Open-source tools and experiments for AI-assisted software development and developer experience
I build small, focused tools that fit into the workflows of engineers using AI coding agents. These are open source under the MIT license. More projects are landing here over the next few weeks.
A disciplined, adaptive workflow for building production software with AI coding agents. Turns accepted intent into the smallest safe working change through focused requirements, checks, independent review, and feedback.
A completed experiment in using specialized, in-context guidance to improve agentic code reviews. Includes 23 reviewer skills and retained real-code evaluations; the results found no conclusive improvement over ordinary agent reviews.
Browse and export AI coding assistant conversation history across Claude Code, Codex CLI, Gemini CLI, and Pi. Reaches local, WSL, Windows, and SSH homes; produces listings, markdown exports, and usage metrics.
Preflight a repository before AI-assisted refactors. Finds duplicate-code candidates, repeated documentation sections, and docs IA overlap so an agent can target real consolidation work.
Installs Git, Node, uv, Python, and Px on Windows without administrator rights. Meant for coding agents such as the GitHub Copilot desktop app that rely on the machine's own Node.js and Python, on corporate laptops behind an authenticating proxy.
Live Q&A and quizzes for training sessions, lectures, and workshops. Participants join from their phones to ask and upvote questions and answer moderator-run quizzes, while a projector view shows the room the same state. Installs with one command.