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

# EngramDB Documentation

> Documentation for EngramDB, a specialized database for agent memory management

# Welcome to EngramDB Documentation

EngramDB is a specialized database system designed specifically for agent memory management. It provides efficient storage, retrieval, and querying of agent memories using a unified memory representation model.

## What is EngramDB?

EngramDB is a database system that combines vector, graph, and temporal properties in a single primitive called a MemoryNode. This unified approach allows for rich, multi-dimensional representation of agent memories, enabling complex queries that can leverage semantic similarity, relational connections, and temporal evolution.

## Core Features

<CardGroup cols={2}>
  <Card title="Unified Memory Representation" icon="database">
    Combines graph, vector, and temporal properties in a single primitive
  </Card>

  <Card title="Vector Similarity Search" icon="magnifying-glass">
    Find memories with similar semantic content
  </Card>

  <Card title="Flexible Storage Options" icon="server">
    In-memory database for testing and development, file-based for persistence
  </Card>

  <Card title="Query API" icon="code">
    Rich querying with vector similarity, attribute filters, and temporal constraints
  </Card>

  <Card title="Memory Evolution" icon="clock">
    Track changes to memories over time with temporal layers
  </Card>

  <Card title="Python Bindings" icon="python">
    First-class Python API for integration with ML and AI applications
  </Card>

  <Card title="Web Interface" icon="browser">
    Browser-based UI for visualization and interaction with the database
  </Card>
</CardGroup>

## Getting Started

<CardGroup cols={2}>
  <Card title="Installation" icon="rocket" href="/getting-started">
    Learn how to install and set up EngramDB
  </Card>

  <Card title="Core Concepts" icon="book" href="/core-concepts">
    Understand the fundamental building blocks of EngramDB
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/memory-node">
    Explore the detailed API documentation
  </Card>

  <Card title="Examples" icon="flask" href="/examples/rust-examples">
    See EngramDB in action with code examples
  </Card>
</CardGroup>

## Why EngramDB?

Traditional databases are not optimized for the unique requirements of agent memory systems:

* **Vector databases** excel at similarity search but lack graph capabilities
* **Graph databases** handle relationships well but aren't optimized for vector similarity
* **Document databases** provide flexible schemas but lack specialized memory features
* **Time-series databases** track changes over time but aren't designed for semantic search

## Advanced Topics

<CardGroup cols={2}>
  <Card title="Temporal Layers" icon="clock" href="/advanced-topics/temporal-layers">
    Learn how to track memory evolution over time
  </Card>

  <Card title="Connections" icon="link" href="/advanced-topics/connections">
    Create and manage relationships between memories
  </Card>

  <Card title="Storage Engines" icon="server" href="/advanced-topics/storage-engines">
    Understand the different storage backends
  </Card>

  <Card title="Embeddings" icon="network-wired" href="/advanced-topics/embeddings">
    Learn about vector and multi-vector embeddings
  </Card>

  <Card title="Background Processing" icon="gears" href="/advanced-topics/background-processing">
    Discover sleep-time compute capabilities
  </Card>
</CardGroup>

We welcome contributions to EngramDB! Check out our [contributing guide](/contributing) to get started.