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
A monorepo of TypeScript tools built on TypeSafe AI's Jev: an agent tool-call guardrail, a GitHub issue-triage Action, and a bulk classification CLI/library, plus a shared Jev client. For developers wanting typed, confidence-gated LLM decisions.
How it uses Jev
All three tools ask narrow typed questions (choice/score/noul) against text state and branch on the answer in code. Guard vets agent tool calls (allow/block/hold); triage labels, prioritises, routes and dedupes issues; sort appends typed columns and a _confidence field to JSONL/CSV rows. Low-confidence answers escalate to a human or larger model.
Primitives:choicescorenoul
Technique worth stealing
Ask narrow typed questions, branch on the answer in code, and escalate anything Jev is unsure about to a human or larger model.
Try it
npm install @cmaintz/jev-guard, or npm install -g @cmaintz/jev-sort; set JEV_API_KEY.
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 patternFound in material0.91
- Describes handling uncertaintyFound in material0.89
- Reports measured numbersnot found in the excerpt0.06
- Is a runnable toolFound in material0.95
- Top-10 learning shortlist signalunclear0.56
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.47 / 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 11 Oct 2026.