I built the thing I couldn't find.
One person, one instance at a time, in the open.
I have a master's in accounting and a career spent building software for other people. mini‑me started because my own money got away from me; too many accounts, too many moving pieces, and nothing on the shelf that used any of what I already knew.
So I built the first section for myself. Then I kept going, because the same thing kept happening elsewhere: the tracking outgrew my head, and the tool I wanted still didn't exist.
I only add a section once I've been asking Claude for it long enough to know its shape. That is slower than shipping against a roadmap. It also means nothing in here is speculative; every part of it started as something I needed twice.
Real accounting under a personal finance app, because I couldn't find one that had it.
A second section, still lived mostly in conversation while the interface catches up.
Standing them up gradually, and training whatever early users keep asking Claude for.
One instance per person, and a way out of it.
Your instance runs on its own database (a couple, actually). Your data isn't sharing a table with anyone else's. Everything is stored in open formats you can export and read without me. The engine underneath is open source: WeOS, licensed AGPL.
If mini‑me disappeared tomorrow, your data would still be readable and the core would still exist. I can't promise you forever. I can promise you're never locked in.
Early instances shape what gets built.
I'm taking on instances gradually — each one is a real database I stand up and support, and I'd rather do that well than fast.
What early users ask Claude for is what gets trained next. The questions you keep repeating are the roadmap.
You're not joining a queue. You're steering.