Today's RAG & Vector Databases: Fastest-Growing Projects — April 17, 2026
The RAG & Vector Databases space is heating up this week, with several projects showcasing innovative applications of Retrieval-Augmented Generation (RAG) technology. We're seeing a trend towards more specialized use cases, such as AI-powered document search and cyber threat intelligence analysis. Meanwhile, open-source implementations continue to attract attention from developers.
joungminsung/OpenDocuments is making waves with its impressive growth score of 16.55 and 65 stars. This open-source RAG tool enables AI-powered document search across multiple platforms like GitHub, Notion, and Google Drive, providing cited answers to users' queries. Its self-hosted capabilities using Ollama, OpenAI, or Claude have likely contributed to its rapid growth.
yanhua1010/zero-to-ai-fullstack has garnered a significant following with 146 stars and a respectable growth score of 13.94. This repository chronicles the author's journey as a Java backend engineer learning AI full-stack in public, incorporating RAG, pgvector, and Next.js. Its growth can be attributed to the increasing interest in full-stack AI development and the value of publicly documented learning journeys.
vixhal-baraiya/pageindex-rag boasts 83 stars and a growth score of 5.43, indicating steady interest in its vectorless, reasoning-based Retrieval-Augmented Generation approach. By offering an alternative to traditional RAG methods, this project has attracted attention from researchers and developers exploring novel applications of RAG technology.
nashsu/llm_wiki stands out with an impressive 1,474 stars and a growth score of 5.15, demonstrating the popularity of its LLM-powered desktop application for turning documents into organized knowledge bases. Unlike traditional RAG approaches, this tool incrementally builds and maintains a persistent wiki from user sources, likely contributing to its widespread adoption.
Ais1on/CTI-RAG has garnered 45 stars and a growth score of 4.75, reflecting interest in its Retrieval-Augmented Generation framework for Cyber Threat Intelligence (CTI) analysis. By integrating knowledge graph and causal reasoning capabilities, this project offers security analysts an intelligent tool for threat intelligence analysis.
Vbj1808/Dokis has attracted 34 stars and achieved a growth score of 2.38 with its lightweight RAG provenance middleware. This tool verifies the grounding of claims in LLM responses without requiring an additional LLM call, addressing concerns around transparency and accountability in AI-generated content.
McKern3l/RAGdrag rounds out our list with 25 stars and a growth score of 1.83, showcasing its RAG pipeline security testing toolkit. With 27 techniques across six kill chain phases mapped to MITRE ATLAS, this project has likely appealed to developers focused on securing their RAG pipelines.
These projects collectively demonstrate the diverse applications and innovations emerging in the RAG & Vector Databases space, from document search and knowledge base creation to cyber threat intelligence analysis and pipeline security testing.
joungminsung/OpenDocuments is making waves with its impressive growth score of 16.55 and 65 stars. This open-source RAG tool enables AI-powered document search across multiple platforms like GitHub, Notion, and Google Drive, providing cited answers to users' queries. Its self-hosted capabilities using Ollama, OpenAI, or Claude have likely contributed to its rapid growth.
yanhua1010/zero-to-ai-fullstack has garnered a significant following with 146 stars and a respectable growth score of 13.94. This repository chronicles the author's journey as a Java backend engineer learning AI full-stack in public, incorporating RAG, pgvector, and Next.js. Its growth can be attributed to the increasing interest in full-stack AI development and the value of publicly documented learning journeys.
vixhal-baraiya/pageindex-rag boasts 83 stars and a growth score of 5.43, indicating steady interest in its vectorless, reasoning-based Retrieval-Augmented Generation approach. By offering an alternative to traditional RAG methods, this project has attracted attention from researchers and developers exploring novel applications of RAG technology.
nashsu/llm_wiki stands out with an impressive 1,474 stars and a growth score of 5.15, demonstrating the popularity of its LLM-powered desktop application for turning documents into organized knowledge bases. Unlike traditional RAG approaches, this tool incrementally builds and maintains a persistent wiki from user sources, likely contributing to its widespread adoption.
Ais1on/CTI-RAG has garnered 45 stars and a growth score of 4.75, reflecting interest in its Retrieval-Augmented Generation framework for Cyber Threat Intelligence (CTI) analysis. By integrating knowledge graph and causal reasoning capabilities, this project offers security analysts an intelligent tool for threat intelligence analysis.
Vbj1808/Dokis has attracted 34 stars and achieved a growth score of 2.38 with its lightweight RAG provenance middleware. This tool verifies the grounding of claims in LLM responses without requiring an additional LLM call, addressing concerns around transparency and accountability in AI-generated content.
McKern3l/RAGdrag rounds out our list with 25 stars and a growth score of 1.83, showcasing its RAG pipeline security testing toolkit. With 27 techniques across six kill chain phases mapped to MITRE ATLAS, this project has likely appealed to developers focused on securing their RAG pipelines.
These projects collectively demonstrate the diverse applications and innovations emerging in the RAG & Vector Databases space, from document search and knowledge base creation to cyber threat intelligence analysis and pipeline security testing.