Local AI, developer tools, and a chess engine. A few ways I’ve put what I’m learning to work.
Drag or use arrow keys to turn the model. Press Home to return to its original orientation.
Your knowledge. A little more connected.
A self-hosted RAG system that turns a document collection into grounded, cited answers. It combines semantic and keyword search on local GPUs, with an evidence panel that lets you follow each answer back to the passages it used.
Drag or use arrow keys to turn the model. Press Home to return to its original orientation.
A small agent. A hands-on approach.
A lightweight AI coding agent with a terminal-style web interface. Persistent sessions, streaming responses, and file tools let you work directly with a project, while separate working directories keep each conversation tied to the code it belongs to.
Drag or use arrow keys to turn the model. Press Home to return to its original orientation.
Sixty-four squares. Endless questions.
An experimental chess engine in C++, built to explore board representation, move generation, and the logic behind a familiar game. It starts with a FEN position and a command-line loop for moving pieces around the board, one small rule at a time.