Starred repositories
ALLWEONE® Open source AI presentation generator Gamma Alternative. Create professional slides with customizable themes and AI-generated content in minutes.
A multi-platform proxy client based on ClashMeta,simple and easy to use, open-source and ad-free.
Automate your mobile devices with natural language commands - an LLM agnostic mobile Agent 🤖
An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone
Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently. By capturing real-time visual data and consolidating it into structured mem…
🎥 Make videos programmatically with React
The official rendering library for PAG (Portable Animated Graphics) files that renders After Effects animations natively across multiple platforms.
Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.
The official Python library for the OpenAI API
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
[NeurIPS 2025] PyTorch implementation of [ThinkSound], a unified framework for generating audio from any modality, guided by Chain-of-Thought (CoT) reasoning.
A fast video processing library based on node.js (一个基于node.js的高速视频制作库)
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors
[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling
Build effective agents using Model Context Protocol and simple workflow patterns
Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.
React UI + elegant infrastructure for AI Copilots, AI chatbots, and in-app AI agents. The Agentic Frontend 🪁
Production-ready platform for agentic workflow development.
No fortress, purely open ground. OpenManus is Coming.
利用AI大模型,一键解说并剪辑视频; Using AI models to automatically provide commentary and edit videos with a single click.
A free and open-source inpainting & image-upscaling tool powered by webgpu and wasm on the browser。| 基于 Webgpu 技术和 wasm 技术的免费开源 inpainting & image-upscaling 工具, 纯浏览器端实现。
[CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting
A simple screen parsing tool towards pure vision based GUI agent
OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340
[ICCV 2025 Highlight] OminiControl: Minimal and Universal Control for Diffusion Transformer
[CVPR2025 Highlight] Video Generation Foundation Models: https://saiyan-world.github.io/goku/