A fast accurate API for detecting NSFW images.
Self-Supervised Euphemism Detection and Identification for Content Moderation, IEEE S&P (Oakland) 2021
The Open Source Firewall for LLMs. A self-hosted gateway to secure and control AI applications with powerful guardrails.
AI-powered customer service assistant with guardrails for safe, compliant interactions using an LLM and multiple detector models.
Self-hosted content moderation API that outperforms Amazon Comprehend. 100% offline, your data never leaves your server. Text + Image moderation.
Dataset and code implementation for the paper "Decoding the Underlying Meaning of Multimodal Hateful Memes" (IJCAI'23).
An ML driven NSFW moderator for Slack 🚨👮♂️🤖
Middleware library for pydantic-ai agents - before/after hooks for guardrails, logging, rate limiting, PII redaction, content moderation, and input validation.
OpenSceneSense is a Python library that harnesses AI for advanced video analysis, offering customizable frame and audio insights for dynamic applications in media, education, and content moderation.
Content moderation papers @ ICWSM 2019 & AAAI 2020.
NLP/ViT-driven bot for detection & moredation of inappropriate content in Telegram groups
LyricMind is an AI-powered cognitive firewall that analyzes song lyrics to protect against unconscious absorption of harmful content. Using customizable frameworks and LLMs, it detects risky patterns and integrates with music players to trigger protective actions when thresholds are exceeded.
一款针对 LLM 输入侧审查的精确逆向分析工具。自动定位 NewAPI、OneAPI 及任何实施基于字典规则进行 Prompt 过滤的 API 网关中的敏感关键词 | A precision reverse-engineering tool for LLM input censorship. Automatically pinpoints blocked keywords in NewAPI, OneAPI, and any API gateways enforcing dictionary-based prompt filtering.
NudeDetect is a Python-based tool for detecting nudity and adult content in images. This project combines the capabilities of the NudeNet library, EasyOCR for text detection, and the Better Profanity library for identifying offensive language in text.
Python SDK
An AI-powered content moderation system using Python and Hugging Face Transformers. Combines rule-based filtering and machine learning to detect and block toxic, profane, and politically sensitive content, built for developers and communities to create safer, positive online spaces.
Trying to make sense of the EU's DSA Transparency DB
Real-time ML agent that detects sensitive content in video streams for classroom, parental, and enterprise safety.
A new package is designed to analyze user inputs related to avoiding negative or unwelcome appearances on a Louis Rossmann video. It processes the text input to identify key factors or common pitfalls
A simple toxicity detector.
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."