Automated README summary
Automatically summarized from the README on 29 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Python safety guardrail and interactive Streamlit dashboard that validates AI agent tool calls before execution, for developers building safer AI agents.
How it uses Jev
Jev receives agent state plus proposed tool details and returns a structured decision: Choice (Approved/Rejected/Suggested Alternative), Score (confidence 0-1), or Noul (uncertainty). The guardrail allows execution if approved with high confidence, blocks if rejected or low confidence, suggests alternatives, or requests clarification.
Primitives:choicescorenoul
Technique worth stealing
Intercept tool calls and route them through Jev for typed, calibrated decisions before execution.
Try it
pip install -r requirements.txt; export JEV_API_KEY; python demo.py or streamlit run streamlit_app.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 material0.95
- Shows a System One patternunclear0.47
- Describes handling uncertaintynot found in the excerpt0.08
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.75
- Top-10 learning shortlist signalunclear0.42
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.82 / 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 29 Sept 2026.