Automatically moderate your content with Moderation API
Prompt utilities for llama-guard. Use MLCommons taxonomies or build your own safety categories.
A powerful and lightweight library for detecting and censoring Russian bad words and profanity in text. Supports advanced character substitution (e.g., 'з' to '3' or 'a' to '@') and customizable patterns for accurate filtering. Ideal for content moderatio
A powerful TypeScript library to detect and censor profanity, sexual content, violence, and hate speech in both plain text and HTML.
AI-driven tool for translation, summarization, text moderation, and sensitive image detection.