Jev in production › Agent tool and action selection
Mac computer-use agent that reads the screen through OCR and accessibility data, then asks Jev a Choice over the numbered on-screen items for the next action, calling a writing model only for free text. $0.0002 per decision (author).
typesafe-computer-use (jev for short) drives a Mac toward a goal you type in plain English, for about a fiftieth of a cent per step. It reads the screen deterministically, asks a small classifier which action comes next, and only calls a writing model when a text field genuinely needs free text or the classifier has stopped and the screen needs reading.
One idea runs through it: the classifier picks, code decides facts, and the writer only writes free text. Anything a model would have to work out (a date, whether a field is focused, whether a URL is clean) is computed in code and handed over as state. VISION.md says what it is for in a dozen lines.
For the project's own README, linking back here: