Automated README summary
Automatically summarized from the README on 3 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Node.js library and CLI that gives a parent agent bounded browser tasks. Jev selects the next typed browser action, agent-browser executes it, and ambiguity or stuck states become structured handoffs back to the parent.
How it uses Jev
Jev decides the next typed browser action from the live page snapshot plus the goal and supplied inputs. Its choice is executed by agent-browser; success or a structured escalation (input-required, stuck) is returned to the parent via runLoop/resumeLoop.
Primitives:choice
Technique worth stealing
Keep the decision loop bounded and typed: Jev picks actions, the browser engine executes them, and ambiguity escalates as a resumable handoff.
Try it
npm install -g agent-browser jev-agent-browser; export TYPESAFE_API_KEY=...; jev --url ... --goal '...' --max-steps 6
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 material0.86
- Shows a System One patternFound in material0.81
- Describes handling uncertaintyFound in material0.73
- Reports measured numbersFound in material0.88
- Is a runnable toolFound in material0.94
- Top-10 learning shortlist signalunclear0.56
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale1.18 / 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 3 Oct 2026.