OpenDCAI

[SIGMOD'27] Easy Data Preparation with latest LLMs-based Operators and Pipelines.

[NeurIPS 2026] DataFlex: A Unified Benchmark and Evaluation Platform for Data-Centric Training of Large Language Models

Turn paper/text/topic into editable research figures, technical route diagrams, and presentation slides.

A comprehensive open-source 3A game-generation skill and asset framework.

Unified Codebase for Advanced World Models.

All-in-one intelligent assistant powered by LlamaIndex — RAG, GraphRAG, NL2SQL, Skills & Memory with multimodal support.

Open-source implementation of AI-powered academic writing workspace inspired by OpenAI Prism, featuring LaTeX editing, PDF preview, and intelligent AI assistance

An NL2Pipeline Harness for building AI-ready data workflows.

A unified, downstream-grounded benchmark for LLM-driven training data construction, selection, and quality evaluation.

Official repository of RARE: Retrieval-Augmented Reasoning Modeling [KDD 2026 Research Track]

Automated system for LLM evaluation via agents. Doc as below:

The First Unified Agent Data Synthesis Framework for Custom Agentic Task with all-in-one envrionment

Connect people, agents, and teams for the next era of human-AI collaboration.

Official implementation of Text2VectorSQL: Towards a Unified Interface for Vector Search and SQL Queries

An Open Source implementation of Notebook LM.

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、面向集群的数据基础设施。

Dataflow-MM, multi-media operators for Dataflow. We aim to prepare data for Multimodal Large Language Models.