Rust implementation of the SuperKMeans paper from CWI

`arrowspace` for Python. A graph analysis and vector search library

Self-hosted AI workspace.

A provider-agnostic scaffolding kit for running structured multi-agent workflows in your codebase.

Official repository of TACHIOM.

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.

Automatic query privatization in DuckDB

[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++. 100x faster clustering of vector embeddings than FAISS

[WIP] A state-of-the-art IVF index for lightweight but fast (filtered) vector similarity search in DuckDB.

HPC research and demonstrations

Performance-portable, length-agnostic SIMD with runtime dispatch

Framework for evaluating ANNS algorithms on billion scale datasets.

Read-through cache for object storage

TPC-H benchmark data generation in pure Rust

DuckLake is an integrated data lake and catalog format

[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

High-Performance K-Means Clustering Library

Query-Adaptive Vector Search

[NeurIPS'24] Approximate Nearest Neighbor search using reduced-rank regression, with extremely fast queries, tiny memory usage, and rapid indexing on modern vector embeddings.

A list of papers in the field of approximate nearest neighbor search on high-dimensional vectors.

Soon filled, stay tuned!

Low-latency NUMA-aware fork-join thread-pool with zero allocations, syscalls, CAS, or false-sharing on the hot path for C, C++, Rust, and Zig 🍴