Today's RAG & Vector Databases: Fastest-Growing Projects — April 18, 2026
This week, we've seen significant growth in the RAG & Vector Databases space, with several tools leveraging Retrieval-Augmented Generation (RAG) to enhance AI document search and knowledge base management. The trend towards self-hosted solutions is also evident, with many projects incorporating popular AI models like OpenAI and Claude. Additionally, there's a growing interest in using RAG for specific applications, such as cyber threat intelligence analysis.
FlowElement-ai/m_flow has taken the top spot this week, with an impressive Growth Score of 39.28 and 526 stars. This tool uses graph-based RAG to find similar documents and M-flow to identify relevant information, making it a powerful solution for AI-powered document search. Its rapid growth is likely due to its innovative approach to combining multiple techniques for improved results.
OpenDocuments by joungminsung has seen significant traction with a Growth Score of 15.89 and 66 stars. This open-source RAG tool allows users to connect various data sources like GitHub, Notion, and Google Drive, enabling AI-powered document search with cited answers. Its self-hosted capabilities using popular models like Ollama, OpenAI, and Claude have likely contributed to its growing popularity.
Yanhua1010's zero-to-ai-fullstack project has gained a notable following, boasting 147 stars and a Growth Score of 12.60. This comprehensive repository documents the author's journey learning AI full-stack development using Python, FastAPI, RAG, pgvector, and Next.js. Its growth is likely due to its well-rounded approach to teaching AI development concepts.
Vixhal-baraiya's pageindex-rag project has seen moderate growth with a Growth Score of 5.22 and 84 stars. This vectorless RAG solution uses reasoning-based retrieval for improved results, making it an interesting alternative to traditional approaches. Its slow but steady growth suggests that users are interested in exploring new methods.
Ais1on's CTI-RAG framework has garnered attention with a Growth Score of 5.14 and 60 stars, despite having no recent commits. This cyber threat intelligence tool integrates knowledge graph and causal reasoning capabilities for intelligent threat analysis. Its growth is likely due to its unique application of RAG in the security domain.
Nashsu's llm_wiki project has seen significant interest with a whopping 1,679 stars and a Growth Score of 4.05. This cross-platform desktop application turns documents into an organized knowledge base using incremental LLM updates. Its popularity can be attributed to its innovative approach to traditional RAG methods.
Vbj1808's Dokis project has gained some traction with a Growth Score of 2.30 and 34 stars. This lightweight RAG middleware verifies the provenance of claims in LLM responses without requiring an additional LLM call. Its growth suggests that users value tools that prioritize transparency and accountability.
McKern3l's RAGdrag toolkit rounds out our list, with a Growth Score of 1.76 and 25 stars. This pipeline security testing tool offers 27 techniques across six kill chain phases, making it a useful resource for those working in the field. Its slow growth may indicate that users are still exploring its capabilities.
Overall, Today's trends highlight the growing importance of RAG & Vector Databases in various applications, from AI document search to cyber threat intelligence analysis.
FlowElement-ai/m_flow has taken the top spot this week, with an impressive Growth Score of 39.28 and 526 stars. This tool uses graph-based RAG to find similar documents and M-flow to identify relevant information, making it a powerful solution for AI-powered document search. Its rapid growth is likely due to its innovative approach to combining multiple techniques for improved results.
OpenDocuments by joungminsung has seen significant traction with a Growth Score of 15.89 and 66 stars. This open-source RAG tool allows users to connect various data sources like GitHub, Notion, and Google Drive, enabling AI-powered document search with cited answers. Its self-hosted capabilities using popular models like Ollama, OpenAI, and Claude have likely contributed to its growing popularity.
Yanhua1010's zero-to-ai-fullstack project has gained a notable following, boasting 147 stars and a Growth Score of 12.60. This comprehensive repository documents the author's journey learning AI full-stack development using Python, FastAPI, RAG, pgvector, and Next.js. Its growth is likely due to its well-rounded approach to teaching AI development concepts.
Vixhal-baraiya's pageindex-rag project has seen moderate growth with a Growth Score of 5.22 and 84 stars. This vectorless RAG solution uses reasoning-based retrieval for improved results, making it an interesting alternative to traditional approaches. Its slow but steady growth suggests that users are interested in exploring new methods.
Ais1on's CTI-RAG framework has garnered attention with a Growth Score of 5.14 and 60 stars, despite having no recent commits. This cyber threat intelligence tool integrates knowledge graph and causal reasoning capabilities for intelligent threat analysis. Its growth is likely due to its unique application of RAG in the security domain.
Nashsu's llm_wiki project has seen significant interest with a whopping 1,679 stars and a Growth Score of 4.05. This cross-platform desktop application turns documents into an organized knowledge base using incremental LLM updates. Its popularity can be attributed to its innovative approach to traditional RAG methods.
Vbj1808's Dokis project has gained some traction with a Growth Score of 2.30 and 34 stars. This lightweight RAG middleware verifies the provenance of claims in LLM responses without requiring an additional LLM call. Its growth suggests that users value tools that prioritize transparency and accountability.
McKern3l's RAGdrag toolkit rounds out our list, with a Growth Score of 1.76 and 25 stars. This pipeline security testing tool offers 27 techniques across six kill chain phases, making it a useful resource for those working in the field. Its slow growth may indicate that users are still exploring its capabilities.
Overall, Today's trends highlight the growing importance of RAG & Vector Databases in various applications, from AI document search to cyber threat intelligence analysis.