Skip to content

jev-is-not-odd

Joke npm package that asks Jev whether a number is not odd or not even via the Vercel AI SDK.

Libraryprototype

Overview

jev-is-not-odd is a tongue-in-cheek npm package, in the spirit of is-odd style micro-packages, that determines whether a number is not odd or not even by asking Jev through the Vercel AI SDK. It exports isNotOdd and isNotEven, which return booleans.

It requires a Vercel AI Gateway key loaded via dotenv. It illustrates how simple a Jev call can be, but using a model for parity checks is obviously not a practical choice; Jev's own guidance is to keep arithmetic in code.

What the decision model decides

TypeQuestionAnswers
Yes / noIs this number not odd?(inferred)—

How it works

  1. Call isNotOdd or isNotEven with a number
  2. Package asks Jev via the Vercel AI SDK
  3. Return a boolean

Strengths

  • Minimal example of calling Jev from JavaScript

Caveats

  • Joke package; parity belongs in code
  • Costs an API call per check

Getting started

`npm install jev-is-not-odd`, set AI_GATEWAY_API_KEY, then `await isNotOdd(4)`.

At a glance

Type
Library
Status
prototype
Language
JavaScript
Runtime
npm library (Vercel AI SDK)
Has code
yes

Use cases and integrations

How curated lists describe it

  • A probabilistic, AI-powered utility to determine if a number is not odd (or not even) using TypeSafe's Jev model and the Vercel AI SDK.

    logicrw/awesome-jev-projects

Frequently asked questions

Is this serious?

No, it is a joke package.

Should I use a model for parity?

No; arithmetic belongs in code.

Which key does it need?

A Vercel AI Gateway key.

Related projects

  • Hack Club's lightweight LLM proxy, listed for adding a Jev forwarding endpoint behind its auth, limits and usage logging.

    MCP serverproductionTypeScript
  • Ax, a DSPy-style multi-language LLM framework, listed with a native TypeSafe provider for Boolean, Choice, Score and raw Jev questions.

    PluginproductionTypeScript
  • Effect TypeScript library whose @effect/ai-typesafe package maps classify, probability and rating operations to Jev questions.

    ProjectproductionTypeScript
  • PHP monorepo whose Polyglot module adds a TypeSafe driver for typed Noul, Choice and Score decisions alongside LLM inference.

    ProjectproductionPHP
  • Go MCP server giving any client typed Jev decisions via OpenRouter or TypeSafe, with validated answers and no paid retries.

    MCP serverproductionGo
  • Simon Willison's LLM plugin that adds Jev as a model for yes/no, choice and score questions from the command line.

    PluginproductionPython