DiceDB is a redis-compliant, in-memory, real-time, and reactive database optimized for modern hardware and for building and scaling truly real-time applications.

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

Run GPU Workloads Across Multiple Clouds

Distributed SQL database in Rust, written as an educational project

LevelDB is a fast key-value storage library written at Google that provides an ordered mapping from string keys to string values.

A library that provides an embeddable, persistent key-value store for fast storage.

A modern replacement for Redis and Memcached

The lightweight, user-friendly, distributed relational database built on SQLite.

Container Network Interface - networking for Linux containers

A fast bump allocation arena for Rust

A minimalist yet highly performant, lightweight, lightning fast, multisource, multimodal and local embedding solution, built in rust.

Library for generating vector embeddings, reranking in Rust

Limbo is a work-in-progress, in-process OLTP database management system, compatible with SQLite.

Tantivy is a full-text search engine library inspired by Apache Lucene and written in Rust

libSQL is a fork of SQLite that is both Open Source, and Open Contributions.

From the Transistor to the Web Browser, a rough outline for a 12 week course

ClickHouse® is a real-time analytics DBMS

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

On-Call/DevOps Assistant - Get a head start on fixing alerts with AI investigation

Integrate AI-powered Document Analysis Pipelines

AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark

Yet another operator for running large language models on Kubernetes with ease. Powered by Ollama! 🐫

Unicode Algorithms Implementation for C/C++

Unicode Normalization forms according to UAX#15 rules

unicodedata backport/updates

A C++ library for Unicode

Highly specialized crate to parse and use `google/sentencepiece` 's precompiled_charsmap in `tokenizers`

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.

MTEB: Massive Text Embedding Benchmark