What it is
A Discord moderation bot for server admins and moderators. It analyzes incoming messages in real time, deletes spam and scam links, escalates offenses through a four-stage ladder, and profiles members based on their message history.
How it uses Jev
Jev scores incoming messages for spam and scam links. It also scores user profiles across scam risk, spamminess, noobness, toxicity, and helpfulness. Results drive automatic deletion, escalation, and persona assignment.
Primitives:score
Technique worth stealing
Pardoned messages are stored as safe precedents and fed into future Jev prompts, enabling server-specific false-flag learning without retraining.
Try it
Clone repo, install requirements, set DISCORD_TOKEN and TYPESAFE_API_KEY in .env, run python3 main.py, then !sync.
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-centricyes0.84
- Shows a System One patternunclear0.41
- Handles uncertaintyno0.06
- Measuredno0.04
- Runnableyes0.92
- Worth recommendingno0.39
- Model replicano0.08
- Problem scopescore on a 0–2 scale1.77
- About Jevyes0.95
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.