# HNSWLIB

> HNSWLIB is a pure ANN index library implementing Hierarchical Navigable Small World (HNSW) graphs for high-performance approximate nearest neighbor search. Features L2/cosine metrics, multi-threading, low memory, C++/Python bindings. Ideal for custom vector engines, benchmarks on millions of vectors; core building block for DBs like Qdrant/Chroma vs complete solutions.

- **URL:** https://github.com/nmslib/hnswlib
- **Category:** ANN Indexing Libraries
- **Tags:** Pure ANN, Index Only, Benchmark Tool
- **Updated:** 2026-04-24 10:19
- **Canonical page:** https://vectordb.ever.works/items/hnswlib

## Details

## Features

- Fast query performance
- Support for multi-core parallelism
- Custom distance metrics: Euclidean, Cosine, L1, and more
- Python and C++ interfaces

## Installation and Usage

HNSWLIB can be installed using pip, and its API is easy to use with Python and C++ examples provided in the official repository.

---

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