Best Vector Databases & Retrieval AI GitHub Repos

Chroma

AI GitHub Repos

#25

AI-focused search infrastructure project hosted on GitHub. It enables developers to contribute to its development and enhance AI search capabilities through…Chroma is an AI-focused search infrastructure project hosted on GitHub. It enables developers to contribute to its development and enhance AI search capabilities through…

RAGFlow

AI GitHub Repos

#30

Open-source Retrieval-Augmented Generation (RAG) engine that integrates advanced RAG with Agent capabilities, providing a robust context layer for large language…RAGFlow is an open-source Retrieval-Augmented Generation (RAG) engine that integrates advanced RAG with Agent capabilities, providing a robust context layer for large language…

Open-source tool for vector similarity search in Postgres. It allows developers to efficiently manage and query vector data, enhancing applications that rely on…pgvector is an open-source tool for vector similarity search in Postgres. It allows developers to efficiently manage and query vector data, enhancing applications that rely on…

Milvus - High-Performance Vector Database

AI GitHub Repos

#40

High-performance, cloud-native vector database designed for scalable vector approximate nearest neighbor (ANN) search, enabling efficient data retrieval and management…Milvus is a high-performance, cloud-native vector database designed for scalable vector approximate nearest neighbor (ANN) search, enabling efficient data retrieval and management…

Cognee

AI GitHub Repos

#124

Open-source AI memory platform designed for agents, enabling persistent long-term memory across sessions with a self-hosted knowledge graph engine. Ideal for…Cognee is an open-source AI memory platform designed for agents, enabling persistent long-term memory across sessions with a self-hosted knowledge graph engine. Ideal for…

R2R — AI Retrieval System

AI GitHub Repos

#238

State-of-the-art AI retrieval system designed for efficient data retrieval and generation. It utilizes Agentic Retrieval-Augmented Generation (RAG) with a RESTful API,…R2R is a state-of-the-art AI retrieval system designed for efficient data retrieval and generation. It utilizes Agentic Retrieval-Augmented Generation (RAG) with a RESTful API,…

AWS Bedrock S3 Vectors RAG

AI GitHub Repos

High-performance, cost-efficient multimodal retrieval-augmented generation (RAG) system. It integrates S3 Vector storage, Redis semantic caching,…AWS Bedrock S3 Vectors RAG is a high-performance, cost-efficient multimodal retrieval-augmented generation (RAG) system. It integrates S3 Vector storage, Redis semantic caching,…

RAG for Engineering Documents

AI GitHub Repos

A multimodal RAG system designed to extract, index, and query technical information from engineering drawings. It utilizes Gemini, OCR, vector search, and semantic retrieval to…

MemoryVault AI

AI GitHub Repos

Open-source persistent multimodal AI memory system. It utilizes hybrid retrieval, reranking, and an agentic workflow to manage and access information…MemoryVault AI is an open-source persistent multimodal AI memory system. It utilizes hybrid retrieval, reranking, and an agentic workflow to manage and access information…

Faiss Library

AI GitHub Repos

Library designed for efficient similarity search and clustering of dense vectors, developed by Facebook Research. It is widely used for large-scale machine learning…Faiss is a library designed for efficient similarity search and clustering of dense vectors, developed by Facebook Research. It is widely used for large-scale machine learning…

Text Embeddings Inference (TEI)

AI GitHub Repos

High-speed solution for generating text embeddings. It is designed to efficiently process and infer embeddings from text models, making it…Text Embeddings Inference (TEI) is a high-speed solution for generating text embeddings. It is designed to efficiently process and infer embeddings from text models, making it…

Qdrant Vector Database

AI GitHub Repos

High-performance, massive-scale vector database and search engine designed for the next generation of AI applications. It offers cloud availability and is optimized…Qdrant is a high-performance, massive-scale vector database and search engine designed for the next generation of AI applications. It offers cloud availability and is optimized…

pgvectorscale Postgres Extension

AI GitHub Repos

Postgres extension designed for vector search using DiskANN. It complements pgvector to enhance performance and scalability, and is open-source licensed under…pgvectorscale is a Postgres extension designed for vector search using DiskANN. It complements pgvector to enhance performance and scalability, and is open-source licensed under…