AI open source project

综合介绍 LongWriter是由清华大学数据挖掘研究组（THUDM）开发的一款强大的长文本生成工具。该工具基于先进的长上下文语言模型（LLM），能够生成超过10000字的长文本。LongWriter...

综合介绍 Plate 是一个由 AI 驱动的富文本编辑器，基于 React 和 TypeScript 构建，旨在提供高度可定制和扩展的编辑体验。它利用 Slate.js 作为核心，结合了现代化的 UI...

General Introduction MuseGAN is a music generation project based on Generative Adversarial Networks (GANs) designed to generate multi-track (multi-instrument) music. The project is capable of generating music from scratch or accompanied by user-supplied tracks.MuseGAN uses Lakh Pianor...

综合介绍 Docling 是一个强大的文档解析和导出工具，支持多种文档格式，包括 PDF、DOCX、PPTX、XLSX、图像、HTML、AsciiDoc 和 Markdown。它能够将这些文档解析并导...

综合介绍 MockingBird 是一个开源项目，旨在通过 AI 技术实现快速语音克隆和文本转语音。用户只需提供 5 秒的语音样本，即可生成任意语音内容。该项目支持多种中文数据集，并在 Windows...

综合介绍 Zed 是由 Atom 和 Tree-sitter 的创造者开发的一款高性能、多用户协作的代码编辑器。Zed 采用 Rust 语言编写，旨在提供快速、流畅的编码体验。其主要特点包括支持多人实...

Comprehensive Introduction PaddleOCR is a multilingual OCR toolkit based on PaddlePaddle, designed to provide a practical and ultra-lightweight OCR system. It supports the recognition of more than 80 languages and provides data annotation and synthesis tools to support the service...

General Introduction ControlFlow is a Python framework developed by PrefectHQ focused on building and managing AI workflows. It provides a structured, developer-oriented framework for defining workflows and delegating tasks to Large Language Model (LLM) generation...

Comprehensive Introduction ConsisID is an open source project developed by Yuan Rong's group at Peking University, aiming to realize identity-consistent text-to-video generation (IPT2V) through frequency decomposition techniques. The core of the project is a DiT (Diffusion Transfor...

综合介绍 GraphRAG Visualizer 是一个基于网页的工具，旨在帮助用户可视化和探索来自 Microsoft GraphRAG 的工件。通过上传由 GraphRAG 索引管道生成的 Par...

综合介绍 Crawlee 是一个由 Apify 开发的开源网络爬虫和浏览器自动化库，专为 Node.js 环境设计。它支持 JavaScript 和 TypeScript，能够与 Puppeteer...

综合介绍 观察者（Observers）是一个开源的Python SDK，旨在为生成式AI API提供全面的可观测性。该库使用户能够轻松跟踪和记录与AI模型的交互，并将这些观察结果存储在多个后端中。无论...

综合介绍 TRELLIS是一个由Microsoft开发的大型3D资产生成模型。它能够接收文本或图像提示，并生成各种格式的高质量3D资产，如辐射场、3D高斯和网格。TRELLIS的核心是统一的结构化潜在...

综合介绍 GraphCast是由Google DeepMind开发的一个先进的天气预报工具，旨在通过深度学习技术提升中期全球天气预报的准确性。该项目提供了多种预训练模型和示例代码，用户可以利用这些资源...

Comprehensive Introduction Bambo is a new type of proxy framework, which is lighter and more flexible than the mainstream frameworks and can handle a variety of load tasks.Bambo achieves efficient proxy functionality by defining all the tools in the tool catalog and using asynchronous custom functions. Users can use the llm_c...

综合介绍 Marco-o1是由阿里巴巴国际数字商业集团（AIDC-AI）开发的开放式推理模型，旨在解决复杂的现实世界问题。该模型结合了思维链（CoT）微调、蒙特卡洛树搜索（MCTS）和创新的推理策略...

Comprehensive Introduction Laminar is an open source AI engineering optimization platform focused on AI engineering from first principles. It helps users collect, understand, and use data to improve the quality of LLM (Large Language Model) applications.Laminar provides comprehensive observability, text...

Comprehensive Introduction Flow is a lightweight task engine designed for building AI agents, emphasizing simplicity and flexibility. Unlike traditional node- and edge-based workflows, Flow uses a dynamic task queuing system that supports parallel execution, dynamic scheduling, and intelligent dependency management. Its core concept is ...

General Description Translation Agent WebUI is a Gradio-based web user interface designed for Andrewyng's translation-agent. The tool is able to automatically detect the transmission...