Starred repositories
Production-grade engineering skills for AI coding agents.
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
💫 Toolkit to help you get started with Spec-Driven Development
A ComfyUI custom node designed for advanced image background removal and object, face, clothes, and fashion segmentation, utilizing multiple models including RMBG-2.0, INSPYRENET, BEN, BEN2, BiRefN…
🚀 即梦3.0逆向API【特长：图像生成顶流】，零配置部署，多路token支持，仅供测试，如需商用请前往官方开放平台。
Memory Debugger for Windows, Linux, Mac, and Android
A Kotlin Multiplatform UI framework from Tencent TDS — high-performance, one codebase for six platforms, with dynamic delivery.
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
Extract base runtime of chromium from chromium source tree
Strip mojo and base from chromium, support msvc compile(从chromium剥离mojo和base，支持msvc编译)
C++ media player library which use chromium media module
GPU accelerated deep learning inference applications for RaspberryPi / JetsonNano / Linux PC using TensorflowLite GPUDelegate / TensorRT
Static checks to aid with a healthy adoption of Compose
低延时直播（Low-Latency Streaming，LLS）是网易云信推出的低延时、强同步、高质量的直播产品。低延时直播产品基于云信 WE-CAN 全球智能路由网络，为开发者提供毫秒级延时、多平台同步、高可靠高并发的直播服务。 集成网易云信播放器 SDK/NERTD 插件，实现毫秒级延时、稳定流畅的高质量直播场景。
HackWebRTC Book source repo, please check those updated hack_webrtc_xxxxx branches.
OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image genera…
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Oboe is a C++ library that makes it easy to build high-performance audio apps on Android.
Shader playground website for exploring HLSL, GLSL, SPIR-V compilers