Today's RAG & Vector Databases: Fastest-Growing Projects — April 15, 2026
Today's RAG & Vector Databases, we're seeing a surge in interest around open-source tools that enable AI-powered document search and knowledge management. The trend is driven by the growing need for efficient information retrieval and organization, particularly among developers and researchers. As a result, repositories with high growth scores are those that offer innovative solutions to these challenges.
joungminsung/OpenDocuments, with a growth score of 18.26 and 64 stars, is an open-source RAG tool that allows users to search AI documents by connecting GitHub, Notion, Google Drive, and asking questions with cited answers. Its self-hosted capabilities with Ollama/OpenAI/Claude have likely contributed to its rapid growth, as developers seek more control over their document management workflows.
yanhua1010/zero-to-ai-fullstack has a growth score of 17.64 and an impressive 145 stars, showcasing the popularity of this Java backend engineer's journey in learning AI full-stack in public. The repository's focus on Python, FastAPI, RAG, pgvector, and Next.js provides a comprehensive resource for developers looking to expand their skills in AI development.
vixhal-baraiya/pageindex-rag boasts a growth score of 5.95 and 82 stars, with its Vectorless, Reasoning-Based Retrieval-Augmented Generation (RAG) approach attracting attention from researchers and developers seeking innovative solutions. Although its growth rate is slower compared to the top two repositories, pageindex-rag's unique approach has likely contributed to its steady increase in popularity.
nashsu/llm_wiki has a remarkable 1,355 stars, but a relatively lower growth score of 5.27, indicating a established repository with continued interest. LLM Wiki is a cross-platform desktop application that turns documents into an organized, interlinked knowledge base – automatically. Its incremental approach to building and maintaining a persistent wiki from sources has likely resonated with users seeking efficient document management solutions.
Ais1on/CTI-RAG has a growth score of 5.25 and 30 stars, indicating moderate interest in its Retrieval-Augmented Generation (RAG) framework for Cyber Threat Intelligence (CTI). Although there have been no recent commits, the integration of knowledge graph and causal reasoning capabilities provides security analysts with an intelligent threat intelligence analysis tool, which may explain its steady growth.
Lastly, Vbj1808/Dokis has a growth score of 2.46 and 34 stars, with its lightweight RAG provenance middleware verifying claims in LLM responses without requiring an additional LLM call. Although it has a lower growth rate compared to other repositories, Dokis's innovative approach to trustworthiness in AI-generated content may contribute to its continued interest among developers.
These repositories showcase the diverse range of applications and approaches within the RAG & Vector Databases space, from document search and knowledge management to threat intelligence analysis. As the demand for efficient information retrieval and organization continues to grow, we can expect to see more innovative solutions emerge in this category.
joungminsung/OpenDocuments, with a growth score of 18.26 and 64 stars, is an open-source RAG tool that allows users to search AI documents by connecting GitHub, Notion, Google Drive, and asking questions with cited answers. Its self-hosted capabilities with Ollama/OpenAI/Claude have likely contributed to its rapid growth, as developers seek more control over their document management workflows.
yanhua1010/zero-to-ai-fullstack has a growth score of 17.64 and an impressive 145 stars, showcasing the popularity of this Java backend engineer's journey in learning AI full-stack in public. The repository's focus on Python, FastAPI, RAG, pgvector, and Next.js provides a comprehensive resource for developers looking to expand their skills in AI development.
vixhal-baraiya/pageindex-rag boasts a growth score of 5.95 and 82 stars, with its Vectorless, Reasoning-Based Retrieval-Augmented Generation (RAG) approach attracting attention from researchers and developers seeking innovative solutions. Although its growth rate is slower compared to the top two repositories, pageindex-rag's unique approach has likely contributed to its steady increase in popularity.
nashsu/llm_wiki has a remarkable 1,355 stars, but a relatively lower growth score of 5.27, indicating a established repository with continued interest. LLM Wiki is a cross-platform desktop application that turns documents into an organized, interlinked knowledge base – automatically. Its incremental approach to building and maintaining a persistent wiki from sources has likely resonated with users seeking efficient document management solutions.
Ais1on/CTI-RAG has a growth score of 5.25 and 30 stars, indicating moderate interest in its Retrieval-Augmented Generation (RAG) framework for Cyber Threat Intelligence (CTI). Although there have been no recent commits, the integration of knowledge graph and causal reasoning capabilities provides security analysts with an intelligent threat intelligence analysis tool, which may explain its steady growth.
Lastly, Vbj1808/Dokis has a growth score of 2.46 and 34 stars, with its lightweight RAG provenance middleware verifying claims in LLM responses without requiring an additional LLM call. Although it has a lower growth rate compared to other repositories, Dokis's innovative approach to trustworthiness in AI-generated content may contribute to its continued interest among developers.
These repositories showcase the diverse range of applications and approaches within the RAG & Vector Databases space, from document search and knowledge management to threat intelligence analysis. As the demand for efficient information retrieval and organization continues to grow, we can expect to see more innovative solutions emerge in this category.