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
jev-browser is a browser automation library, CLI and MCP server where an LLM (e.g. Claude) states one outcome per step and Jev makes the per-round decisions, so the LLM rarely reads page snapshots.
How it uses Jev
Each round, code describes the page (elements, labels, state, text). One ~300 ms Jev request answers several typed questions at once: which element, which action, which value, and whether the step is done, blocked, showing an error, or about to do something irreversible. Playwright then performs the chosen action.
Primitives:choicescorenoul
Technique worth stealing
Turn free-form choices into typed questions: Jev only returns probability distributions, so callers supply candidate values and code maps low confidence or disagreement to actionable statuses.
Try it
npx playwright install chromium, then add the MCP server with TYPESAFE_API_KEY or OPENROUTER_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 material0.93
- Shows a System One patternFound in material0.95
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersnot found in the excerpt0.28
- Is a runnable toolFound in material0.93
- Top-10 learning shortlist signalunclear0.52
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.14 / 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.