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 sorting desk for a creator's comments and DMs. Every message is read by Jev, then deterministic rules decide whether to flag, draft, like, hide, archive, or hand it to a human.
How it uses Jev
One API call asks five typed questions on the message state: what the person wants, how much a personal reply is worth, and whether it is spam, abusive, or mentions a health issue. The returned calibrated probabilities feed the rules in src/shared/route.ts, which pick an action.
Primitives:choicescorenoul
Technique worth stealing
Jev reads instructions literally, so wording matters more than thresholds: describe what counts as yes and no in the questions before tuning thresholds.
Try it
npm install, npm run dev, then paste a TypeSafe key from console.typesafe.ai/keys.
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 material0.94
- Shows a System One patternFound in material0.94
- Describes handling uncertaintyunclear0.43
- Reports measured numbersnot found in the excerpt0.09
- Is a runnable toolFound in material0.63
- Top-10 learning shortlist signalunclear0.45
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.13 / 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.