Automated README summary
Automatically summarized from the README on 17 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A System One decision pattern for OpenClaw: when the task is choosing from a bounded set of candidates, score them and select rather than generate. Includes an applicability checklist, a two-mode CLI, and escalation thresholds.
How it uses Jev
Jev-style choice is applied via a CLI: embed mode scores options by semantic similarity through any OpenAI-compatible embed server; matrix mode scores options with a weighted criteria matrix from JSON. Output JSON gives the choice, confidence, margin, and all candidate scores; low confidence or a small top-1/top-2 gap triggers escalation.
Primitives:choice
Technique worth stealing
Score a bounded candidate set and pick the top one, escalating when confidence is low or the top two are close.
Try it
Run python decide.py embed --query ... --options ... or python decide.py matrix --spec examples/supplier_matrix.json
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 material0.72
- Shows a System One patternunclear0.51
- Describes handling uncertaintyunclear0.40
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.91
- Top-10 learning shortlist signalunclear0.51
- Is a replica of the modelunclear0.58
- Solves a common problem (0–2)score on a 0–2 scale1.08 / 2
- About JevFound in material0.89
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 17 Oct 2026.