Skip to content

@OpenDCAI OpenDCAI

All

    Repositories list

    46 repositories

    • gugu

      Public
      Gugu (咕咕): personal assistant, chat and device client — source release
      electronchatpersonal-assistant
      electronchatpersonal-assistantcapacitorsupabaseai-agent
      TypeScript
      •
      Other
      •21•79•120•19•Updated Oct 30, 2026Oct 30, 2026

    • gugu-supabase

      Public
      Gugu community backend on Supabase: identity, messaging, sync, device permissions and file services
      chatpostgresbackend
      chatpostgresbackendsupabaseai-agent
      PLpgSQL
      •
      Other
      •0•6•14•1•Updated Oct 30, 2026Oct 30, 2026

    • DataFlow

      Public
      [SIGMOD'27] Easy Data Preparation with latest LLMs-based Operators and Pipelines.
      data-sciencedataoperators
      data-sciencedataoperatorsdata-processingdata-pipelinesdata-cleaningdata-synthesisgradio-interfacellmsdata-agent
      Python
      •
      Apache License 2.0
      •1.2k•8.4k•13•19•Updated Oct 30, 2026Oct 30, 2026

    • GameFactory-3A

      Public
      A comprehensive open-source 3A game-generation skill and asset framework.
      blenderunity3dimage-generation
      blenderunity3dimage-generationunreal-enginethree-js3d-generationmotion-generationaudio-generation3a-gamecg-video-generation
      Python
      •
      Apache License 2.0
      •102•979•8•2•Updated Oct 29, 2026Oct 29, 2026

    • OpenWorldLib

      Public
      Unified Codebase for Advanced World Models.
      simulatorvideo-editingvla
      simulatorvideo-editingvlavlmworld-modelsdiffusion-models3d-scene-generationworld-modelgaussian-splattingvggt
      Python
      •
      Apache License 2.0
      •55•889•6•0•Updated Oct 29, 2026Oct 29, 2026

    • DataMind

      Public
      All-in-one intelligent assistant powered by LlamaIndex — RAG, GraphRAG, NL2SQL, Skills & Memory with multimodal support.
      datadatabaseskills
      datadatabaseskillsmemorydata-preparationraggraphrag
      Python
      •
      Apache License 2.0
      •59•456•1•2•Updated Oct 23, 2026Oct 23, 2026

    • DataFlex

      Public
      [NeurIPS 2026] DataFlex: A Unified Benchmark and Evaluation Platform for Data-Centric Training of Large Language Models
      data-sciencedatamodel-training
      data-sciencedatamodel-trainingdata-selectiondata-mixturedata-reweightingdata-model-interaction
      Python
      •
      Apache License 2.0
      •499•3.3k•1•2•Updated Oct 21, 2026Oct 21, 2026

    • Dataflow-LoopAI

      Public
      Dataflow-LoopAI is an intelligent system with self-optimization capabilities that automatically detects and evaluates generation deficiencies in LLMs within spe…
      loop-optimizationself-evolvingcodex-sdk
      loop-optimizationself-evolvingcodex-sdkloop-engineering
      Python
      •
      Apache License 2.0
      •4•29•0•0•Updated Oct 8, 2026Oct 8, 2026

    • RayOrch

      Public
      Ray-native programming and execution of lineage-controlled, multi-grain dataflows for scalable multimodal data preparation. 基于 Ray 编程与执行血缘控制的多粒度数据流，面向可扩展的多模态数据准…
      data-infrainferenceray
      data-infrainferenceraymllms
      Python
      •
      Apache License 2.0
      •8•19•0•2•Updated Sep 29, 2026Sep 29, 2026

    • Flash-MinerU

      Public
      Ray-powered accelerator for MinerU, turning PDF → Markdown into a scalable, cluster-ready data infrastructure. 基于 Ray 的 MinerU 加速层，将 PDF → Markdown 构建为可扩展、面向集群的…
      pdfparallel-computingdistributed-computing
      pdfparallel-computingdistributed-computingraymulti-gpupdf-parsingdocument-aillm-inferenceminerupdf2markdown
      Python
      •
      Other
      •6•72•4•0•Updated Sep 28, 2026Sep 28, 2026

    • RayOrch-doc

      Public
      Apache License 2.0
      •1•0•0•0•Updated Sep 28, 2026Sep 28, 2026

    • TrajWeave

      Public
      Python
      •
      Apache License 2.0
      •0•4•0•0•Updated Sep 27, 2026Sep 27, 2026

    • DataFlow-MultiAgent

      Public
      Python
      •1•1•0•0•Updated Sep 22, 2026Sep 22, 2026

    • DataFlow-AgentMM

      Public
      A framework for collecting and evaluating multimodal agent trajectories in visual environments.
      Python
      •
      Apache License 2.0
      •0•23•0•0•Updated Sep 22, 2026Sep 22, 2026

    • DataFlow-Agent

      Public
      Python
      •3•13•0•0•Updated Sep 18, 2026Sep 18, 2026

    • DataMind-Doc

      Public
      Documentation site for DataMind
      Python
      •0•0•0•0•Updated Sep 12, 2026Sep 12, 2026

    • ThinkFlow

      Public
      An Open Source implementation of Notebook LM.
      Python
      •
      Apache License 2.0
      •24•79•4•6•Updated Sep 11, 2026Sep 11, 2026

    • One-Eval

      Public
      Automated system for LLM evaluation via agents. Doc as below:
      agentdata-sciencedata
      agentdata-sciencedatabenchmarkevaluationdata-analysisagentsllmllmsvllm
      Python
      •
      Apache License 2.0
      •29•163•1•1•Updated Aug 31, 2026Aug 31, 2026

    • Paper2Any

      Public
      Turn paper/text/topic into editable research figures, technical route diagrams, and presentation slides.
      agentaippt-generator
      agentaippt-generatorlanggraphaipptpaper2slideseditable-pptx
      Python
      •
      Apache License 2.0
      •197•2.8k•4•4•Updated Aug 31, 2026Aug 31, 2026

    • DataFlow-WebUI

      Public
      An NL2Pipeline Harness for building AI-ready data workflows.
      Python
      •
      Apache License 2.0
      •67•254•2•1•Updated Aug 26, 2026Aug 26, 2026

    • .github

      Public
      0•0•0•0•Updated Aug 5, 2026Aug 5, 2026

    • DataFlow-KG

      Public
      DataFlow Knowledge Graph -- Knowledge graph data preparation with DataFlow style operators and pipelines
      Python
      •
      Apache License 2.0
      •4•45•0•0•Updated Jun 30, 2026Jun 30, 2026

    • DataFlow-Doc

      Public
      Documentation for DataFlow, Data-centric AI system for LLM.
      Python
      •32•12•4•1•Updated Jun 25, 2026Jun 25, 2026

    • Mycel

      Public
      Connect people, agents, and teams for the next era of human-AI collaboration.
      Python
      •
      MIT License
      •11•113•1•3•Updated Jun 25, 2026Jun 25, 2026

    • OpenResearchFlow

      Public
      Python
      •
      MIT License
      •2•17•0•0•Updated Jun 21, 2026Jun 21, 2026

    • Data-Preparation-Bench

      Public
      A unified, downstream-grounded benchmark for LLM-driven training data construction, selection, and quality evaluation.
      Python
      •27•241•2•1•Updated Jun 20, 2026Jun 20, 2026

    • SciReasoner

      Public
      Python
      •
      GNU General Public License v3.0
      •1•9•0•0•Updated May 20, 2026May 20, 2026

    • RARE

      Public
      Official repository of RARE: Retrieval-Augmented Reasoning Modeling [KDD 2026 Research Track]
      Python
      •
      Apache License 2.0
      •31•185•0•0•Updated May 20, 2026May 20, 2026

    • DataFlex-Doc

      Public
      DataFlex is a data-centric training framework that enhances model performance by either selecting the most influential samples, optimizing their weights, or adj…
      data-sciencedatamodel-training
      data-sciencedatamodel-trainingdata-selectiondata-mixturedata-reweighting
      Python
      •7•5•0•0•Updated May 13, 2026May 13, 2026

    • OpenPrism

      Public
      Open-source implementation of AI-powered academic writing workspace inspired by OpenAI Prism, featuring LaTeX editing, PDF preview, and intelligent AI assistanc…
      latexacademic-writingacademic-writing-analytics
      latexacademic-writingacademic-writing-analyticswriting-assistantopenai-prism
      TypeScript
      •44•381•5•4•Updated May 12, 2026May 12, 2026
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.