A public workshop

Useful systems for a brain that works differently.

I’m Lee. I write and build practical ways to keep working when memory, concentration and energy are unreliable. Here are the systems I use, the experiments that helped, and the ones that didn’t.

Follow the writing on Substack ↗Explore the work ↓

New to AI? Start here →

From a real problem to something useful

On the bench.

Released · Omarchy Briefing

An update list that explains itself.

A real memory gap became an experiment, a build with Codex, everyday testing and a public MIT release. Package changes explained, with Omarchy news in one place.

Explore the plugin and its Lab record →

Try · First Steps

Prepare for the conversation.

An early tool for turning half-noticed Parkinson’s symptoms into a printable record for a clinical conversation. Entries stay on your device; it does not diagnose.

Explore First Steps ↗

Experiment · Local AI

An AI that stays on my desk.

A desktop test returned an answer in 5.18 seconds from cold and 1.36 seconds warm. The next question: what useful work can it do?

See the result and limits →

Latest from the Lab

Current experiment · September 2026

My Linux Changes — remembering why I changed it

Can a small desktop journal keep the reason for a Linux change alongside what changed, where the backup is and how to undo it?

What happened
A local Omarchy bar prototype is built and in development. It combines deliberately written explanations with observations of installed package and plugin changes. Detection can flag a change; it cannot know why I made it. This is not a public release or a finished reliability verdict.

Read the experiment →

Find your way in

Start with the part that sounds most like your problem.

How the pieces fit

Keep following the work.

I publish the full stories on Substack. This workshop is where the projects, experiments and useful tools live.

Read and subscribe on Substack ↗