USearch
Compact single-header vector search engine supporting multiple languages.
About
USearch by Unum is a compact single-header vector and text similarity search engine with bindings for C, C++, Python, JavaScript, Java, Rust, and many more languages across desktop, mobile, and WebAssembly. Built on the HNSW algorithm, it is far smaller than FAISS and supports half-precision, SIMD acceleration, and custom distance functions. 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
Open-source big data serving engine with built-in vector search and ML inference.
Highly scalable distributed vector search engine by Yahoo Japan.
Open-source vector similarity search extension for PostgreSQL.
High-performance embedding server by Hugging Face for production deployment.
All-in-one embeddings database for semantic search, LLM orchestration, and language model workflows.
Efficient similarity search library by Meta for dense vector clustering and retrieval.