> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/zeroclaw-labs/zeroclaw/llms.txt
> Use this file to discover all available pages before exploring further.

# Memory Tools

> Store and retrieve information across conversations

Memory tools enable agents to persist and recall information across conversations.

## Available Tools

<CardGroup cols={2}>
  <Card title="memory_store" icon="floppy-disk">
    Store new information
  </Card>

  <Card title="memory_recall" icon="brain">
    Search and retrieve memories
  </Card>

  <Card title="memory_list" icon="list">
    List all stored memories
  </Card>

  <Card title="memory_forget" icon="trash">
    Delete specific memories
  </Card>
</CardGroup>

## memory\_store

Store information for later retrieval.

### Parameters

<ParamField path="content" type="string" required>
  Information to remember
</ParamField>

<ParamField path="category" type="string">
  Category for organization: `fact`, `preference`, `task`, `context`
</ParamField>

<ParamField path="tags" type="array">
  Optional tags for filtering
</ParamField>

### Example

```json theme={null}
{
  "content": "User prefers TypeScript for new projects",
  "category": "preference",
  "tags": ["programming", "languages"]
}
```

## memory\_recall

Search memories using semantic similarity or keywords.

### Parameters

<ParamField path="query" type="string" required>
  Search query
</ParamField>

<ParamField path="category" type="string">
  Filter by category
</ParamField>

<ParamField path="limit" type="integer">
  Maximum results (default: 10)
</ParamField>

### Example

```json theme={null}
{
  "query": "programming language preferences",
  "category": "preference",
  "limit": 5
}
```

### Response

Returns array of matching memories with relevance scores:

```json theme={null}
[
  {
    "content": "User prefers TypeScript for new projects",
    "category": "preference",
    "tags": ["programming", "languages"],
    "timestamp": "2026-03-03T12:00:00Z",
    "relevance": 0.95
  }
]
```

## memory\_list

List all memories, optionally filtered by category.

### Parameters

<ParamField path="category" type="string">
  Filter by category
</ParamField>

### Example

```json theme={null}
{
  "category": "fact"
}
```

## memory\_forget

Delete memories by ID or pattern.

### Parameters

<ParamField path="id" type="string">
  Memory ID to delete
</ParamField>

<ParamField path="pattern" type="string">
  Delete all memories matching pattern
</ParamField>

### Example

```json theme={null}
{
  "pattern": "old project"
}
```

## Memory Categories

<Accordion title="fact">
  Objective information and data

  Examples:

  * "API endpoint is [https://api.example.com](https://api.example.com)"
  * "Project uses Python 3.11"
</Accordion>

<Accordion title="preference">
  User preferences and choices

  Examples:

  * "User prefers concise responses"
  * "Avoid emojis in documentation"
</Accordion>

<Accordion title="task">
  Ongoing tasks and TODOs

  Examples:

  * "Need to update README with new features"
  * "Pending code review for PR #123"
</Accordion>

<Accordion title="context">
  Conversation context and state

  Examples:

  * "Currently debugging authentication issue"
  * "Working on feature branch: auth-v2"
</Accordion>

## Backend Support

<Tabs>
  <Tab title="Markdown (Default)">
    Stores memories as markdown files in `~/.zeroclaw/memory/`

    **Features:**

    * Human-readable format
    * Git-friendly
    * No dependencies
    * File-based search
  </Tab>

  <Tab title="SQLite">
    Stores memories in SQLite database with vector embeddings

    **Features:**

    * Semantic search with cosine similarity
    * Fast full-text search
    * Structured queries
    * Requires embedding model
  </Tab>

  <Tab title="PostgreSQL">
    Enterprise-grade memory with pgvector extension

    **Features:**

    * Distributed memory across agents
    * Advanced vector search
    * Transaction support
    * Requires PostgreSQL with pgvector
  </Tab>
</Tabs>

## Configuration

```toml theme={null}
[memory]
backend = "sqlite"  # or "markdown", "postgres"
embedding_model = "text-embedding-3-small"
max_memories = 10000

[memory.sqlite]
path = "~/.zeroclaw/memory.db"

[memory.postgres]
url = "postgresql://user:pass@localhost/zeroclaw"
```

## Source Code

* [`src/tools/memory_store.rs`](https://github.com/zeroclaw-labs/zeroclaw/blob/main/src/tools/memory_store.rs)
* [`src/tools/memory_recall.rs`](https://github.com/zeroclaw-labs/zeroclaw/blob/main/src/tools/memory_recall.rs)
* [`src/memory/`](https://github.com/zeroclaw-labs/zeroclaw/tree/main/src/memory)

## Related

* [Memory Trait](/api/memory-trait)
* [Memory Concepts](/concepts/memory)
* [Custom Memory Guide](/guides/custom-memory)