Nexus Office
Agents that keep working without you need a place where you can see and answer them.
Public MIT repo with live Mac and phone clients.
Aria Han / CTO, Thinking Brain School
I design and run autonomous AI systems end to end: architecture, orchestration, memory, evals, and verifiable receipts. Humans review where judgment matters.
Eight of 20 projects. Built, broken, rebuilt, shipped.
Agents that keep working without you need a place where you can see and answer them.
Public MIT repo with live Mac and phone clients.
Claude Code kept starting over, so I built memory, rules, and receipts around it.
360 commits since January 2026, on the Claude plugin marketplace.
Leaderboards were not answering my questions, so I made tests that did.
21 tests, graded by programmatic verifiers.
Memory gets noisy unless it has to prove itself.
Correct answers were not enough. I wanted to know whether the model computed something real.
The failed hypothesis is documented next to the confirmed one.
AI education felt backwards, so I built the course I wanted people to have first.
Live on the App Store for iPhone, iPad, and Mac.
Safari tabs ate my research life, so I built a library.
Built and shipped solo in under a week.
A screen should be inspectable in every meaningful state before the whole app can run.
Published on npm with multi-viewport capture.
The record, not the claim.