gg-friggin-ez
Fast, drop-in profanity and toxicity screener for Node.js, powered by TypeSafe AI Jev. Catches leetspeak, character spacing, and romanized profanity across languages including Kannada, Telugu, Tamil, Hindi, and Bengali. ~50-500ms latency.
Fast, drop-in multilingual profanity and toxicity screener for Node.js, powered by System 1 models like TypeSafe AI Jev and Laya. Catches leetspeak, character spacing, and romanized profanity across languages including Kannada, Telugu, Tamil, Hindi, and Bengali. ~50-500ms latency.
How it uses Jev
Fast, drop-in profanity and toxicity screener for Node.js, powered by TypeSafe AI Jev .
Use cases
- Games & platforms - lobby chat, team comms, live game chat (Valorant, Counter-Strike: Global Offensive (CS:GO), Counter-Strike 2 (CS2), League of Legends (LoL)), Discord/Telegram…
- Chat & messaging surfaces - live chat (Twitch chat, TikTok Live comments), group chat, live customer support chat widgets, marketplace buyer-seller chat (Alibaba chat), dating app…
- Moderation use cases - game profanity filter, toxic chat filter, multiplayer chat moderation API, real-time toxicity detection, AI content moderation, automated harassment detecti…
- Multilingual & Indic-language support - works across languages broadly, with especially strong coverage for Indic and code-mixed text - a gap most moderation packages don't handle…
Getting started
Or require() it from plain CommonJS Node:
Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README · the project website.