What it is
Jevfanity is a small profanity and moderation API for developers who need to flag text. It runs on Cloudflare Workers, exposes a hosted endpoint, and ships a typed npm SDK.
How it uses Jev
Jevfanity sends text to Jev and asks one focused Noul question per moderation category (profanity, slur, harassment, threat, sexual). Jev returns a probability for each category; the API compares the maximum score against the level policy and threshold to set flagged and flagged_categories.
Primitives:noul
Technique worth stealing
Ask one focused yes/no question per category instead of one broad question, then apply policy thresholds to the per-category probabilities.
Try it
curl -X POST https://api.jevfanity.app/v1/moderate -H "Content-Type: application/json" -d '{"text":"your message here","level":"medium"}'
Evidence
Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.
- Jev-centricyes0.88
- Shows a System One patternno0.28
- Handles uncertaintyno0.06
- Measuredno0.05
- Runnableyes0.89
- Worth recommendingno0.32
- Model replicano0.04
- Problem scopescore on a 0–2 scale1.96
- About Jevyes0.98
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 21 Sept 2026.