AI open source project

General Introduction SegAnyMo is an open source project developed by a team of researchers at UC Berkeley and Peking University, including members such as Nan Huang. This tool focuses on video processing and can automatically recognize and segment arbitrary moving objects in a video, such as people, animals or...

General Introduction GenXD is an open source project, developed by the National University of Singapore (NUS) and Microsoft team. It focuses on generating arbitrary 3D and 4D scenes , to solve the real-world 3D and 4D generation due to insufficient data and model design complexity brought about by the problem . The project was developed by ...

General Introduction ChatAnyone is an innovative project developed by the HumanAIGC team. It utilizes artificial intelligence techniques to generate digital human portrait videos with upper body movements from a single photo and audio input. The project is based on a hierarchical motion diffusion model that generates head movements...

综合介绍 Search-R1 是一个开源项目，由 PeterGriffinJin 在 GitHub 上开发，基于 veRL 框架构建。它通过强化学习（RL）技术训练大语言模型（LLM），让模型自主学会...

综合介绍 DeepGemini 是一个开源项目，由开发者 Thomas Sligter 创建。它是一个支持多模型编排的 AI 管理工具，主要特点是能灵活组合多种 AI 模型，并通过 OpenAI 兼容...

综合介绍 Optexity 是一个在 GitHub 上开源的项目，由 Optexity 团队开发。它的核心是用人类演示数据训练 AI 完成计算机任务，尤其是网页操作。项目包含三个代码库：Compute...

General Introduction II-Researcher is an open source artificial intelligence research tool developed by the Intelligent-Internet team and hosted on GitHub.It is designed for deep search and complex reasoning, with the ability to search through intelligent web pages and multi-step sub...

综合介绍 Cua 是一个开源项目，全称“Computer-Use Agent”（计算机使用代理），读作“koo-ah”。它专为 Apple Silicon 设备设计，能创建并运行高性能的 macOS ...

综合介绍 Paper to Podcast 是一个开源工具，专门把学术研究论文转化为生动有趣的播客。它通过人工智能技术，将 PDF 格式的论文变成三个角色——主持、学习者和专家——之间的对话，让复杂的...

综合介绍 Anubis 是一个由 TecharoHQ 团队开发的开源工具，主要用来保护网站免受 AI 爬虫的侵扰。它在 HTTP 请求中加入 SHA256 工作量证明（Proof-of-Work）挑战...

综合介绍 OmniSQL 是一个开源项目，由 RUCKBReasoning 团队开发，托管在 GitHub 上。它的核心功能是将用户输入的自然语言问题转化为高质量的 SQL 查询语句，帮助用户轻松与数...

General Introduction LatentSync is an open source tool developed by ByteDance and hosted on GitHub. It drives the lip movements of characters in a video directly through audio, allowing the mouth shape to match the voice precisely. The project is based on Stable Di...

综合介绍 Morphik Core 是一个开源项目，由 morphik-org 团队开发，托管在 GitHub 上。它以前叫 DataBridge Core，现在更名为 Morphik Core。这个...

综合介绍 serverless-markdown-convertor 是一个免费的开源工具，基于 Cloudflare Worker 和 Workers AI 开发，能将多种文件转换为 Markdow...

综合介绍 EditorJumper 是一个专为 JetBrains IDE 设计的插件，由 GitHub 用户 wanniwa 开发。它能让开发者在 JetBrains IDE（如 IntelliJ ...

VirtualWife is an open source virtual digital person project created by developer yakami129. It is currently in the incubation stage, the goal is to create a virtual character with a "soul", the user can interact with it like a friend. The project is supported by B Station Live...

综合介绍 GPT-Crawler 是由 BuilderIO 团队开发的一个开源工具，托管在 GitHub 上。它通过输入一个或多个网站 URL，爬取页面内容，生成结构化的知识文件（output.jso...

Comprehensive Introduction MegaTTS3 is an open source speech synthesis tool developed by ByteDance in cooperation with Zhejiang University, focusing on generating high-quality Chinese and English speech. Its core model is only 0.45B parameters , lightweight and efficient , support for mixed Chinese and English speech generation and speech cloning . The project is hosted on ...

综合介绍 KBLaM 是微软开发的一个开源项目，全称是“Knowledge Base augmented Language Model”（知识库增强语言模型）。它通过将外部知识转化为向量并嵌入大模型的...