Why would this catch sh1t or spaced-out text my denylist misses?

Keyword lists miss leetspeak, spacing, stretching, mixed-script, and romanized code-mixing. This sends the raw text to a classifier and returns calibrated probabilities, which is why obfuscated Hinglish, Tanglish, romaji, and symbol swaps are the stated focus.

Should I call isProfane and isToxic separately on every message?

isProfane() and isToxic() each trigger an inference request. Call screen() once when you need several signals together, and read isProfane, isToxic, severity, severityScore, language, obfuscation types, and action from one result.

Does the model itself decide to ban a user or censor a message?

No. Jev returns probabilities and scores for toxicity, profanity, severity, language, and obfuscation type, then the library applies deterministic policy thresholds to select the action. Ambiguous cases can route to SUSPICIOUS_REVIEW instead of forcing a binary call.

What if Jev is not the classifier I want behind the API?

Install the npm package on Node 18 or newer, create a screener with your key, and optionally pass a custom schema or your own System 1 model through the system1 option. It ships as ESM and CommonJS with bundled types.

What does screen() return that the booleans do not?

screen() returns isProfane, isToxic, a severity of NONE, MILD or SEVERE, a continuous severityScore from 0.0 to 2.0, the detected language, one primary obfuscationType plus every obfuscationTypes entry, the chosen action, the measured latencyMs and costUsd.

What are the four actions, and who chooses them?

ALLOW, SUSPICIOUS_REVIEW, AUTO_CENSOR and AUTO_BAN. The System 1 model returns only probabilities and scores; deterministic client-side thresholds turn those into the action, so ambiguous cases can route to SUSPICIOUS_REVIEW instead of forcing a binary call.

What runtime does it need, and how is it packaged?

Node.js 18 or newer, or Bun. It ships as both ESM and CommonJS with bundled TypeScript types, and installs with npm, yarn, pnpm or bun.

CommunityJev Demos & Experiments

Gg Friggin Ez

Node.js profanity and toxicity screener that sends text to a System 1 classifier with Jev as the default model and returns booleans plus severity, language, obfuscation types, action, latency, and cost.

See highlights

Open github.com

Stars: 7
Language: TypeScript
License: MIT
Published by: Community
Author: ItisShikhar
Last verified: Oct 2026

ItisShikhar/gg-friggin-ez

User repository on GitHub

View on GitHub

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.

Forks: 0
Last pushed: Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.Homepage

About this project

Fast, drop-in profanity and toxicity screener for Node.js, powered by TypeSafe AI Jev . Fast. Cheap. Catches the friggin crap. Live Demo | Quick Start | Create Custom Screener | Install | The Problem & The Solution | Custom Schemas | Demos. ⭐ Help us reach more developers and grow the community. Star this repo! Works across languages and scripts, with zero training required.

Quoted from the project's README. Read the full README.

Tagscommunity awesomejev catalog-import

Works forJev for Classification

Used inJev for Software & DevTools

Languages: TypeScript

Highlights

Exposes isProfane(), isToxic(), and screen() with a shared options argument.
Handles leetspeak, spacing, stretching, mixed-script, and romanized code-mixing.
screen() reports severity, language, obfuscation types, action, latency, and cost.
Jev is the default model and can be swapped through the system1 option.

Watch out

The configured System 1 model only returns probabilities and scores; deterministic client-side thresholds produce the ALLOW, SUSPICIOUS_REVIEW, AUTO_CENSOR, and AUTO_BAN actions. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

laya-server

Self-hosted Docker service and web UI that packages Laya structured-decision inference behind a compatible System One endpoint.

Jev Demos & Experiments#community#jevbest#catalog-import

Community

1Panel-dev/laya-serverPython

jot

General-purpose System One agent where Jev chooses tools and arguments while Jot executes them and loops until it can reply.

Jev Demos & Experiments#community#awesomejev#catalog-import

Community

runta-dev/jotTypeScript

jev-reflex-autonomy-lab

Browser drone-fleet lab where TypeSafe Jev steers each drone as fast reflexes and an optional planner offers one-use strategy advice when confidence drops, without pausing control.

Jev Demos & Experiments#community#jevbest#catalog-import

Community

khordoo/jev-reflex-autonomy-labTypeScript

x-scanner

Chrome extension that sends each X post to Jev with six typed questions in one call near the viewport, then renders a behavior chip under the post plus a session cost and latency panel.

Jev Demos & Experiments#community#jevbest#catalog-import

Community

oso95/x-scannerTypeScript

lkclean

Manifest V3 Chrome extension in TypeScript that sends each LinkedIn post to Jev and collapses bait, self-promo, off-topic, and sponsored posts into a one-line bar with reasons and scores.

Jev Demos & Experiments#community#jevbest#catalog-import

Community

stefw/lkcleanTypeScript

flue-jev-demo

Standalone Flue example that routes support chat through Cloudflare Workers AI, using gpt-4o-mini for chat and Jev for typed intent and urgency routing.

Jev Demos & Experiments#community#awesomejev#catalog-import

Community

matthewp/flue-jev-demoTypeScript

From the Jev guides

Original write-ups on what this entry is for.

Per-Tick Decisions in Games

Sep 28, 2026

A game tick is a state plus a legal action list. How Clash Royale, Minecraft, and the earlier Mario, Pokémon, StarCraft, and drone loops ask Jev one step at a time.

Jev Demos & Experiments#gaming#agents#control

Read article

Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai