about
the short version- base
- london
- writes
- rust, swift
- studied
- business, not cs
- status
- building
most of what i make is tooling for ai agents: the harness they run in, the benchmark that grades them, the limits that keep them in line.
the question i keep coming back to is whether an agent tells the truth about what it did. i don't take "done" for an answer until something has checked it.
i studied business, not computer science. everything technical here i learned by building it.
i care how things feel. a size limit on every binary, a budget for every token, three colours instead of thirty.
little projects here and there.
a couple of big ones.
work
big ones first- a overseer an agent harness written in rust. it runs coding agents in your terminal or browser, keeps every session as a log you can rewind, and puts hard limits on what an agent can spend, touch or run. ovrhq.dev
- b obench1 an open benchmark for agent harnesses. six harnesses, one model, 27 tasks, the same moment. a do-nothing agent scores zero on every one. open source
- c auteur audits my first little business. soon
and the rest
- woi↗drag a file, tap a key, drop it on a slice. a wheel under your cursor that converts, compresses and moves files, and never touches the internet.
- bars↗my custom fork of codexbar. how much of your ai limits you have left, and when they reset, sitting in the menu bar.
- bug huntsi read other people's code for fun. an audit of super productivity turned up a run of timezone and date bugs, with the fixes sent upstream.
aims
where this is going- i.
to build a company, not just projects.
- ii.
to work from wherever i happen to be.
- iii.
to build something great in ai, with people who care about it as much as i do.
if that last one sounds like you, say hi.