# DiskANN

> DiskANN is a pure ANN index library implementing Vamana graphs for disk-based billion-scale approximate nearest neighbor search with low memory footprint. Features GPU acceleration, dynamic updates, cached SSD search, C++/Python bindings. Suited for custom vector engines handling large cold datasets in search/recommendations, benchmarks; more disk-efficient than HNSWLib vs full DBs like Qdrant.

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

## Details

# DiskANN

- **Description:** DiskANN is a graph-based approximate nearest neighbor search (ANNS) system designed for fast and accurate billion-point nearest neighbor search on a single node, utilizing SSD storage. It is suitable for large-scale vector database applications that require efficient and scalable vector search.
- **Source:** [arXiv:2105.09613](https://arxiv.org/abs/2105.09613)

## Features
- Graph-based ANNS algorithm
- Optimized for billion-point nearest neighbor search
- Efficient operation on a single node
- Leverages SSD storage for scalability and performance
- Suitable for large-scale vector database and similarity search applications

## Pricing
- No pricing information provided.

---

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