Jev in production › Moderation and content filtering

Jev Anti-Spam Bot

Telegram bot that sends each group message to Jev with twenty-one spam questions and deletes it, with linked recent messages from the same campaign, when any signal reaches 0.90; messages stay when Jev is unavailable.

Open on GitHub ↗

The source publishes no measured number.
Use
Moderation and content filtering
Industry
Media and social
Form
Open-source tool
Stage
Beta
Plugs into
Telegram
Listed
2026-09-22
Found via
github
Repository
backmeupplz/jev_antispam_bot
Stars
16
Forks
2
Last push
2026-10-10
Language
TypeScript
License
MIT

The README opens with

A minimal grammY Telegram bot that asks TypeSafe's Jev model whether each group message is spam and deletes only high-confidence matches.

- token, investment, referral, gambling, giveaway, and service shilling; - “check my bio/profile/description” and DM/channel funnels; - low-substance emoji or generic-engagement hooks backed by adult-content bio/personal-channel metadata; - phishing, wallet drainers, fake support, and fraudulent airdrops; - unsolicited bot/game promotion, sexual/DM bait, and easy-money pitches; - unsolicited testimonial/social-proof promotion of bots, channels, groups, mini apps, sites, courses, or providers, even without a start/join/buy command; - unsolicited service or product ads that funnel members to DMs, email, or...

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for moderation and content filtering