OSS Radar
SponsorYour product here, sponsor OSS Radar →

Trending RAG / vector repos

Retrieval-augmented generation, vector databases, embeddings and search.

OSS Radar tracks 12 RAG / vector repos that together gained about 6.3k stars in the last 7 days. Leading this week: HKUDS/DeepTutor, deeplethe/utopia and infiniflow/ragflow.

est. means the star gain is estimated, not measured: until OSS Radar has collected enough daily snapshots for a repo, we use total stars ÷ days since creation (or extrapolate from the snapshots we do have). Estimates are replaced by measured deltas automatically as history builds up.

  1. 1
    HKUDS/DeepTutor

    DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/. Why it matters: relevant for grounding LLMs in your own data.

    RAG / vectorPython★ 41k

    +143est.

    stars / 24h

  2. 2
    deeplethe/utopia

    World's first open-source enterprise world model. Why it matters: relevant for grounding LLMs in your own data.

    RAG / vectorRust★ 8.3k

    +125est.

    stars / 24h

  3. 3
    infiniflow/ragflow

    RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior… Why it matters: relevant for grounding LLMs in your own data.

    RAG / vectorGo★ 92k

    +89est.

    stars / 24h

  4. 4
    RyanCodrai/turbovec

    A vector index built on TurboQuant, written in Rust with Python bindings. Why it matters: relevant for grounding LLMs in your own data.

    RAG / vectorRust★ 17k

    +86est.

    stars / 24h

  5. 5
    StarTrail-org/PixelRAG

    https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/. Why it matters: relevant for grounding LLMs in your own data.

    RAG / vectorPython★ 10k

    +75est.

    stars / 24h

  6. 6
    ConardLi/garden-skills

    ConardLi's open-source Skills collection, featuring web design, knowledge retrieval, image generation, and more. Why it matters: relevant for grounding LLMs in your own data.

    RAG / vectorCSS★ 13k

    +73est.

    stars / 24h

  7. 7
    VectifyAI/PageIndex

    PageIndex: Document Index for Vectorless, Reasoning-based RAG. Why it matters: relevant for grounding LLMs in your own data.

    RAG / vectorPython★ 39k

    +70est.

    stars / 24h

  8. 8
    opendataloader-project/opendataloader-pdf

    PDF Parser for AI-ready data. Automate PDF accessibility. Open-source. Why it matters: relevant for grounding LLMs in your own data.

    RAG / vectorJava★ 30k

    +57est.

    stars / 24h

  9. 9
    HKUDS/LightRAG

    [EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation. Why it matters: relevant for grounding LLMs in your own data.

    RAG / vectorPython★ 40k

    +54est.

    stars / 24h

  10. 10
    alibaba/zvec

    A lightweight, lightning-fast, in-process vector database. Why it matters: relevant for grounding LLMs in your own data.

    RAG / vectorC++★ 16k

    +52est.

    stars / 24h

  11. 11
    microsoft/graphrag

    A modular graph-based Retrieval-Augmented Generation (RAG) system. Why it matters: relevant for grounding LLMs in your own data.

    RAG / vectorPython★ 36k

    +39est.

    stars / 24h

  12. 12
    NirDiamant/RAG_Techniques

    This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook… Why it matters: relevant for grounding LLMs in your own data.

    RAG / vectorJupyter Notebook★ 30k

    +36est.

    stars / 24h

Other categories