Automated README summary
Automatically summarized from the README on 18 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A browser automation library, CLI and MCP server for LLM agents. The calling LLM states one outcome per step; code describes the page and Jev picks the element, action and value, while Playwright executes.
How it uses Jev
Each round, code describes the settled page (elements, labels, state, visible text, diff, counts). One ~300 ms System One request asks Jev several questions at once: is the step done, blocked, showing an error, or irreversible; which tool, target element and value. Playwright then acts; low confidence or disagreement becomes a status the LLM can act on.
Primitives:choicescorenoul
Technique worth stealing
Keep the LLM out of page snapshots: let a small typed model answer many page questions per round, and turn its uncertainty into statuses.
Try it
npx playwright install chromium, then add the MCP server with npx -y -p jev-browser jev-browser-mcp and TYPESAFE_API_KEY.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.92
- Shows a System One patternFound in material0.95
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersnot found in the excerpt0.27
- Is a runnable toolFound in material0.94
- Top-10 learning shortlist signalunclear0.53
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.11 / 2
- About JevFound in material0.98
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 18 Oct 2026.