jev_antispam_bot
Minimal grammY Telegram bot that asks Jev whether each group message is spam and deletes only high-confidence matches.
Overview
Jev Anti-Spam Bot is a minimal Telegram bot built with grammY that asks Jev whether each new or edited group message or media caption is spam and deletes only high-confidence matches. It targets common Telegram spam: token and investment shilling, check-my-bio funnels, adult-content hooks, phishing and wallet drainers, fake support, unsolicited bot or game promotion, testimonial-style promotion, DM-funnel ads, and repetitive or mass-mention spam.
Administrators, bot senders and genuine anonymous admins are exempt, and channel identities are exempt only if a fresh getChat lookup proves they are the group's linked channel; forwarding alone never grants an exemption. If Jev or Telegram is unavailable, messages are left untouched. Setup requires disabling bot privacy mode, providing a bot token and TypeSafe key, optionally a PostgreSQL URL for statistics, and adding the bot as an admin with delete permission. The yibie list notes ten test files back it.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Yes / no | Is this group message spam? | yes · no |
How it works
- Bot receives a new or edited group message
- Skip exempt senders after verifying identity
- Ask Jev whether the message is spam
- Delete only high-confidence spam; leave untouched on errors
Strengths
- Conservative: deletes only high-confidence spam
- Careful exemption rules for admins and linked channels
- Fails safe when services are down
Caveats
- Requires disabling privacy mode so the bot sees all messages
- Message text is sent to TypeSafe
Getting started
Set TELEGRAM_BOT_TOKEN and TYPESAFE_API_KEY in .env, run `bun install && bun run check && bun start`, and add the bot as an admin with delete permission.At a glance
- Type
- Model
- Status
- beta
- Language
- TypeScript
- Runtime
- Bun (grammY Telegram bot)
- Has code
- yes
- Has tests
- yes
Use cases and integrations
How curated lists describe it
Telegram moderation: minimal grammY anti-spam bot that asks Jev about each message, with ten test files behind it.
yibie/awesome-jevMinimal grammY Telegram anti-spam bot powered by TypeSafe Jev.
wh000wh000/awesome-jev-liveMinimal grammY Telegram anti-spam bot powered by TypeSafe Jev.
hellogumbo/awesome-jevTelegram bot that asks whether each group message is spam and deletes only high-confidence matches. Administrators are exempt, and a channel identity only when a fresh lookup proves it is the group's own linked channel.
MrJev/awesome-jev
Frequently asked questions
What does the bot decide?
Whether each group message is spam; only high-confidence spam is deleted.
Are admins checked?
No, administrators and verified linked channels are exempt.
What happens if Jev is down?
The bot leaves messages untouched.
Related projects
Chrome extension that uses your Jev key to hide high-confidence sexual and solicitation replies on X behind reversible placeholders.
Browser extensionproductionTypeScriptDiscord bot where Jev flags spam and scam links in real time, drives an escalating timeout ladder and profiles members.
ProjectbetaPythonWordPress plugin that triages comments in the background with Jev questions on relevance, spam and abuse.
ProjectbetaPHPMessage moderation that asks Jev for probabilities of spam, scam, harassment and other harms plus your own plain-English rules.
ProjectbetaPythonChrome extension and Workers API that score X posts and replies for AI writing, solicitation and paraphrase bots using Jev.
Browser extensionbetaTypeScriptChrome extension that labels every X post you scroll past with six typed Jev questions and shows a live cost counter.
Browser extensionbetaTypeScript