MegaMemory

<p align="center"> <h1 align="center">MegaMemory</h1> </p> <p align="center">Persistent project knowledge graph for coding agents.</p> <p align="center"> <a href="https://www.npmjs.com/package/megamemory"><img alt="npm" src="https://img.shields.io/npm/v/megamemory?style=flat-square" /></a> <a href="./LICENSE"><img alt="license" src="https://img.shields.io/npm/l/megamemory?style=flat-square" /></a> <a href="https://nodejs.org"><img alt="node" src="https://img.shields.io/node/v/megamemory?style=flat-square" /></a> <a href="https://www.npmjs.com/package/megamemory"><img alt="npm downloads" src="https://img.shields.io/npm/dm/megamemory?style=flat-square" /></a> <a href="https://x.com/M3ruH4sh"><img alt="Twitter Follow" src="https://img.shields.io/twitter/follow/M3ruH4sh?style=social" /></a> </p> <p align="center"> <img src="./assets/preview.png" alt="MegaMemory web explorer" width="800" /> </p>

---

An MCP server that lets your coding agent build and query a graph of concepts, architecture, and decisions — so it remembers across sessions.

The LLM is the indexer. No AST parsing. No static analysis. Your agent reads code, writes concepts in its own words, and queries them before future tasks. The graph stores concepts — features, modules, patterns, decisions — not code symbols.

The Loop

<p align="center"> <img src="./assets/how-it-works.svg" alt="How MegaMemory works" width="800" /> </p>

understand → work → update

1. Session start — agent calls list_roots to orient itself
2. Before a task — agent calls understand with a natural language query (or get_concept for exact ID lookup)
3. After a task — agent calls create_concept or update_concept to record what it built