# ANN Library

> A C++ library for approximate nearest neighbor searching in arbitrarily high dimensions, developed by David Mount and Sunil Arya at the University of Maryland. Provides data structures and algorithms for both exact and approximate nearest neighbor searching.

- **URL:** https://www.cs.umd.edu/~mount/ANN/
- **Category:** Developer Tools & Libraries
- **Tags:** Ann, cpp, high-dimensional
- **Updated:** 2026-04-22 04:16
- **Canonical page:** https://vectordb.ever.works/items/ann-library

## Details

## Overview

ANN (Approximate Nearest Neighbors) is a library written in C++, which supports data structures and algorithms for both exact and approximate nearest neighbor searching in arbitrarily high dimensions.

## Features

- Supports both exact and approximate nearest neighbor searching
- Optimized for arbitrarily high dimensions
- Provides kd-tree and bd-tree data structures
- Priority search for approximate searching
- Fixed-radius and k-nearest neighbor queries
- Written in C++ for high performance
- Portable across multiple platforms

## Applications

Used in machine learning tasks including image recognition, natural language processing, and recommendation systems.

## Pricing

Free and open-source.

---

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