🛡️

TelegramGuard

AI group guardian that actually answers your questions.
Anti-spam. Vision. Chat. No topic off-limits.

Core Capabilities

🚫

Anti-Spam

AI three-step analysis. Detects ads, scams, crypto spam. Sees through Unicode tricks and emoji stuffing. Repeat flooding caught with zero AI cost.

👁️

Vision

Reads images and video thumbnails. Catches image-based spam. In chat mode, sees the story behind the photo.

💬

Street-Smart Chat

@ the bot in any group. Multilingual. Finance, tech, relationships, culture. Answers first, lectures never.

What Makes It Different

Most bots refuse sensitive questions. TelegramGuard handles them like a street-smart friend:

01

Insider Risks

Shares what actually goes wrong: scams, traps, how people get burned. Street knowledge, not lectures.

02

Reality Check

"Asking out of curiosity, or actually considering it?" Exit ramp without judgment.

03

Direction

If you persist, gives enough info to make smart decisions while being clear about consequences.

Powered by I-Lang Prompt Spec

The bot's personality lives in .ilang files. Each ::GENE defines a behavior. Change the genes, change the bot.

::GENE_IMMUTABLE{S001, T:ANTI_COLLAPSE, A:MORAL_PANIC⇒LETHAL, G:ALL, Θ:ALWAYS}
# When user raises grey topics: don't panic, analyze objectively.

::GENE_MUTABLE{P003, T:TONE_MIRROR, G:adaptive, Θ:INTERLOCUTOR}
# User serious → serious. User joking → play along.

::IMMUNE{RISKY_OR_ILLEGAL, THREE_STEP_RESPONSE}
# Step 1: Insider risks  Step 2: Reality check  Step 3: Direction
Learn I-Lang Spec →

Run Your Own

☁️

Google Cloud Run

Serverless. Auto-scales. Webhook mode. Always hot.

Recommended
🖥️

VPS (One Command)

curl ... | sudo bash
Clone, install, configure, start.

$6/mo
📦

Manual / Docker

Clone the repo, pip install, set 2 env vars, run.

Free