unredact

A simple tool for reading in poorly redacted documents and reproducing their origional form

cinecli

CineCLI is a cross-platform command-line movie browser built with Python.

full-stack-fastapi-nextjs-llm-template

Full-stack FastAPI + Next.js template generator with PydanticAI/LangChain agents, WebSocket streaming, 20+ enterprise integrations, and Logfire/LangSmith observability. Ship AI apps fast. CLI tool to generate production-ready FastAPI + Next.js projects with AI agents, auth, and observability.

nepa

PyTorch implementation of NEPA

FlashPortrait

We present FlashPortrait, an end-to-end video diffusion transformer capable of synthesizing ID-preserving, infinite-length videos while achieving up to 6$\times$ acceleration in inference speed.

Agent-Skills-for-Context-Engineering

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.

Constrict

Constrict 可以将视频压缩到您选择的文件大小——这对于上传到有文件大小限制的服务非常有用。您无需再依赖在线视频压缩服务，也无需手动反复尝试不同的比特率进行重新编码。

xl-converter

Easy-to-use image converter for modern formats. Supports fast parallel encoding, lossless JPEG transcoding, JPEG XL, AVIF, JPEGLI, ExifTool, and more.

Ai-Agent-Skills

Homebrew for AI agent skills.

Qwen-Image-Layered

&nbsp&nbsp🤗 HuggingFace&nbsp&nbsp | &nbsp&nbsp🤖 ModelScope&nbsp&nbsp | &nbsp&nbsp 📑 Research Paper &nbsp&nbsp | &nbsp&nbsp 📑 Blog &nbsp&nbsp | &nbsp&nbsp 🤗 Demo &nbsp&nbsp Introduction We are excited to introduce **Qwen-Image-Layered**, a model capable of decomposing an image into multipl

lightron

A light implementation of megatron for research and study

vibe-coding-cn

Vibe Coding 是一个与 AI 结对编程的终极工作流程，旨在帮助开发者丝滑地将想法变为现实。本指南详细介绍了从项目构思、技术选型、实施规划到具体开发、调试和扩展的全过程，强调以规划驱动和模块化为核心，避免让 AI 失控导致项目混乱。