# amem

> Agentic memory that evolves

An open-source agentic-memory stack for LLM agents — memories evolve, not just accumulate. Graph linking, hybrid retrieval, LLM-driven evolution. TypeScript, local embeddings, no Python.

## Table of Contents

### Overview

- [Introduction](/guide/introduction.md)

### Concepts

- [How It Works](/guide/how-it-works.md)
- [Evolution & Quality](/guide/evolution.md)
- [Agent Isolation](/guide/agent-isolation.md)
- [A-MEM vs Traditional RAG](/guide/comparison.md)
- [Design Rationale](/guide/design-rationale.md)

### OpenClaw Plugin

- [Installation](/guide/installation.md)
- [Quick Start](/guide/quick-start.md)
- [Configuration](/reference/configuration.md)
- [Tools Reference](/reference/tools.md)
- [Embedding models](/reference/embedding-models.md)
- [Smoke Test Results](/reference/smoketest.md)

### Contributing

- [Contributing](/guide/contributing.md)