Automated README summary
Automatically summarized from the README on 30 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
WebJev is a family of open-weight decision models specialized for browser use. Given a live web page, it picks the next action in a single forward pass. It is a drop-in replacement for Jev and is used by the jev-ultrafast browser agent.
How it uses Jev
WebJev answers per-step Choice questions from jev-ultrafast: which operation (CLICK, TYPE_TEXT, SELECT, page controls, DONE, BLOCKED), which click target, which type_text target, which select target. Each option gets a probability; the most probable operation and target are executed in the browser.
Primitives:choice
Technique worth stealing
Fine-tuning a mixture-of-experts model on live-web decision data to improve browser agent decisions.
Try it
Serve the model with evaluation/serving/serve.sh, then run apps/browser-agent/.
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 material0.91
- Shows a System One patternFound in material0.87
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersFound in material0.97
- Is a runnable toolnot found in the excerpt0.34
- Top-10 learning shortlist signalnot found in the excerpt0.38
- Is a replica of the modelFound in material0.95
- Solves a common problem (0–2)score on a 0–2 scale1.01 / 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 30 Sept 2026.