Midscene.js: Open Source Plugin for Automated Browser Testing Driven by AI
综合介绍 Midscene.js是一个由AI驱动的浏览器自动化工具，能够通过自然语言指令来控制网页、执行断言和提取数据。它支持Chrome扩展、JavaScript SDK和YAML脚本，简化了UI测...
Sorting
Video Analyzer: analyzes video content and generates detailed descriptions
Comprehensive Introduction Video Analyzer (Video Analyzer) is a comprehensive video analysis tool that combines computer vision, audio transcription and natural language processing techniques to generate detailed video content descriptions. The tool transcribes audio content by extracting key frames in the video...
Unsloth: an open source tool for efficiently fine-tuning and training large language models
综合介绍 Unsloth 是一个开源项目，旨在提供高效的微调和训练大语言模型（LLMs）的工具。该项目支持多种知名模型，包括 Llama、Mistral、Phi 和 Gemma 等。Unsloth 的...
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...
OmniThink: a writing framework for generating high-quality long articles, searching for external knowledge and then reflecting on it and building a knowledge tree step by step
综合介绍 OmniThink 是一个创新的机器写作框架，旨在通过模拟人类认知过程中的迭代扩展和反思，生成高质量的长篇文章。该框架专注于扩展知识边界，生成的信息丰富且具有深度。OmniThink 通过构...
OpenAI Realtime Agents: A Multi-Intelligent Body Speech Interaction Application (OpenAI Example)
综合介绍 OpenAI Realtime Agents是一个开源项目，旨在展示如何利用OpenAI的实时API来构建多智能体的语音应用。它提供了高级的智能体模式（借鉴 OpenAI Swarm），允许...
DeepFace: a lightweight Python library that implements facial age, gender, emotion, race recognition
综合介绍 DeepFace是一个轻量级的面部识别和面部属性分析（包括年龄、性别、情绪和种族）的Python库。它集成了多种先进的面部识别模型，如VGG-Face、FaceNet、OpenFace、De...
SynthLight: natural light rendering of portrait images (unreleased)
综合介绍 SynthLight 是一个基于扩散模型的肖像重光照工具。它通过学习重新渲染合成的人脸图像，实现对真实肖像照片的光照效果调整。该工具利用物理渲染引擎生成数据集，模拟不同光照条件下的光照转换...
1-2-1-MNVTON: Efficient images, virtual trying on of clothes by people in videos (to be opened)
General Introduction 1-2-1-MNVTON is a GitHub-based open source project that aims to provide "Modality-specific Normalization for Virtual Try-On" (MNVTON) technology through...
Kokoro-ONNX: Efficient Text-to-Speech Tool with Multi-Language and Multi-Voice Support
General Introduction Kokoro-ONNX is an open source text-to-speech (TTS) tool based on ONNX runtime. Developed by thewh1teagle, the project aims to provide efficient and fast speech synthesis solutions.Kokoro-ONNX supports ...
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...
Charla: a minimalist endpoint-based AI chat tool with native integration to the Ollama backend
综合介绍 Charla 是一个基于终端的聊天应用程序，旨在与本地语言模型进行对话。该应用程序集成了 Ollama 后端，支持上下文感知的对话，并将聊天会话保存为 Markdown 文件。用户可以通过简...
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...
Omni-RGPT: A Multimodal Large Model for Image and Video Region-Level Understanding to Enhance Visual Content Analysis
综合介绍 Omni-RGPT 是一个多模态大语言模型，旨在实现图像和视频的区域级理解。通过引入 Token Mark 技术，Omni-RGPT 能够在视觉特征空间内高亮目标区域，并通过区域提示（如框或...
Bailing: a low-latency open source voice dialog assistant that easily realizes natural conversational exchanges
综合介绍 百聆（Bailing）是一个开源的语音对话助手，旨在通过语音与用户进行自然的对话。该项目结合了语音识别（ASR）、语音活动检测（VAD）、大语言模型（LLM）和语音合成（TTS）技术，实现了...
MetaWorld AI: Open Source Version of AI Digital Human Cloning and Short Video Generation Tool
Comprehensive Introduction Metaverse AI (open source version) is a project hosted on GitHub, developed by libn-net team. It can clone digital human images and voices through AI technology to generate short videos, and also supports dubbing and subtitling. This tool provides Windo...
WikiChat: A Chat Tool for Retrieving Knowledge Using Wikipedia Data
综合介绍 WikiChat是由斯坦福大学开发的一款实验性聊天机器人，旨在通过从维基百科检索数据来提高大语言模型的事实性。大语言模型（如ChatGPT和GPT-4）在处理最新信息或不太流行的话题时，往往...
OpenAI Edge TTS: Free text-to-speech API utilizing Edge TTS, compatible with OpenAI formats
General Introduction OpenAI Edge TTS is an open source project that provides an OpenAI-compatible native text-to-speech (TTS) API.The project uses Microsoft Edge's online text-to-speech service to allow users to generate high-quality...
AIEvo: An Efficient Framework for Creating Multi-Intelligent Collaborative Applications
综合介绍 AIEvo是蚂蚁集团开源的多代理框架，旨在高效创建多代理应用。该框架严格遵循SOP任务图，提升复杂任务的执行成功率，并通过反馈和监控机制确保高灵活性和可扩展性。AIEvo已在蚂蚁集团内部生产...
English 
简体中文 
日本語 
한국어 
Español 
Deutsch 
Français 
Português do Brasil