The glamourous AI coding agent for your favourite terminal 💘

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

Multilingual Document Layout Parsing in a Single Vision-Language Model

一个通用的深度智能体Python框架，适合想深入研究和开发复杂Agent的开发者。

A TTS model capable of generating ultra-realistic dialogue in one pass.仅限英文

MAGI-1: Autoregressive Video Generation at Scale

FULL v0, Cursor, Manus, Same.dev, Lovable, Devin, Replit Agent, Windsurf Agent & VSCode Agent (And other Open Sourced) System Prompts, Tools & AI Models.

Suna - Open Source Generalist AI Agent

LLMxMapReduce

The ultimate LLM/AI application development framework in Golang.

Lightweight coding agent that runs in your terminal

Awesome curated collection of GPT-4o images & prompts. Explore diverse AI-generated art styles (Ghibli, 3D, etc.) from OpenAI's latest model.

SkyReels-V2: Infinite-length Film Generative model

🇨🇳 Chinese sticker pack,More joy / 表情包的博物馆, Github最有毒的仓库, 中国表情包大集合, 聚欢乐~

Lets make video diffusion practical!

Visual testing tool for MCP servers

前两天在 AI 社区掀起热潮的 AI 控制手机工具：DroidRun 已经正式开源了！

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

⚡ TabPFN: Foundation Model for Tabular Data ⚡

Smart glasses OS, with dozens of built-in apps. Users get AI assistant, notifications, translation, screen mirror, captions, and more. Devs get to write 1 app that runs on any pair of smart glases.

Implementation of "EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer"

SkyReels-A2: Compose anything in video diffusion transformers

GitHub's official MCP Server

Dolphin is a multilingual, multitask ASR model jointly trained by DataoceanAI and Tsinghua University.

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

提取微信聊天记录，将其导出成HTML、Word、Excel文档永久保存，对聊天记录进行分析生成年度聊天报告，用聊天数据训练专属于个人的AI聊天助手

volcengine/ai-app-lab

说一下这个模型，这个是基于qwen-2.5微调的一个金融领域推理模型，是上海财经大学统计与数据科学学院张立文教授领衔主导的一个项目，据他们自己发的测评结果7B模型的结果和deepdeek-R1满血版成绩基本接近

A Conversational Speech Generation Model

Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.