Highlights
- Pro
Stars
High-performance vector search for PostgreSQL
FilmCraft: An open-source, nonlinear video editor written from scratch in pure Rust
Rank-Biased Precision, Overlap, Recall, and Alignment
[SIGMOD REC 2026] The DaiSy Library for Fast and Exact, Data Series and Vector Similarity Search
Billion-scale embedded vector database built entirely on Parquet and Arrow.
Rust implementation of the SuperKMeans paper from CWI
`arrowspace` for Python. A graph analysis and vector search library
A provider-agnostic scaffolding kit for running structured multi-agent workflows in your codebase.
Free and Open Source, Distributed, RESTful Search Engine
A library for efficient similarity search and clustering of dense vectors.
One Postgres for your application data, full-text search, vector retrieval, and aggregations. Home of the pg_search extension.
Noorts / VectorDBBench
Forked from zilliztech/VectorDBBench[WIP] DuckDB clients and new datasets for VectorDBBench
Vector search using only Parquet and DataFusion
⚡ Super fast clustering for high-dimensional vectors on CPUs (x86, ARM) and GPUs — for Python and C++. Faster clustering of vector embeddings than FAISS
⚡ DuckIR: A DuckDB extension for Information Retrieval. Fast (filtered) vector search beyond memory fully integrated with DuckDB. FTS and hybrid search coming soon.
Performance-portable, length-agnostic SIMD with runtime dispatch
Framework for evaluating ANNS algorithms on billion scale datasets.
TPC-H benchmark data generation in pure Rust
DuckLake is an integrated data lake and catalog format
[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal d…