multiple vantage point distance-based tree data structure

index binary vectors for efficient nearest neighbor search

hnswlib-wasm attempts to create a browser friendly version of hnswlib

The engine for Sembed written in C++. Sembed is a vector database made for small projects and dosent require a ton of memory to work

A cute toy of IVF (PQ).

A Vector Database Tutorial (over CMU-DB's BusTub system)

Simple and Efficient DiskANN implementation

MSVBASE is a system that efficiently supports complex queries of both approximate similarity search and relational operators. It integrates high-dimensional vector indices into PostgreSQL, a relational database to facilitate complex approximate similarity queries.

Experimental HNSW Index implementation.

A remote cache for vector databases which allows for a dynamically updated subset of a large dataset to be held entirely in memory.

Epsilla is a high performance Vector Database Management System. Try out hosted Epsilla at https://cloud.epsilla.com/

Vector Database with support for late interaction and token level embeddings.

A vector 'database' plugin for Unreal Engine 5. Built for leveraging the power of embeddings to create semantic search functionalities

Fast, SQL powered, in-process vector search for any language with an SQLite driver

A distributed Key-Value Storage using Raft

OceanBase is an enterprise distributed relational database with high availability, high performance, horizontal scalability, and compatibility with SQL standards.

PostgreSQL extension for supporting deep learning model inference within the database and vector storage

Base ANNS Library

MariaDB server is a community developed fork of MySQL server. Started by core members of the original MySQL team, MariaDB actively works with outside developers to deliver the most featureful, stable, and sanely licensed open SQL server in the industry.

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text