AI open source project

综合介绍 它能自动分析PDF文档的布局，识别页面中的文字、标题、图片、表格、公式等元素，并判断它们的正确顺序。工具支持OCR功能，可以把扫描PDF转为可搜索文本。它基于Docker运行，提供两种模型...

Comprehensive Introduction Dolphin is an open source model developed by DataoceanAI and Tsinghua University, focusing on speech recognition and language recognition for Asian languages. It supports 40 languages in East Asia, South Asia, Southeast Asia, and the Middle East, as well as 22 Chinese dialects...

综合介绍 AstrBot 是一个开源的聊天机器人开发框架，它支持 QQ、Telegram、微信等多种消息平台，并能轻松接入 OpenAI、DeepSeek、Google Gemini 等大语言模型（L...

综合介绍 WeClone 是一个开源项目，它通过微信聊天记录和语音消息，结合大语言模型和语音合成技术，让用户创建个性化的数字分身。项目能分析用户的聊天习惯来训练模型，还可以用少量语音样本生成逼真的声音...

综合介绍 DiffPortrait360 是一个开源项目，隶属于 CVPR 2025 论文《DiffPortrait360: Consistent Portrait Diffusion for 360...

General Introduction Text2Voice is an open source tool that provides text-to-speech functionality based on a silicon-based mobility API, and is best characterized as coming with a clean graphical user interface (GUI). It was created by developer Sheldon Lee on GitHub to allow...

综合介绍 mcp-ui 是一个开源项目，由开发者 machaojin1917939763 创建，基于 Model Context Protocol（MCP）协议打造，是一款支持 Web 和桌面环境的智...

综合介绍 Comp AI 是一个开源平台，由 Comp AI, Inc. 开发，总部位于美国旧金山。它帮助企业通过自动化工具快速完成 SOC 2、ISO 27001 和 GDPR 等合规要求，目标是几...

综合介绍 RolmOCR 是由 Reducto AI 团队开发的一款开源光学字符识别（OCR）工具，基于 Qwen2.5-VL-7B 视觉语言模型。它能从图片和 PDF 文件中提取文字，速度比同类工具...

General Introduction AiryLark is an open source document processing and translation tool hosted on GitHub and built by developer wizd based on the Next.js framework. It supports a variety of file formats (such as PDF, Word, TXT, Markdo...

General Introduction Zola is a free and open source AI chat application developed by developer Julien Thibeaut (GitHub username ibelick) and hosted on GitHub. Its best feature is that it supports multiple AI modes...

Comprehensive Introduction DeepResearcher is an open source project developed by the GAIR-NLP team at Shanghai Jiao Tong University. It is an intelligent research tool based on Large Language Models (LLMs), trained end-to-end in real web environments through Reinforcement Learning (RL). The project ...

AnimeGamer is an open source tool launched by Tencent ARC Lab. Users can generate anime videos with simple language commands, such as "Sousuke drive around in a purple car", as well as allow different anime characters to interact with each other, such as Kiki from The Witch's House, and Sky City...

General Introduction Lumina-mGPT-2.0 is an open source project jointly developed by Shanghai AI Laboratory (Shanghai AI Laboratory), The Chinese University of Hong Kong (CUHK) and other organizations, hosted on GitHub by Alpha...

General Introduction Aider is a powerful open source AI programming assistant tool that helps developers write, edit and refactor code through natural language conversations. As an interactive AI pair programming tool, Aider supports many major programming languages and can be seamlessly integrated into Git...

General Introduction Agent S is an open-source framework developed by Simular AI that lets intelligences operate computers like humans through a graphical user interface (GUI). It uses a multimodal large language model and empirical learning techniques to accomplish tasks such as browsing the web, editing documents, using software...

General Introduction FreeAI is an open source AI application platform based on the Pollinations.AI API, providing free and unlimited AI chat assistants, image generation and speech synthesis services. The project was started by developer Azad-sl in G...

General Introduction Open WebUI Artifacts Overhaul is a fork project based on Open WebUI, developed by developer Nick Tonjum. It is an open source tool focused on improving AI generated code...

Synthesis Gaze-LLE is a gaze target prediction tool based on a large-scale learning encoder. It was developed by Fiona Ryan, Ajay Bati, Sangmin Lee, Daniel Bolya, Judy Hoffman, and J...