# embedded-vector-db

> Lightweight Node.js library for low-latency on-device vector similarity search using HNSW and BM25 hybrid, with CRUD, metadata filtering, and persistence for edge RAG pipelines. Enables real-time semantic search without servers; more lightweight than cloud Qdrant.

- **URL:** https://github.com/pguso/embedded-vector-db
- **Category:** Embedded & Edge Vector Databases
- **Tags:** Open Source, Embedded, Lightweight, No Server, Hybrid Search, Nodejs, Bm25, Edge Ai
- **Updated:** 2026-04-24 10:19
- **Canonical page:** https://vectordb.ever.works/items/embedded-vector-db

## Details

## Overview
embedded-vector-db delivers low-latency hybrid vector/full-text search on-device.

## Features
- HNSW ANN + BM25 hybrid (RRF fusion)
- Multi-namespace CRUD
- Metadata filtering
- Disk persistence

## Use Cases
- IoT real-time search
- Edge RAG apps
- CV inference Node.js

## Comparisons
- On-device vs cloud Qdrant
- Lighter, no-server alternative

## Pricing
Free open-source (MIT).

---

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