# MeMemo

> A JavaScript library that brings vector search and RAG (Retrieval-Augmented Generation) to browser environments, enabling efficient searching through millions of vectors using HNSW algorithm with IndexedDB and Web Workers.

- **URL:** https://github.com/poloclub/mememo
- **Category:** SDKs & Libraries
- **Tags:** Javascript, browser, Rag
- **Updated:** 2026-03-14 12:39
- **Canonical page:** https://vectordb.ever.works/items/mememo

## Details

## Overview

MeMemo is a JavaScript library that brings RAG and vector search to browser environments. MeMemo adapts the state-of-the-art approximate nearest neighbor search technique HNSW to browser environments.

## Key Features

- **Browser-Native**: Developed with modern Web technologies like IndexedDB and Web Workers
- **Client-Side Processing**: Leverages client-side hardware capabilities to efficiently search through millions of high-dimensional vectors in browsers
- **Easy Integration**: Install with a single command `npm install mememo` and import into any web app
- **Framework Agnostic**: Works with JavaScript, TypeScript, React, Svelte, or Lit
- **HNSW Algorithm**: Uses state-of-the-art approximate nearest neighbor search

## Purpose

MeMemo is the first JavaScript toolkit that offloads vector storage and dense retrieval to the client—empowering a broader range of audiences to leverage cutting-edge retrieval techniques to enhance their LLM experiences.

## Applications

Enables private, on-device RAG for personalized text generation without sending data to external servers. Includes RAG Playground demo application.

## Resources

- GitHub: https://github.com/poloclub/mememo
- NPM Package: https://www.npmjs.com/package/mememo
- Website: https://poloclub.github.io/mememo/

---

_This Markdown mirror is generated by Ever Works for AI agents. The canonical HTML page is at https://vectordb.ever.works/items/mememo._