Today's RAG & Vector Databases: Fastest-Growing Projects — September 17, 2026
This week, the RAG (Retrieval-Augmented Generation) and Vector Databases space continues to see significant activity as developers explore innovative ways to integrate real-time data retrieval with AI-driven chatbots and knowledge assistants. The top performers this week are primarily focused on leveraging vector databases for enhanced data querying and synthesis capabilities, catering to diverse use cases from cryptocurrency analysis to academic assistance.
iamzulx/crypto-rag is a crypto assistant that combines RAG technology with real-time market data across six exchanges, WebSocket integration, derivatives, on-chain information, TVL (Total Value Locked), and DeFi insights. With 739 stars and a growth score of 36.67, this tool's popularity stems from its comprehensive approach to integrating diverse financial data streams into an AI-driven assistant.
codeforstartups/dynavec introduces a serverless hybrid vector database solution that leverages DynamoDB and Amazon S3 Vectors for efficient storage and querying of large-scale datasets. This project has gained traction with 24 stars and a growth score of 25.25, likely due to its innovative use of cloud services to provide scalable and cost-effective vector database solutions.
BenyRonald77/uajy-academic-rag-chatbot offers a production-grade chatbot for the academic handbook of Universitas Atma Jaya Yogyakarta, utilizing Streamlit for web interface, FAISS for vector search, and Google Gemini 2.5 Flash for language model synthesis. The chatbot has attracted significant attention with 640 stars and a growth score of 20.41, likely due to its practical application in academic settings and the seamless integration of cutting-edge technologies.
makralabs/makra, while showing less growth compared to other tools, provides an intriguing memory layer between web content and AI agents, serving real-time structured data through vector search queries. With 28 stars and a growth score of 2.32, Makra's steady development over the past month suggests it is building a niche user base interested in efficient data retrieval mechanisms for AI applications.
The variety and depth of these projects highlight the evolving landscape of RAG and Vector Databases, with developers increasingly focusing on practical implementations that cater to specific industry needs while leveraging advanced AI capabilities.
iamzulx/crypto-rag is a crypto assistant that combines RAG technology with real-time market data across six exchanges, WebSocket integration, derivatives, on-chain information, TVL (Total Value Locked), and DeFi insights. With 739 stars and a growth score of 36.67, this tool's popularity stems from its comprehensive approach to integrating diverse financial data streams into an AI-driven assistant.
codeforstartups/dynavec introduces a serverless hybrid vector database solution that leverages DynamoDB and Amazon S3 Vectors for efficient storage and querying of large-scale datasets. This project has gained traction with 24 stars and a growth score of 25.25, likely due to its innovative use of cloud services to provide scalable and cost-effective vector database solutions.
BenyRonald77/uajy-academic-rag-chatbot offers a production-grade chatbot for the academic handbook of Universitas Atma Jaya Yogyakarta, utilizing Streamlit for web interface, FAISS for vector search, and Google Gemini 2.5 Flash for language model synthesis. The chatbot has attracted significant attention with 640 stars and a growth score of 20.41, likely due to its practical application in academic settings and the seamless integration of cutting-edge technologies.
makralabs/makra, while showing less growth compared to other tools, provides an intriguing memory layer between web content and AI agents, serving real-time structured data through vector search queries. With 28 stars and a growth score of 2.32, Makra's steady development over the past month suggests it is building a niche user base interested in efficient data retrieval mechanisms for AI applications.
The variety and depth of these projects highlight the evolving landscape of RAG and Vector Databases, with developers increasingly focusing on practical implementations that cater to specific industry needs while leveraging advanced AI capabilities.