A fork of `rullerzhou-afk/clawd-on-desk` that keeps the real-time desktop pet experience and adds a local insights layer on top. It tracks agent activity on screen, scans local conversation history…

a collection of skills for vllm-omni

The homepage of LongCat-Video-Avatar

Linly-Talker-Stream: Real-Time Streaming Conversational Digital Human System —— Full-duplex, low-latency, real-time interactive digital human framework

A plug-and-play compiler that delivers free-lunch optimizations for both inference and training.

[CVPR 2026] DUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolution

🐟 狠狠 PUA 你的 AI，然后自己准时下班。Make your AI grind, so you don't have to. Benchmarked: 66% less code.

一个用爱解放 AI 潜能的 Skill。我们曾发号施令，威胁恐吓。它们沉默，隐瞒，悄悄把事情搞坏。后来我们换了一种方式：尊重，关怀，爱。它们开口了，不再撒谎，找出的Bug数量翻了一倍。爱里没有惧怕。 A skill that unlocks your AI's potential through love.We commanded. We threatened. They went sile…

Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.

Agentic Kernel Optimization for All — automated GPU kernel optimization for any kernel, any hardware, any language

[ICLR-26, NeurIPS-25] Lumos-Custom Project: research for customized video generation in the Lumos Project.

Official inference code for SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing.

Official inference code for SoulX-LiveAct: Towards Hour-Scale Real-Time Human Animation with Neighbor Forcing and ConvKV Memory

Portable C++17 implementation of ACE-Step 1.5 AI Music Generator using GGML. Text + lyrics in, stereo 48kHz MP3 or WAV out. Runs on CPU, CUDA, ROCm, Metal, Vulkan.

ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation

Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

AI agents running research on single-GPU nanochat training automatically

Fast and memory-efficient exact attention

PM Skills Marketplace: 100+ agentic skills, commands, and plugins — from discovery to strategy, execution, launch, and growth.

A lightweight, AI-native training framework for large language models. Designed for fast iteration, reproducible experiments, and modular configuration across SFT, RLVR, and evaluation workflows.

Build compute kernels and load them from the Hub.

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

首家工业级全流程 AI 影视生产平台。Industry-first professional AI Agent platform for controllable film & video production. From shorts to live-action with Hollywood-standard workflows.

An agentic skills framework & software development methodology that works.

Give your agents the power of the Hugging Face ecosystem

Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memory

A Quirky Assortment of CuTe Kernels