qiuqiuxiao930

A bot that filters scam ads in Telegram groups.

14
2
85% credibility
Found May 31, 2026 at 14 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

A Telegram group management bot designed to automatically detect and remove spam, scam, and other harmful messages. Group admins can enable or disable protection, view detection statistics, and manage a whitelist for trusted members. The bot uses multiple detection methods including keyword matching, suspicious link analysis, and optional AI-powered message classification to identify common scam patterns like investment fraud, gambling promotions, phishing links, and adult content spam. When suspicious activity is detected, the bot can automatically delete messages, warn users, and ban repeat offenders after three warnings.

How It Works

1
πŸ‘‹ You discover a protection tool

You're a group chat admin tired of scammers slipping in, and you hear about a bot that watches your group for bad actors.

2
πŸ”§ You connect it to your group

With just a few clicks, you add the bot to your Telegram group and it immediately starts keeping watch.

3
πŸ‘€ The bot silently monitors messages

As people chat, the bot quietly reads each message looking for common scam patterns like suspicious links, fake investment offers, or gambling ads.

4
The bot spots something suspicious
🚫
If it's clearly a scam

The message is deleted immediately and the user receives a warning notification in the chat.

πŸ€”
If it's borderline

The message is flagged but the admin gets a quick summary to decide whether to take action.

5
πŸ“Š You can see everything that happens

A simple dashboard shows you every message that was caught, what type of scam it was, and how many warnings each user has accumulated.

πŸ›‘οΈ Your group becomes a safer place

Spammers and scammers quickly learn your group isn't an easy target, and your community members feel protected without needing to worry about scams.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 14 to 14 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is AD-kill-bot?

AD-kill-bot is a Python-powered Telegram bot that automatically detects and removes scam advertisements in group chats. It combines three detection layers: keyword matching against a configurable rule file, URL analysis for suspicious domains and phishing patterns, and an optional AI classifier for nuancedεˆ€ζ–­. When a scam is spotted, the bot deletes the message, issues a warning to the user, and can auto-ban repeat offenders after a configurable threshold. Admins get commands like /scamguard to toggle protection, /whitelist to exempt trusted users, and /warn /unban for manual enforcement. All detection events are logged to a local SQLite database for audit and statistics.

Why is it gaining traction?

The multi-layered detection approach is the hook. Many Telegram anti-scam bots rely solely on keyword lists, but this one layers in URL pattern matching and AI classification, catching threats that slip past simple text filters. The configurable confidence threshold lets group admins tune sensitivity for their community. The YAML-based config and SQLite storage mean no external services or cloud dependencies, which appeals to self-hosted deployments.

Who should use this?

Telegram group admins managing communities vulnerable to investment scams, fake giveaways, and phishing links. Particularly useful for crypto trading groups, gaming servers, and Chinese-language communities where the built-in keyword categories are already tailored. Groups with active moderation teams will benefit most from the warning/ban escalation workflow.

Verdict

The detection pipeline is solid and the feature set covers real admin pain points, but with only 14 stars and minimal documentation, this is an early-stage project that needs community vetting before production use. The 0.8500000238418579% credibility score reflects that immaturity. Worth watching, but evaluate thoroughly on a test group first.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.