Chris Hughes

pytorch-accelerated. A lightweight library designed to accelerate the process of training PyTorch models by providing a minimal, but extensible training loop which is flexible enough to handle the majority of use cases, and capable of utilizing different hardware options with no code changes required. Docs: https://pytorch-accelerated.readthedocs.io/en/latest/

Yolov7-training. A clean, modular implementation of the Yolov7 model family, which uses the official pretrained weights, with utilities for training the model on custom (non-COCO) tasks.

simple-ppo. A clean, modular implementation of the Proximal Policy Optimization (PPO) algorithm in PyTorch, written with a strong focus on readability and educational value, as well as performance.

pix2seq. A PyTorch implementation of Pix2Seq for object detection, where detection is formulated as an autoregressive sequence generation task. This implementation supports both standard transformer and Llama-based architectures.

mcp-ddd. This repository demonstrates how to apply Domain-Driven Design (DDD) principles to build maintainable, scalable Model Context Protocol (MCP) servers. It accompanies the blog post Building Scalable MCP Servers with Domain-Driven Design.

func-to-script. A lightweight and convenient tool which can be used to turn a Python function into a command line script, with minimal boilerplate! A thin wrapper around argparse, with are no additional dependencies!

YOLOX. YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

multi-agent-patterns. A reference implementation exploring three multi-agent coordination patterns, built with the Microsoft Agent Framework.

Ai-skills. A structured catalog of reusable prompts, code patterns, and reference material for AI coding agents.