Today's RAG & Vector Databases: Fastest-Growing Projects — April 29, 2026
Today's the RAG & Vector Databases space, we've seen a surge in interest around tools that leverage graph-based architectures to enhance knowledge retrieval and generation capabilities. The top-growing repositories are showcasing innovative applications of Retrieval-Augmented Generation (RAG) technology, from threat intelligence analysis to intelligent chatbots.
FlowElement-ai's m_flow repository leads the pack with an impressive Growth Score of 59.16 and over 2,138 stars. M-flow is a graph-based RAG system that identifies relevant information by finding similarities in data, making it an attractive solution for applications requiring robust knowledge retrieval capabilities. Its rapid growth can be attributed to its unique approach to relevance ranking, which sets it apart from traditional RAG systems.
Rolandpg's zettelforge repository has also seen significant traction, with a Growth Score of 14.09 and 33 stars. Zettelforge is an agentic memory framework for CTI in Python, featuring STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, and MCP server capabilities. Its growth can be attributed to its comprehensive feature set, which addresses the complex needs of cyber threat intelligence analysis.
Ais1on's CTI-RAG repository boasts 169 stars and a Growth Score of 5.86, despite having no commits in the past 30 days. CTI-RAG is a RAG framework designed specifically for Cyber Threat Intelligence (CTI) analysis, integrating knowledge graph and causal reasoning capabilities to provide security analysts with an intelligent threat intelligence analysis tool. Its growth can be attributed to its specialized focus on CTI, which has garnered attention from security professionals seeking innovative solutions.
Yanhua1010's zero-to-ai-fullstack repository has a Growth Score of 4.98 and 152 stars, with 7 commits in the past 30 days. This repository chronicles the author's journey as a Java backend engineer learning AI full-stack development, featuring Python, FastAPI, RAG, pgvector, and Next.js. Its growth can be attributed to its unique blend of technical topics, which has attracted developers interested in AI full-stack development.
Nashsu's llm_wiki repository has an impressive 4,767 stars and a Growth Score of 4.36, with 100 commits in the past 30 days. LLM Wiki is a cross-platform desktop application that turns documents into an organized, interlinked knowledge base using RAG technology. Its growth can be attributed to its user-friendly approach to knowledge management, which has resonated with users seeking to streamline their document organization.
Zhanghang2017's AI-chat-rag repository rounds out the list with a Growth Score of 1.38 and 41 stars, featuring a React+Node+LangChain-based intelligent chatbot application that leverages RAG technology. Its growth can be attributed to its innovative application of RAG in conversational AI, which has garnered attention from developers interested in building intelligent chatbots.
FlowElement-ai's m_flow repository leads the pack with an impressive Growth Score of 59.16 and over 2,138 stars. M-flow is a graph-based RAG system that identifies relevant information by finding similarities in data, making it an attractive solution for applications requiring robust knowledge retrieval capabilities. Its rapid growth can be attributed to its unique approach to relevance ranking, which sets it apart from traditional RAG systems.
Rolandpg's zettelforge repository has also seen significant traction, with a Growth Score of 14.09 and 33 stars. Zettelforge is an agentic memory framework for CTI in Python, featuring STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, and MCP server capabilities. Its growth can be attributed to its comprehensive feature set, which addresses the complex needs of cyber threat intelligence analysis.
Ais1on's CTI-RAG repository boasts 169 stars and a Growth Score of 5.86, despite having no commits in the past 30 days. CTI-RAG is a RAG framework designed specifically for Cyber Threat Intelligence (CTI) analysis, integrating knowledge graph and causal reasoning capabilities to provide security analysts with an intelligent threat intelligence analysis tool. Its growth can be attributed to its specialized focus on CTI, which has garnered attention from security professionals seeking innovative solutions.
Yanhua1010's zero-to-ai-fullstack repository has a Growth Score of 4.98 and 152 stars, with 7 commits in the past 30 days. This repository chronicles the author's journey as a Java backend engineer learning AI full-stack development, featuring Python, FastAPI, RAG, pgvector, and Next.js. Its growth can be attributed to its unique blend of technical topics, which has attracted developers interested in AI full-stack development.
Nashsu's llm_wiki repository has an impressive 4,767 stars and a Growth Score of 4.36, with 100 commits in the past 30 days. LLM Wiki is a cross-platform desktop application that turns documents into an organized, interlinked knowledge base using RAG technology. Its growth can be attributed to its user-friendly approach to knowledge management, which has resonated with users seeking to streamline their document organization.
Zhanghang2017's AI-chat-rag repository rounds out the list with a Growth Score of 1.38 and 41 stars, featuring a React+Node+LangChain-based intelligent chatbot application that leverages RAG technology. Its growth can be attributed to its innovative application of RAG in conversational AI, which has garnered attention from developers interested in building intelligent chatbots.