🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

The agent that grows with you

The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞

Run OpenClaw more securely inside NVIDIA OpenShell with managed inference

The agent-native LLM router for OpenClaw. 41+ models, <1ms routing, USDC payments on Base & Solana via x402.

A set of ready to use Agent Skills for research, science, engineering, analysis, finance and writing.

AI agents running research on single-GPU nanochat training automatically

Simple code sandbox supporting jupyter notebook style code execution. Used for agent training

Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.

Diffusion Models in Medical Imaging (Published in Medical Image Analysis Journal)

Digital mammography processing tools

"🐈 nanobot: The Ultra-Lightweight Personal AI Agent"

CUDA Templates and Python DSLs for High-Performance Linear Algebra

[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"

🚀 Efficient implementations for emerging model architectures

Improving Performance, Robustness, and Fairness of Radiographic AI Models with Finely-Controllable Synthetic Data

Repo for Qwen Image Finetune

Official implementation of the Fréchet Radiomic Distance

cuTile is a programming model for writing parallel kernels for NVIDIA GPUs

MedSAM3: Delving into Segment Anything with Medical Concepts

[ICLR 2025] This is the official repository of our paper "MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine“

The official codes for "PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents"

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

Biomedical Visual Instruction Tuning with Clinician Preference Alignment

SGLang is a high-performance serving framework for large language models and multimodal models.