# GLASS

> Leading graph-based ANN library optimized for approximate nearest neighbor search, offering competitive performance especially at lower recall levels across diverse datasets.

- **URL:** https://github.com/JinHai-CN/glass
- **Category:** Sdks & Libraries
- **Tags:** Ann, graph-based, cpp
- **Updated:** 2026-03-10 11:58
- **Canonical page:** https://vectordb.ever.works/items/glass

## Details

## Overview

GLASS is a leading graph-based ANN (Approximate Nearest Neighbor) library that provides fast query times especially at recall levels under 90% on most datasets.

## Features

- Graph-based indexing algorithm
- Optimized for approximate nearest neighbor search
- Competitive performance across benchmarks
- Efficient at lower recall thresholds
- Support for large-scale datasets

## Technical Details

- Graph-based index structure
- Optimized traversal algorithms
- Memory-efficient implementation
- Scalable to millions of vectors

## Performance

- Faster query times than alternatives at <90% recall
- Competitive with leading libraries
- Good balance of speed and accuracy
- Efficient memory usage

## Use Cases

- Large-scale similarity search
- Applications tolerating approximate results
- Performance-critical deployments
- Research and benchmarking

## Comparison

Research shows GLASS performs well compared to other leading libraries like LoRANN at various recall levels, particularly excelling in the 70-90% recall range.

## 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/glass._