Stars
OmX - Oh My codeX: Your codex is not alone. Add hooks, agent teams, HUDs, and so much more.
Teams-first Multi-agent orchestration for Claude Code
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
AI agents running research on single-GPU nanochat training automatically
A collection of AI Agents papers (Updated biweekly)
Stay in flow while building with AI
Ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete.
A set of ready to use Agent Skills for research, science, engineering, analysis, finance and writing.
Official Notion Skills for Claude - step-by-step guides for Notion workflows
Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"
Light Image Video Generation Inference Framework
Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.
State is a machine learning model that predicts cellular perturbation response across diverse contexts
We present StableAvatar, the first end-to-end video diffusion transformer, which synthesizes infinite-length high-quality audio-driven avatar videos without any post-processing, conditioned on a re…
Unlimited-length talking video generation that supports image-to-video and video-to-video generation
Unlimited-length talking video generation that supports image-to-video and video-to-video generation
[AAAI 2026] FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation
Real-time Claude Code usage monitor with predictions and warnings
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance…
Accessible large language models via k-bit quantization for PyTorch.
A pytorch quantization backend for optimum
[NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation
[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.
A unified inference and post-training framework for accelerated video generation.
[CVPR 2025] Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers