Libraries tagged by Moderate

AI-powered civility filter that analyzes posts for incivility using Anthropic Claude, OpenAI GPT, or OpenRouter

Go to Download

Google Perspective Comment Analyzer API for PHP

Go to Download

Profanity matcher for English, Romanized Nepali and Devanagari Nepali: leetspeak, stretched and spelled-out letters, Nepali postpositions, with care not to block real names.

Go to Download

Moderator role implementation

Go to Download

Community forum for Laravel: boards, threads, replies, voting, moderation, subscriptions, badges.

Go to Download

Website and polymorphic model reviews for Laravel: configurable weighted criteria, a single rating grid, moderation, official replies and settings-driven notification emails.

Go to Download

A safety layer for LLM input and output in Laravel: a fluent, composable pipeline of guards (PII redaction, prompt-injection detection, moderation, schema validation) plus a provider-agnostic wrapper for any LLM call.

Go to Download

ModShield anti-spam connector for Flarum

Go to Download

Official PHP SDK for Moderyo Content Moderation API

Go to Download

Official Mirador PHP Client

Go to Download

Suspicion-scoring trust & moderation engine for Laravel. Pluggable detectors accrue suspicion points; thresholds flag, restrict, queue for review, or ban.

Go to Download

Unofficial Laravel/PHP SDK for TypeSafe AI's System One decision model (Jev): typed choice, score and yes/no judgments, a validation rule and test fakes.

Go to Download

Filter out words and phrases from forum posts with Gemini API support

Go to Download

Official PHP client for the Insion API

Go to Download

A configurable profanity filter for Laravel. Block or censor profanity with multi-language support.

Go to Download