayFactor: number;      // Decreases over time
  sourceMessageIds: string[];
  createdAt: Date;
  lastAccessedAt: Date | null;
}
```

## Memory Types

<CardGroup cols={2}>
  <Card title="Fact" icon="circle-info">
    Concrete information: "Works at Acme Corp as a senior engineer"
  </Card>

  <Card title="Preference" icon="heart">
    Likes and dislikes: "Prefers dark mode IDEs"
  </Card>

  <Card title="Event" icon="calendar">
    Things that happened: "Started a new project last week"
  </Card>

  <Card title="Context" icon="layer-group">
    Situational info: "Currently debugging a production issue"
  </Card>
</CardGroup>

## Importance Scoring

Memories are scored by likely future relevance:

| Score   | Description        | Examples                        |
| ------- | ------------------ | ------------------------------- |
| 0.8+    | Core identity/role | Job title, primary tech stack   |
| 0.6-0.8 | Ongoing projects   | Current goals, active work      |
| 0.4-0.6 | Preferences        | Tool preferences, working style |
| \< 0.4  | Ephemeral context  | Today's specific task           |

## Memory Decay

Over time, memories become less relevant. The `decayFactor` (starting at 1.0) decreases:

* Unused memories decay faster
* Accessed memories are "refreshed"
* Low importance memories decay faster

This ensures recent and frequently-relevant information takes priority.

## Memory Retrieval

When building context for a request, GetProfile retrieves memories based on:

1. **Recency**: More recent memories score higher
2. **Importance**: Higher importance memories are prioritized
3. **Relevance**: (Future) Semantic similarity to the current query
4. **Access patterns**: Frequently accessed memories are boosted

## Example: Memory Extraction

Given this conversation:

```
User: I'm working on migrating our monolith to microservices at work. 
      We're using Kubernetes and having some issues with the service mesh.
      By the way, I'll be on vacation next week.
```

GetProfile extracts:

```json theme={null}
[
  {
    "content": "Working on migrating a monolith to microservices",
    "type": "event",
    "importance": 0.8
  },
  {
    "content": "Uses Kubernetes at work",
    "type": "fact",
    "importance": 0.7
  },
  {
    "content": "Experiencing issues with service mesh",
    "type": "context",
    "importance": 0.6
  },
  {
    "content": "Will be on vacation next week",
    "type": "event",
    "importance": 0.4
  }
]
```

## Deduplication

GetProfile automatically handles duplicate memories:

* Identical content is merged
* Similar memories may be consolidated
* Source messages are aggregated