Let an AI agent drive your Mac for a fiftieth of a cent per step with TypeSafe Computer Use A developer released TypeSafe Computer Use (jev), an open-source macOS computer-use agent that reads the screen deterministically and routes each step through a small classifier, calling a frontier model only when free text or screen reading is needed. Per the project's README, jev costs about $0.0002 per decision versus $0.032 for Claude Opus 5 on a bare screenshot, and roughly $0.003 for a 12-step task versus $0.40 to $0.90, with model latency of 0.13 to 0.38 seconds against 5.2 seconds. The README acknowledges the trade-off: reasoning a frontier model performs for free must be rebuilt as deterministic state, such as date parsing written in code. Computer-use agents built on frontier models work, but every step ships a screenshot to a big model and waits several seconds for a plan. A twelve-step task can cost close to a dollar. Most of those steps do not need a plan at all: they need one choice from a short list of buttons. awlevin/typesafe-computer-use https://github.com/awlevin/typesafe-computer-use , called jev for short, is built on that observation. Per the README it 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. This post covers what it is good for, the install, and a safe first run. The README measures one decision on the same screenshot and goal against Claude Opus 5 given a bare screenshot: | | jev | frontier model, bare screenshot | |---|---|---| | cost per decision | $0.0002 | $0.032 | | cost per 12-step task | $0.003 | $0.40 to $0.90 | | model latency | 0.13 to 0.38 s | 5.2 s | | full step with capture and OCR | about 1.5 s | about 5.5 s | It is honest about the catch: the big model read event dates off the pixels and compared them unaided, while the classifier needed date parsing written in code. Every piece of reasoning a frontier model does for free has to be rebuilt as deterministic state. You need macOS 14 or newer, Python 3.12 or newer and uv https://docs.astral.sh/uv/ . Windows 10 and 11 are experimental. git clone https://github.com/awlevin/typesafe-computer-use cd typesafe-computer-use uv sync cp .env.example .env fill in the keys The .env variables: TYPESAFE API KEY required : used for every decision. ANTHROPIC API KEY optional : used for typing free text, writer-proposed URLs and the final answer. The README documents pointing the writer at another model instead, including LM Studio, Ollama or any OpenAI-compatible server. CLICKER EMAIL optional : enables the type email action. CLICKER BROWSER optional : defaults to Google Chrome. Then grant your terminal Screen Recording and Accessibility in System Settings, Privacy & Security. Without the first, captures are just wallpaper. Without the second, clicks are silently dropped and --act refuses to start. It drives your real mouse and keyboard, so start without --act : uv run clicker "open the Playground" dry run: one step, prints what it would do uv run clicker-inspect "any goal" capture and open the annotated screen + payload Clear the terminal before you run it. The terminal is on screen, so its text becomes OCR input. uv run clicker "open the Playground" --act up to 100 steps uv run clicker "log in" --act --steps 20 --delay 3 longer and slower uv run clicker "log in" --act --handoffs 0 the classifier alone To stop a live run, press Ctrl-C or slam the mouse into the top-left corner of the screen. The loop also stops on done , low confidence, a stall or the step limit. Every run writes a runs/