keywords:Moderation - npm search

@playkit-js/moderation

[![Build Status](https://github.com/kaltura/playkit-js-moderation/actions/workflows/run_canary_full_flow.yaml/badge.svg)](https://github.com/kaltura/playkit-js-moderation/actions/workflows/run_canary_full_flow.yaml) [![code style: prettier](https://img.sh

playkitjs.bot

published version 3.2.24, 8 days ago

Maintenance: 33%. Quality: 65%. Popularity: 1%.

decancer

A library that removes common unicode confusables/homoglyphs from strings.

vierofernando

published version 3.2.8, 24 days ago

Maintenance: 33%. Quality: 61%. Popularity: 3%.

glin-profanity

Glin-Profanity is a lightweight and efficient npm package designed to detect and filter profane language in text inputs across multiple languages. Whether you’re building a chat application, a comment section, or any platform where user-generated content

gdsks

published version 1.1.9, 2 months ago

Maintenance: 33%. Quality: 62%. Popularity: 1%.

content-checker

Open-source and modern AI content moderation

jahabeebs

published version 1.1.3, 6 months ago

Maintenance: 33%. Quality: 63%. Popularity: 1%.

@sergiyiva/badwords-filter

An easy to use badwords filter with advanced detection and anti-workaround

sergiyiva

published version 1.5.4, 2 months ago

Maintenance: 33%. Quality: 62%. Popularity: 1%.

discord-alt-detector

A small library for discord.js to detect the suspiciousness of level of a user.

djj123dj

published version 1.0.3, 4 months ago

Maintenance: 33%. Quality: 61%. Popularity: 0%.

@stackend/api

JS bindings to api.stackend.com

bjorkman

published version 1.4.87, 3 months ago

Maintenance: 33%. Quality: 59%. Popularity: 2%.

prompt-validator

A package to validate OpenAI prompts for high levels of violation

buddha2042

published version 1.1.5, 6 months ago

Maintenance: 33%. Quality: 61%. Popularity: 0%.

ai-content-moderation

AI-powered content moderation system with subscription management

vaiftech

published version 1.1.0, 4 months ago

Maintenance: 33%. Quality: 54%. Popularity: 0%.

@moderation-api/llama-guard-prompt-utils

Prompt utilities for llama-guard. Use MLCommons taxonomies or build your own safety categories.

cruelmoney

published version 0.0.2, 3 months ago

Maintenance: 33%. Quality: 53%. Popularity: 1%.

iffyjs

iffy.com javascript wrapper

abdulhdr1

published version 1.0.2, 4 months ago

Maintenance: 33%. Quality: 52%. Popularity: 0%.

@milcondev/free-ai

This will allow users of your npm package to generate images or ask questions through the `FreeAI` class, keeping both functionalities in one package.

milcondev

published version 6.0.0, a month ago

Maintenance: 33%. Quality: 51%. Popularity: 1%.

abuse-detection

A package to detect abusive words in multiple languages including English, Spanish, French, German, Italian, Portuguese, Dutch, Russian, Chinese, Japanese, Korean, Arabic, and Hindi

deepakmardi22

published version 1.1.0, 3 months ago

Maintenance: 33%. Quality: 51%. Popularity: 0%.

@bedrockapi/moderation-sdk

NodeJS client SDK for integrating the Bedrock Moderation Service

afj176

published version 1.5.0, 5 months ago

Maintenance: 33%. Quality: 49%. Popularity: 1%.

ribald

Ribald is a lightweight and efficient Node.js package designed for detecting vulgar and obscene words within strings. It returns an array containing these offensive terms found in the input string. With its comprehensive list of offensive terms, Ribald em