jev-ultrafast

What it is

Give it one goal. TypeSafe's Jev picks an operation and an element. A small LLM writes text only when the operation is TYPETEXT.

The homepage listed on the repository, browser-use.com, puts it like this: Browser Use is the cloud browser for AI agents. Run web agents that finish the task, or connect your own agent to stealth browsers at $0.02 an hour.

What the README says it does

• One request per decision cycle. Operation and target heads share the same observed state.
• No screenshots in the default agent loop. Jev consumes structured state. The inspector opts into screenshots; the video uses a separate continuous screencast.
• One browser call per snapshot. Read visible controls, their names, values, and text atomically. Keep references to the actual DOM nodes.
• Validate the selected target. Clicks check the document, form values, target, and nearby context. Animation alone does not force another prediction. Resolve current geometry and reject covered controls before input.
• Wait for useful state. After typing into a combobox, wait for visible suggestions, capped at 200 ms. Other interactions get at most two animation frames or 50 ms. These reads happen after execution is logged.

From the project’s README.

Where the decision sits

jev-ultrafast calls the hosted decision API rather than running its own weights. That keeps the project small and means its behaviour moves whenever the vendor ships a new model version. It also means an API key and a network round trip sit in the path of every decision.

Models it references: Jev.

How active it is

Created 2026-09-16, last pushed 2026-10-31, 24,065 stars and 1,843 forks when we read it on 2026-11-02. Everything in this category is weeks old at most, so a stale push date means something different here than it would on a mature project. Check the repository before you depend on it.