0553GitHub
Jev Browser: an LLM plans, Jev executes browser steps
Claude supplies a goal and text; Jev selects the browser element, action, value, and completion state while Playwright executes the step.
The public implementation and evaluation description were inspected on October 1, 2026. The builder reports 40 correct outcomes on 42 live-site tasks, with no false completion claims in the latest run. Counting and sort verification remained problematic. Free-form text comes from the calling model, and uncertain or consequential actions return a status for it to handle. The reported task results have not been independently reproduced.
Ying-Kai-Liao/jev-browserREADME ↗
# jev-browser
Browser automation where an LLM plans and **Jev** decides.
> Unofficial project, not affiliated with TypeSafe. It calls the TypeSafe System One API
> with your own API key.
The calling LLM (Claude, via MCP) says what outcome it wants, one step at a time, and hands
over any text to type. For each round of a step, code describes the page. Then one ~300 ms
[Typesafe System One](https://docs.typesafe.ai) request asks Jev several questions at once:
which element, which action, which value, and is the step done / blocked / showing an error /
about to do something irreversible. Playwright performs the action. The LLM never reads page
snapshots unless it chooses to take over.
```
Claude ── browser_do("Log in", {email, password}) ──▶ jev-browser
│ loop until done / stuck / needs confirmation
│ 1. settle (network + DOM quiet)
│ 2. describe (elements, labels, state, visible text, diff, counts)
│ 3. Jev (done? error? irreversible? tool? target? value?)
│ 4. act (Playwright)
Claude ◀── { status: "done", url, actions[], done_score } ─┘
```
https://github.com/user-attachments/assets/2e688df9-4985-4854-8ebe-ba97c9d13d68
Jev only answers with probability distributions: yes/no (`noul`), pick one option (`choice`)
or a rating (`score`). It never writes text. So everything free-form comes from the caller as
candidates, and code turns disagreement or low confidence into a status the LLM can act on.
## Results
42 tasks in 16 categories on live sites (see [RESULTS.md](RESULTS.md))