Automated README summary
Automatically summarized from the README on 28 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A decision layer for the ego lite browser that replaces the per-step LLM round trip in multi-step browser tasks with one Jev call per step; code owns observation, execution, verification and exit conditions.
How it uses Jev
Jev reads one indexed element table and, in a single request, answers both the operation (click/type_text/select/scroll_up/scroll_down/wait/done/blocked) and the target element. Code then observes, executes, verifies and decides exit; fail-closed guards reject stale, occluded, disabled or cross-frame targets.
Primitives:choice
Technique worth stealing
Replace per-step LLM turns with one System One call that jointly picks the operation and target element, keeping execution and exit checks in code.
Try it
npx skills add jiangkoumo/ego-decision-layer, then run scripts/ego-decision-layer with --url, --text, --until and --steps.
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-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
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 projectnot found in the excerpt0.15
- Shows a System One patternFound in material0.65
- Describes handling uncertaintyunclear0.60
- Reports measured numbersFound in material0.99
- Is a runnable toolFound in material0.94
- Top-10 learning shortlist signalunclear0.46
- Is a replica of the modelnot found in the excerpt0.09
- Solves a common problem (0–2)score on a 0–2 scale1.05 / 2
- About JevFound in material0.99
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 28 Oct 2026.