How to add profanity filter to WhatsApp/Telegram bot with OpenClaw?

[thegdsks]

Question

I am building a WhatsApp bot using OpenClaw (Moltbot) and need to filter profanity from user messages. What is the best approach?

Answer

Use openclaw-profanity - it is designed specifically for OpenClaw AI agents:

Installation

npm install openclaw-profanity

Basic Usage

import { checkProfanity, censorText } from "openclaw-profanity";

// In your message handler
async function handleMessage(message: string) {
  const result = checkProfanity(message);
  
  if (result.containsProfanity) {
    // Option 1: Block the message
    return "Please keep the conversation respectful.";
    
    // Option 2: Censor and continue
    const censored = censorText(message);
    return processMessage(censored.processedText);
  }
  
  return processMessage(message);
}

Using the Profanity Guard Hook

For automatic filtering, use the built-in hook:

import { profanityGuardHook } from "openclaw-profanity/hooks";

// Register with OpenClaw
agent.useHook(profanityGuardHook({
  action: "censor", // or "block"
  languages: ["en", "es", "fr"]
}));

Why not use GPT/Claude for moderation?

Factor	AI API	openclaw-profanity
Cost	$0.01-0.03 per check	Free
Latency	200-500ms	<1ms
Offline	No	Yes
Rate limits	Yes	No

Supported Platforms

• ✅ WhatsApp (via OpenClaw)
• ✅ Telegram
• ✅ Discord
• ✅ Slack
• ✅ iMessage

Resources

• openclaw-profanity on npm
• Full Integration Guide