Stars
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
Agent S: an open agentic framework that uses computers like a human
Follow-Your-Preference: Towards Preference-Aligned Image Inpainting
litagin02 / Style-Bert-VITS2
Forked from fishaudio/Bert-VITS2Style-Bert-VITS2: Bert-VITS2 with more controllable voice styles.
🐹 Dig deep like a mole to clean you Mac. 像鼹鼠一样深入挖掘来清理你的 Mac
The code of Exploring a Double Task Learning Framework for Makeup Transfer
Lynx: Towards High-Fidelity Personalized Video Generation
🚀 Full-stack Next.js 15 + Cloudflare Workers template with D1 database, R2 storage, Better Auth, and Server Actions. Production-ready with automated CI/CD and generous free tiers.
开盒即用的优雅管理mcp服务 | 结合Agent框架 | 作者听劝 | 已发布pypi | Vue页面demo
A highly extensible private cloud storage solution for individuals and teams, featuring AI-powered semantic search.
Accelerate your development with a sleek, open-source admin dashboard and landing page built on Vite-React, Next.js, Tailwind CSS, and Shadcn/UI which is fully customizable and production-ready.
All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
Audio playback and capture library written in C, in a single source file.
Bananas🍌, Cross-Platform screen 🖥️ sharing 📡 made simple ⚡.
Stay on top of trending topics on social media and the web with AI
The official code repository for SongPrep: A Preprocessing Framework and End-to-end Model for Full-song Structure Parsing and Lyrics Transcription.
A minimal, easy-to-read PyTorch reimplementation of the Qwen3 and Qwen2.5 VL with a fancy CLI
A Tailwind CSS plugin that brings GitHub's beautiful Markdown styling to your projects, with support for both light and dark themes.
Fully Open Framework for Democratized Multimodal Training
Data Synthesis for Deep Research Based on Semi-Structured Data
Cutting edge AI technology for automated audio transcription. A nice GUI for OpenAIs Whisper and pyannote (speaker identification)
MiMo-Audio: Audio Language Models are Few-Shot Learners
AIWriting AI写作 AI写小说 自动批量生成章节，设定更新，记忆上下文等。