Annoy
Approximate nearest neighbor library by Spotify optimized for memory usage.
About
Annoy, Approximate Nearest Neighbors Oh Yeah by Spotify, is a C++ library with Python bindings that builds read-only, file-based nearest-neighbor indexes. The indexes are memory-mapped so many processes can share the same data with low overhead, which suits recommendation and embedding lookup at serving time. It trades index immutability for speed and small memory footprint. 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
Python client library for Qdrant vector database.
Efficient similarity search library by Meta for dense vector clustering and retrieval.
Open-source big data serving engine with built-in vector search and ML inference.
Open-source vector similarity search extension for PostgreSQL.
Serverless vector database built on Lance columnar format.
End-to-end vector search engine with built-in model inference.