Automated README summary
Automatically summarized from the README on 11 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Guardian sits between an AI agent and its tools, checking every tool call for safety, risk, and impact. It is for developers building LangGraph/LangChain or Antigravity agents who need a human-in-the-loop safety net.
How it uses Jev
Before any tool call runs, Guardian asks Jev typed questions: is this action safe, what kind of risk, how bad is the impact, and is the content good enough. Jev returns calibrated probabilities and confidence scores. Guardian's policy turns these into ALLOW, BLOCK, or ESCALATE signals.
Primitives:choicescore
Technique worth stealing
Use Jev's calibrated probabilities with configurable policy thresholds to decide between allow, block, and human escalation.
Try it
python dev.py setup, then add keys to .env and run python dev.py run
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 material0.92
- Shows a System One patternFound in material0.94
- Describes handling uncertaintyFound in material0.86
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.75
- Top-10 learning shortlist signalunclear0.51
- Is a replica of the modelnot found in the excerpt0.06
- Solves a common problem (0–2)score on a 0–2 scale1.96 / 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 11 Oct 2026.