Screenshot to Code: AI tool for converting screenshots to clean front-end code
综合介绍 Screenshot-to-Code 是一个开源工具，利用人工智能将截图、设计稿和 Figma 设计转换为干净、功能性的代码。该工具支持多种前端技术栈，包括 HTML、Tailwind CS...
Sorting
Paperless-AI: Automatically analyze and tag documents using AI for the paperless-ngx document management system.
综合介绍 Paperless-AI 是一个创新的文档自动化分析工具，专门为 Paperless-ngx 文档管理系统设计。它巧妙地结合了 OpenAI API 和 Ollama 等多种先进的人工智能模...
Agent.exe: Let AI control your computer directly, an open source implementation of Claude's control computer
综合介绍 Agent.exe 是一个开源的 Electron 应用程序，利用 Anthropic 的 Claude 3.5 Sonnet API，让用户可以通过 AI 直接控制本地计算机。该项目由 K...
Awesome CursorRules: rule sets to enhance the Cursor AI experience
综合介绍 awesome-cursorrules 是一个专门为 Cursor AI 提供自定义规则文件的项目。Cursor AI 是一个由人工智能驱动的代码编辑器，.cursorrules 文件可以定...
MathTranslate: LaTeX Translation Tool for Scientific Papers
General Introduction MathTranslate is an online tool specialized in translating LaTeX documents, especially for scientific papers. The tool is able to keep LaTeX expressions (e.g. mathematical expressions) unchanged and finally compiles LaTeX documents into...
Deep Live Cam: open source real-time AI face-swapping tool, a photo can realize real-time face-swapping live
General Introduction Deep Live Cam is an open source artificial intelligence tool designed to enable real-time face replacement and deep fake video generation from a single photo. The tool utilizes advanced deep learning algorithms to enable real-time face replacement in live streams or video calls, protecting user privacy and adding fun...
OmniGen: Unified Image Generation Model with Multimodal Inputs to Generate Character-Consistent Images
综合介绍 OmniGen 是一个由 VectorSpaceLab（智源） 开发的“通用”图像生成模型，允许用户通过简单的文本提示或多模态输入来创建多样化且具有上下文丰富的视觉效果。它特别适合于需要识别...
IOPaint: All-around AI image processing tool, erasing, expanding, replacing elements and drawing text.
综合介绍 IOPaint是一款免费且开源的AI图像处理工具，支持图像擦除、修复和扩展等功能。它采用最先进的AI模型，能够帮助用户轻松移除图像中的不需要对象、修复瑕疵、添加新内容，甚至扩大图像。IOPa...
MMAudio: generating synchronized sound effects and soundtracks for video footage, video-to-audio multimodal co-training tool
General Introduction MMAudio is an open-source project aiming to generate high-quality synchronized audio through joint multimodal training. Developed by Ho Kei Cheng et al. at the Chinese University of Hong Kong, the project's main function is to generate synchronized audio based on video and/or text input.MM...
MNN-LLM-Android: MNN Multimodal Language Model for Android Applications
综合介绍 MNN（Mobile Neural Network）是阿里巴巴开发的一个高效、轻量级的深度学习框架，专为移动端设备优化。MNN不仅能够在移动设备上进行快速推理，还支持多模态任务，包括文本生成...
TableGPT2: A Multimodal Model for Tabular Data Integration
综合介绍 TableGPT2是由浙江大学团队开发的一款多模态模型，专注于表格数据的集成和处理。该模型通过预训练和微调，能够在表格数据相关任务中表现出色，同时保持强大的通用语言和编码能力。TableGP...
GPT SoVITS: Revolutionary Speech Generation and Speech Cloning Tools
综合介绍 GPT-SoVITS是一款开源的语音转换与合成工具，结合了GPT模型和SoVITS变声器技术。该工具支持零样本与少量样本的即时文本转语音，仅需5秒音频样本即可实现声音风格迁移。其特色包括跨语...
Perplexica: an open source AI search engine that replicates Perplexity AI's features and interface 1 to 1
综合介绍 Perplexica 是一个开源的 AI 驱动搜索引擎，旨在提供深入互联网的答案。它使用先进的机器学习算法，如相似性搜索和嵌入技术，来优化搜索结果，并提供带有引用来源的清晰答案。Perple...
Langflow: a low-code tool for building powerful AI intelligences and workflows
General Introduction Langflow is a low-code tool designed for developers to build powerful AI agents and workflows. It supports the use of any API, model or database, simplifying the development of complex AI applications.Langflow provides an intuitive visual interface...
Kotaemon: simple to deploy open source multimodal document quiz tool
General Introduction Kotaemon is an open source document Q&A tool designed to provide end-users and developers with Q&A functionality based on Retrieval Augmented Generation (RAG). The project is developed by Cinnamon and supports a variety of LLM API providers (e.g. OpenA...
edge-tts: Text-to-Speech Python Module | Free Text-to-Speech Service
General Description edge-tts is an open source Python module that allows users to use Microsoft Edge's online text-to-speech service in Python code without the need for the Microsoft Edge browser, Windows operating system or API secret...
multi-model-bolt.new: open source modification based on Bolt.new, AI-driven full-stack development tools
综合介绍 multi-model-bolt.new 是一个基于 Bolt.new 的修改版本，允许使用 TogetherAI 模型，支持部署、移动响应和语音输入等功能。用户可以直接在浏览器中提示、运行...
CrisperWhisper: Accurate Verbatim Speech Transcription Tool
综合介绍 CrisperWhisper 是一个基于 OpenAI Whisper 的高级语音识别工具，专注于快速、精确和逐字的语音转录。它能够提供精确的单词级时间戳，甚至在语音填充和停顿的情况下也能准...
Open R1: Hugging Face Replicates the Training Process of DeepSeek-R1
综合介绍 Hugging Face的Open R1项目是一个完全开源的DeepSeek-R1复现项目，旨在构建R1管道的缺失部分，使每个人都能复现并在其基础上进行构建。该项目设计简单，主要包括训练和评...
English 
简体中文 
日本語 
한국어 
Español 
Deutsch 
Français 
Português do Brasil