Starred repositories
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static bin…
Implementation for the paper "StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction".
Port of OpenAI's Whisper model in C/C++
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
The open-source AI voice studio. Clone, dictate, create.
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
直播一站式处理工具，支持直播录制&视频处理&弹幕处理&录播姬自动上传
A feature-rich command-line audio/video downloader
An universal Dear ImGui Hook for Directx12, 11, 10, 9 and Vulkan
C++ IPC Library: A high-performance inter-process communication using shared memory on Linux/Windows.
duilib界面库的改进版，支持Windows/Linux/MacOS平台（基于SDL3），支持Skia渲染引擎（支持CPU/GPU），支持DPI感知，多语言动态切换，支持SVG, PNG, GIF, JPG, BMP, APNG, WEBP, ICO图片，支持GIF/WebP/APNG动画。
A conformant OpenGL ES implementation for Windows, Mac, Linux, iOS and Android.
zero-shot voice conversion & singing voice conversion, with real-time support
DeepEP: an efficient expert-parallel communication library
FlashMLA: Efficient Multi-head Latent Attention Kernels
Fully open reproduction of DeepSeek-R1
Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, i…
The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curatio…
so-vits-svc fork with realtime support, improved interface and more features.
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
Cross-platform, customizable ML solutions for live and streaming media.
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
Source code for the X Recommendation Algorithm
RTMP 推流器，RTMP(HLS)秒开播放器，直播点播，跨平台（Win,IOS,Android）开源代码
这是一个用C++实现ASR推理的项目，它依赖很少，安装也很简单，推理速度很快，在树莓派4B等ARM平台也可以流畅的运行。 支持的模型是由Google的Transformer模型中优化而来，数据集是开源wenetspeech(10000+小时)或阿里私有数据集(60000+小时)， 所以识别效果也很好，可以媲美许多商用的ASR软件。