Plate: AI-driven rich text editor with support for rich plugin extensions
综合介绍 Plate 是一个由 AI 驱动的富文本编辑器，基于 React 和 TypeScript 构建，旨在提供高度可定制和扩展的编辑体验。它利用 Slate.js 作为核心，结合了现代化的 UI...
Sorting
DisPose: generating videos with precise control of human posture, creating dancing ladies
综合介绍 DisPose是一个创新的开源人工智能项目，专注于可控的人物图像动画生成。该项目由研究团队开发并在GitHub上开源，采用先进的深度学习技术，通过分解骨骼姿态信息来实现精确的人物动画控制。D...
Zerox: PDF, DOCX, image conversion to Markdown, visual modeling high-precision OCR
Comprehensive introduction Zerox is an open source project designed to convert PDF, DOCX, images and other documents to Markdown format through visual modeling. The project is developed by getomni-ai team , provides a simple and efficient OCR (Optical Character Recognition) solution.Ze...
MaxKB: Out-of-the-box AI Knowledge Base Q&A System for Smart Customer Service and In-house Knowledge Base
综合介绍 MaxKB（Max Knowledge Base）是一款基于大语言模型和RAG（检索增强生成）的开源知识库问答系统。该系统广泛应用于智能客服、企业内部知识库、学术研究与教育等场景。MaxKB...
InsightExpress: generating AI-driven research reports and emailing them out
综合介绍 InsightExpress 是一个基于 Next.js 的应用程序，能够根据用户提供的主题生成 AI 驱动的研究报告，并通过电子邮件发送给用户。该应用程序利用 Langflow 的 AI ...
Babelfish.ai: Browser-Run Real-Time Speech Transcription and Translation Application
综合介绍 Babelfish.ai 是一个基于 Huggingface Transformer.js 和 Supabase Realtime 构建的实时转录和翻译应用。该应用可以在浏览器中加载大模型并...
Atomic Agents: a framework for building lightweight modular AI intelligences
综合介绍 Atomic Agents 是一个围绕原子性概念设计的极其轻量级和模块化的框架，用于构建代理AI管道和应用程序。该框架提供了一组工具和代理，可以组合创建强大的应用程序。它基于 Instruc...
Open NotebookLM: convert PDF to podcasts of open source tools
General Introduction Open NotebookLM is an open source project designed to convert any PDF document into a podcast. The tool utilizes open source Large Language Model (LLM) and Text-to-Speech (TTS) models to process PDF content and generate natural dialog suitable for audio podcasts...
Cosmos: World Base Model, a platform for building AI base models of the physical world
综合介绍 NVIDIA Cosmos 是一个面向开发者的世界基础模型平台，专门设计用于帮助物理人工智能开发者更好、更快地构建其物理人工智能系统。该平台提供了一系列预训练模型，包括基于扩散和自回归的世界...
Higress: Delivering an Efficient AI Gateway Solution to Simplify Microservice Management and Enhance Security
Comprehensive Introduction Higress is a cloud-native API gateway developed by Alibaba, built on Istio and Envoy, designed to provide efficient traffic scheduling, service governance and security solutions. It supports Wasm plugin extensions for multiple programming languages for AI business...
MiniRAG: Simplified Retrieval Enhanced Generation Framework, Entity Graph Index Recall Relevant Text Blocks
综合介绍 MiniRAG是一个极其简单的检索增强生成（RAG）框架，旨在通过异构图索引和轻量级拓扑增强检索，使小模型也能实现良好的RAG性能。该项目由香港大学数据科学实验室（HKUDS）开发，主要解决...
Lecca: Building AI Intelligentsia and AI Workflow Building Platforms without Code
Comprehensive Introduction Lecca is a powerful AI platform that allows users to configure and deploy Large Language Models (LLMs) with multiple tools and workflows. Users can easily build, customize and automate their AI agents.Lecca offers a wide selection of AI providers and models...
Agent Laboratory: automated code and study writing assistant for researchers
综合介绍 Agent Laboratory 是一个端到端的自主研究工作流，旨在帮助研究人员实现他们的研究想法。该系统由大型语言模型驱动的专用代理组成，支持整个研究工作流——从进行文献综述和制定计划到执...
VideoSeal: Advanced open source video hidden watermark embedding and extraction tools to protect video copyrights
综合介绍 VideoSeal是由Facebook Research开发的开源视频水印工具，旨在提供高效的视频水印嵌入与提取功能。该工具支持最新的开源模型，包含预训练模型、训练代码、推理代码和评估工具...
LlamaEdge: the quickest way to run and fine-tune LLM locally
综合介绍 LlamaEdge是一个开源项目，旨在简化本地或边缘设备上运行和微调大型语言模型（LLM）的过程。该项目支持Llama2系列模型，并提供与OpenAI兼容的API服务，使用户能够轻松创建和运...
AIEditor: Creating an AI-driven rich text editor with support for multiple front-end frameworks
综合介绍 AIEditor 是一个由 AI 驱动的下一代富文本编辑器，基于 Web Component 开发，支持 Vue、React、Angular 等几乎所有主流前端框架。它兼容 PC Web 和...
Pocket AI: offline AI assistant running in your phone, adapted for DeepSeek-R1 (5.37GB)
综合介绍 口袋AI（PocketPal AI 中文版）是一款强大的离线AI助手，旨在让用户随时随地与AI进行对话。该项目基于小型语言模型（SLMs），无需联网即可在手机上运行，特别适配中文用户体验。口...
LocalGPT: Ensure data privacy by talking to multiple documents on local devices
General Introduction LocalGPT is an open source project designed to allow users to talk to documents on local devices and ensure data privacy. By using a variety of open source models, LocalGPT can process and understand document content without uploading data to the cloud. The project supports a variety of p...
DeepSeek-VL2: an expert visual language model for advanced multimodal understanding
Comprehensive Introduction DeepSeek-VL2 is a series of advanced Mixture-of-Experts (MoE) visual language models that significantly improve the performance of its predecessor, DeepSeek-VL. The models are useful in visual question and answer, optical character recognition, text...
English 
简体中文 
日本語 
한국어 
Español 
Deutsch 
Français 
Português do Brasil