Projects
Machine learning libraries and developer tools I have created.
Tools to create and evaluate machine learning models for sports betting, compatible with scikit-learn, usable from an AI agent, Python or the command line.
Novel oversampling algorithms for class imbalance, including Geometric SMOTE and clustering-based oversampling.
Task-oriented components for text, images, audio and video with a scikit-learn API, powered by open-source models or cloud APIs.
Create and simulate complex systems: describe a model in a few lines, and it works out the mathematics, picks a solver and runs the simulation.
Certified computer algebra for Lean 4, with agent skills that turn a physics or math statement into a machine-verified proof.
Copier template for modern Python projects.
MCP server for Mathpix OCR, converting images, PDFs and DOCX/PPTX to LaTeX and Markdown from any LLM or agent.
A framework for generating multi-agent organisations powered by Agno.