Stars
结合LightRAG 知识库的知识图谱智能体平台。 An agent platform that integrates a LightRAG knowledge base and knowledge graphs. Build with LangChain v1 + Vue + FastAPI, support DeepAgents、MinerU PDF、Neo4j 、MCP.
The absolute trainer to light up AI agents.
A production-ready runtime framework for agent apps with secure tool sandboxing, Agent-as-a-Service APIs, scalable deployment, full-stack observability, and broad framework compatibility.
FISCO BCOS（发音为/ˈfɪskl bi:ˈkɒz/）是一个稳定、高效、安全的许可区块链平台，已被广泛应用于现实的行业应用。截至目前，已拥有5000多家企事业单位，400多个产业数字化标杆应用，涵盖文化版权、司法服务、政府服务、物联网、金融、智慧社区、房地产建设、社区治理、乡村振兴等领域。FISCO BCOS (pronounced /ˈfɪskl bi:ˈkɒz/) is a st…
Open Source Landscapes and Insights Produced by AntOSS
A simple yet powerful agent framework that delivers with open-source models
[EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
A lightweight LMM-based Document Parsing Model
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
Minimalistic 4D-parallelism distributed training framework for education purpose
Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website …
An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the si…
Witness the aha moment of VLM with less than $3.
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
[CVPR 2024] DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis
The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curatio…
This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, s…
Tile primitives for speedy kernels
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.