Voyager
Approximate nearest neighbor library by Spotify using HNSW.
About
Voyager by Spotify is a library for fast approximate nearest-neighbor search over an in-memory collection of vectors, built on the HNSW algorithm and the hnswlib package with added speed and convenience features. It provides matching Python and Java bindings with compatible on-disk indexes, so the same index works from either language. It is used in production at Spotify. Released under the Apache 2.0 license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Vector Databases & Embeddings
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Easy (2/5)
- License
- Apache-2.0
- Added
- Apr 3, 2026
Related Tools
Fast embedding inference server supporting many embedding models.
Open-source vector similarity search extension for PostgreSQL.
All-in-one embeddings database for semantic search, LLM orchestration, and language model workflows.
Library for representing and sending multimodal data by Jina AI.
Python client library for Qdrant vector database.
Efficient similarity search library by Meta for dense vector clustering and retrieval.