Multi-layer AI content moderation system with toxicity detection, NSFW filtering and policy compliance checking
-
Updated
Mar 21, 2026 - Python
Multi-layer AI content moderation system with toxicity detection, NSFW filtering and policy compliance checking
基于 LLM 的 Telegram 群聊智能管理机器人 — 智能决策、知识库 RAG、内容审查、贴纸学习、联网搜索、多层记忆架构
Real-time ML agent that detects sensitive content in video streams for classroom, parental, and enterprise safety.
AI-powered content moderation API with toxicity detection and trust scoring built using FastAPI and Transformers.
A simple toxicity detector.
Hush: A lightweight, context-aware text toxicity classifier. Leveraging NLP and Random Forest ensemble learning to detect and mitigate harmful language in real-time. Built for efficiency, safety, and cleaner digital communication.
A multilingual text analysis system that performs sentiment analysis and toxicity detection with detoxified text generation.
Self-improving security filter for AI applications. Learns from missed attacks, auto-deploys validated rules, and self-prunes false positives.
Scan Twitter/X post history for problematic content using local LLM analysis via Ollama, optional Claude second-pass review, and automated deletion through the Twitter API.
SmartShelf is a web application for browsing, rating, and reviewing books, enhanced with AI functionalities for content moderation and text-to-speech. Django, PostgreSQL, and OpenAI API.
Production-grade LinkedIn post restyling API with safety and quality checks.
A mini content moderation project app that uses Mistral AI to detect inappropriate or harmful text. Built with FastAPI and Streamlit, it flags content based on certain categories, supports custom "bad words," and masks PII information.
Enterprise-grade Image Object Detection and Content Moderation API with YOLOv8 and AI-powered safety checks
A machine learning pipeline that classifies TikTok videos as claims or opinions to prioritize content moderation, achieving 99% recall using Random Forest and XGBoost.
FastAPI-based AI content moderation and audio transcription API for dating apps with OpenAI integration. Provides hybrid text moderation, high-accuracy audio transcription, and real-time moderation + transcription capabilities.
An autonomous scraper that extracts adult videos, converts them to MP3, and organizes files into labeled folders. Powered by LimitX Browser to help keep the web safer for children.
A high-performance, privacy-focused content moderation microservice built with FastAPI and ONNX. Provides local text toxicity analysis and NSFW image detection with zero external API dependencies.
Production-minded guardrail API for detecting personalized mental-health advice with explainable safe/unsafe decisions. Docker-first, FastAPI, Cloud Run-ready, with auth, rate limits, and cost controls.
🚀 Enable accurate assessment of AI models with the RAIL Score Python SDK, promoting responsible and fair AI development effortlessly.
Add a description, image, and links to the content-moderation topic page so that developers can more easily learn about it.
To associate your repository with the content-moderation topic, visit your repo's landing page and select "manage topics."