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 Python safety gate for proposed actions (file reads, shell commands). It asks Jev the same question in three framings and only allows execution when the perspectives reach consensus.
How it uses Jev
Each proposed action is judged by three independent Jev question sets defined in perspectives.jev: safety, legitimacy, and adversarial. consensus.py gathers the three results and applies an asymmetric rule: all allow means allow, any block means block, any escalate routes to a human.
Primitives:choice
Technique worth stealing
Ask the same judgment three independent ways and require consensus, so a single framing blind spot cannot pass an action.
Try it
uv sync, copy .env.example to .env with your TypeSafe key, then uv run python demo.py
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 material0.85
- Describes handling uncertaintynot found in the excerpt0.07
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolunclear0.59
- Top-10 learning shortlist signalunclear0.40
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale1.84 / 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 17 Oct 2026.