AI open source project

综合介绍 Memora是一个旨在为每个个性化AI复制人类记忆的代理。它通过时间戳记忆、情感标记和多模态记忆等功能，帮助AI像人类一样记住过去的互动细节、情感和共享经历。Memora支持多租户，能够处理...

综合介绍 Stagehand是一个专注于简洁性和可扩展性的AI网页浏览框架。它完全兼容Playwright，提供了三个简单的AI API（act、extract和observe），这些API构建在基础...

General Introduction Micro-Agent is an open source AI coding assistant developed by Builder.io, designed to provide developers with the ability to automatically generate and test code. It generates test cases by understanding natural language descriptions and iterates the code until all tests pass, thus reducing open...

General Introduction sherpa-onnx is an open source project developed by the Next-gen Kaldi team to provide efficient offline speech recognition and speech synthesis solutions. It supports multiple platforms including Android, iOS, Raspber...

综合介绍 EchoMimic 是一个开源项目，旨在通过音频驱动生成逼真的肖像动画。该项目由蚂蚁集团的终端技术部门开发，利用可编辑的标志点条件，结合音频和面部标志点生成动态的肖像视频。EchoMimic...

General Introduction Executive AI Assistant (EAIA) is an AI-based assistant tool designed to help users automate and manage their daily tasks. Developed by LangChain, the tool is capable of handling emails, scheduling, managing tasks and other...

综合介绍 Agent Inbox是由LangChain团队开发的一个开源项目，旨在提供一种新的用户体验，用于与AI智能体进行交互。该项目允许用户通过一个集中的界面管理和优化与多个AI智能体的交互。Ag...

General Introduction Kokoro 82M is an efficient speech synthesis model provided by Hugging Face, designed to generate high quality speech with fewer parameters and data. The model has 82 million parameters and is licensed under Apache 2.0...

General Introduction Audiblez is an open source project designed to convert eBooks (e.g. .epub format) into audiobooks (e.g. .m4b format). The project utilizes Kokoro's high-quality speech synthesis technology to support multiple languages and multiple voices. Users can simply...

Comprehensive Introduction Search-o1 is an open source project that aims to enhance the performance of large-scale reasoning models (LRMs) by integrating advanced search mechanisms. The core idea is to solve the knowledge deficit problem encountered in the reasoning process through dynamic search and knowledge integration. The project was developed by sunn...

General Introduction Transformers.js is a JavaScript library provided by Hugging Face designed to run state-of-the-art machine learning models directly in the browser without server support. The library works in conjunction with the Hugging Fa...

General Introduction MoneyPrinter V2 is an open source project developed by FujiwaraChoki to help users make money online through automation. The project mainly integrates Twitter automation, YouTube short video generation and affiliate camping...

General Introduction RTranslator is a virtually open source, free offline real-time translation app designed for Android devices. Users can keep their phone in their pocket by connecting a Bluetooth headset and have conversations with others as if they were speaking their own language.RTransla...

Comprehensive Introduction MiniPerplx (renamed Scira) is a minimalist designed AI-driven search engine that integrates a variety of useful features to provide users with a full range of information retrieval services. The project uses a modern technology stack including Next.js, Tailwi...

综合介绍 Gemini OpenAI API代理是一个免费且无需服务器维护的OpenAI兼容端点。用户可以轻松将其部署到Vercel、Netlify和Cloudflare等平台，适用于个人使用。该项目...

综合介绍 Gemini Next Chat 是一个开源项目，旨在帮助用户轻松部署私人Gemini应用。该项目支持Gemini 1.5和Gemini 2.0多模态模型，用户可以通过一键部署在Vercel...

综合介绍 AutoMouser 是一个 Chrome 扩展程序，能够智能地跟踪用户交互，并使用 OpenAI 的 GPT 模型自动生成 Selenium 测试代码。它通过记录用户的浏览器操作并将其转换...

Comprehensive Introduction SVFR (Stable Video Face Restoration) is a unified framework for video face restoration that supports Basic Face Restoration (BFR), colorization, repair, and their combination tasks. The framework utilizes generative and kinematic priors by unifying ...

Comprehensive introduction LiveTalking is an open source real-time interactive digital human system , is committed to building high-quality digital human live solution . The project uses the Apache 2.0 open source protocol and integrates a number of cutting-edge technologies , including ER-NeRF rendering , real-time audio and video streaming processing ...