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

# Introduction

> Persistent memory for your OpenClaw agents

<img className="block dark:hidden" src="https://mintcdn.com/orcamemory/5mVXrJpUJbFiHEL2/images/hero-light.png?fit=max&auto=format&n=5mVXrJpUJbFiHEL2&q=85&s=74b61d5396cbcdfb86528486c871f786" alt="Orca Memory" width="3840" height="2160" data-path="images/hero-light.png" />

<img className="hidden dark:block" src="https://mintcdn.com/orcamemory/5mVXrJpUJbFiHEL2/images/hero-dark.png?fit=max&auto=format&n=5mVXrJpUJbFiHEL2&q=85&s=faf9d264e56abbaf88decd807197ea5d" alt="Orca Memory" width="3840" height="2160" data-path="images/hero-dark.png" />

## What is Orca Memory?

Orca Memory is a memory plugin for [OpenClaw](https://openclaw.ai). It gives your Claw persistent memory across sessions - so it remembers your preferences, past decisions, code patterns, and project knowledge.

Without memory, your Claw starts fresh every conversation. It forgets your coding style, repeats mistakes, and asks the same questions. Orca Memory fixes this.

## Key Features

<CardGroup cols={2}>
  <Card title="Persistent Memory" icon="brain">
    Your Claw remembers preferences, decisions, and context across all sessions
  </Card>

  <Card title="Auto-Recall" icon="rotate">
    Relevant memories are automatically injected before every AI turn
  </Card>

  <Card title="Auto-Capture" icon="camera">
    Important information is automatically stored after each turn
  </Card>

  <Card title="Semantic Search" icon="magnifying-glass">
    Find relevant memories using natural language queries
  </Card>
</CardGroup>

## How It Works

Orca Memory is an [OpenClaw plugin](https://docs.openclaw.ai/plugin#plugins). Once installed:

1. **Auto-Recall** - Before each AI response, relevant memories are injected as context
2. **Auto-Capture** - After each turn, important information is extracted and stored
3. **Tools** - Your Claw can manually store, search, and manage memories

## Memory Types

| Type           | Purpose                       | Example                                    |
| -------------- | ----------------------------- | ------------------------------------------ |
| **Episodic**   | Past events and conversations | "Last week we debugged the auth flow"      |
| **Semantic**   | Facts and knowledge           | "This project uses Convex for the backend" |
| **Procedural** | Patterns and preferences      | "User prefers arrow functions"             |
| **Working**    | Active session context        | Current task and recent decisions          |

## Get Started

<CardGroup cols={2}>
  <Card title="Cloud Quickstart" icon="cloud" href="/cloud/quickstart">
    Get started with the hosted version in under 5 minutes
  </Card>

  <Card title="Self-Host" icon="server" href="/self-hosting/requirements">
    Deploy Orca Memory on your own infrastructure
  </Card>
</CardGroup>