Moderation Python Packages

red-discordbot

A multi-function Discord bot

safetext

Fast profanity word, curse word, swear word, bad word filtering tool for English, Spanish, Chinese, Turkish and more.

lexicont

Lightweight LLM agent for text moderation with deterministic pipeline: profanity rules → ML → LLM. Production-grade, YAML configurable. Uses glin-profanity + rapidfuzz + detoxify with Qwen LLM agent (llamacpp/Ollama) + RAG. Early-stop logic. Pure Python, CLI/API/SDK.

django-model-reviews

Easy moderation of changes made to models

siftfy

Official Python client for the Siftfy spam-classification API.

toxic-detection

Intelligent AI Agent for Real-time Content Moderation with 97.5% accuracy

semanticshield

SemanticShield library

imagebreak

ImageBreak is a comprehensive framework for testing AI model safety and content moderation systems. It provides tools to evaluate how well AI models handle potentially harmful prompts and helps researchers identify vulnerabilities in content filtering systems.

django-flag-app

A pluggable django application that adds the ability for users to flag(or report) your models

censore

🃏 A tool for identifying and censoring profanity in text

safelyx

API client for Safelyx.

feedback-analyzer-mod

A new package designed to analyze and structure user-submitted text, specifically focusing on community feedback and moderation. The package leverages the capabilities of llmatch-messages to process a