I built a local-first AI desktop knowledge base — here's what I learned
What actually changes when the model runs on your machine and your documents never leave it — the wins, the trade-offs, and why structure beats re-prompting.
Read on DEV
Blog
Notes from building it
Field notes on local-first AI — the engine, the format, and the decisions behind them — written while shipping it in the open. Long-form pieces live on DEV and CoderLegion.
Deep-dives on DOCNEST & the .udf format
A series of longer write-ups on the structure-first approach, the open knowledge format, and building tools you run yourself.
Read on CoderLegion
Follow the work as it ships
Every layer of the platform is built in public. Star the repos, read the commits, and watch the roadmap turn into releases.
Browse the repos
Get the tools, not just the theory
The writing is the why. The products are the proof — both free and yours to run.