Today's RAG & Vector Databases: Fastest-Growing Projects — April 14, 2026
The RAG & Vector Databases space has seen a surge in innovative projects this week, with a focus on integrating AI-powered search and knowledge management capabilities. Several repositories have gained significant traction, showcasing the growing interest in leveraging Retrieval-Augmented Generation (RAG) technology to enhance information retrieval and analysis.
yanhua1010's "zero-to-ai-fullstack" repository has seen impressive growth, with a Growth Score of 19.75 and 141 stars. This Java-based project showcases a full-stack AI application built using Python, FastAPI, RAG, pgvector, and Next.js, demonstrating the versatility of RAG in real-world applications. Its popularity stems from its comprehensive approach to building an AI-powered backend.
joungminsung's "OpenDocuments" repository has also gained significant attention, boasting a Growth Score of 19.28 and 64 stars. This open-source RAG tool enables users to search documents across multiple platforms, including GitHub, Notion, and Google Drive, providing cited answers with the help of Ollama/OpenAI/Claude. Its growth can be attributed to its ability to streamline document search and knowledge management.
vixhal-baraiya's "pageindex-rag" repository offers a unique approach to RAG, focusing on vectorless, reasoning-based retrieval-augmented generation. With 82 stars and a Growth Score of 6.26, this project has garnered interest for its innovative take on traditional RAG methods. Its growing popularity stems from the potential benefits of using reasoning-based approaches in information retrieval.
nashsu's "llm_wiki" repository is another notable project, boasting an impressive 1,122 stars and a Growth Score of 5.00. This cross-platform desktop application transforms documents into organized knowledge bases by incrementally building and maintaining a persistent wiki from user sources. Its growth can be attributed to its ability to simplify knowledge management and provide a seamless user experience.
Ais1on's "CTI-RAG" repository offers a specialized RAG framework for Cyber Threat Intelligence (CTI), integrating knowledge graph and causal reasoning capabilities. With 23 stars and a Growth Score of 4.83, this project has gained attention from security analysts seeking intelligent threat intelligence analysis tools. Although it hasn't seen recent commits, its growth score indicates continued interest in the project.
Vbj1808's "Dokis" repository provides lightweight RAG provenance middleware, verifying claims in LLM responses without requiring an additional LLM call. With 34 stars and a Growth Score of 2.57, this project has gained traction for its ability to enhance the reliability and transparency of AI-powered information retrieval.
Overall, these projects showcase the diverse applications of RAG technology, from full-stack AI development to specialized threat intelligence analysis tools.
yanhua1010's "zero-to-ai-fullstack" repository has seen impressive growth, with a Growth Score of 19.75 and 141 stars. This Java-based project showcases a full-stack AI application built using Python, FastAPI, RAG, pgvector, and Next.js, demonstrating the versatility of RAG in real-world applications. Its popularity stems from its comprehensive approach to building an AI-powered backend.
joungminsung's "OpenDocuments" repository has also gained significant attention, boasting a Growth Score of 19.28 and 64 stars. This open-source RAG tool enables users to search documents across multiple platforms, including GitHub, Notion, and Google Drive, providing cited answers with the help of Ollama/OpenAI/Claude. Its growth can be attributed to its ability to streamline document search and knowledge management.
vixhal-baraiya's "pageindex-rag" repository offers a unique approach to RAG, focusing on vectorless, reasoning-based retrieval-augmented generation. With 82 stars and a Growth Score of 6.26, this project has garnered interest for its innovative take on traditional RAG methods. Its growing popularity stems from the potential benefits of using reasoning-based approaches in information retrieval.
nashsu's "llm_wiki" repository is another notable project, boasting an impressive 1,122 stars and a Growth Score of 5.00. This cross-platform desktop application transforms documents into organized knowledge bases by incrementally building and maintaining a persistent wiki from user sources. Its growth can be attributed to its ability to simplify knowledge management and provide a seamless user experience.
Ais1on's "CTI-RAG" repository offers a specialized RAG framework for Cyber Threat Intelligence (CTI), integrating knowledge graph and causal reasoning capabilities. With 23 stars and a Growth Score of 4.83, this project has gained attention from security analysts seeking intelligent threat intelligence analysis tools. Although it hasn't seen recent commits, its growth score indicates continued interest in the project.
Vbj1808's "Dokis" repository provides lightweight RAG provenance middleware, verifying claims in LLM responses without requiring an additional LLM call. With 34 stars and a Growth Score of 2.57, this project has gained traction for its ability to enhance the reliability and transparency of AI-powered information retrieval.
Overall, these projects showcase the diverse applications of RAG technology, from full-stack AI development to specialized threat intelligence analysis tools.