Skip to content

ai

Vercel AI SDK for TypeScript, whose TypeSafe provider lets apps call Jev through a shared evaluate interface.

LibraryproductionCustom license

This summary is based on how curated lists describe the project; its README was not available to review.

Overview

The Vercel AI SDK is a widely used TypeScript toolkit for building AI applications. According to the list summary, it includes a TypeSafe provider so TypeScript applications can call Jev through the SDK's shared evaluate interface, alongside its generation APIs.

The repository's top-level README is only a pointer to the package README, so the exact provider API is not documented here.

What the decision model decides

TypeQuestionAnswers
OtherTyped evaluate questions defined by the application(inferred)—

How it works

  1. Install the AI SDK and TypeSafe provider
  2. Call the evaluate interface with state and questions
  3. Receive typed probabilities
  4. Branch in application code

Strengths

  • Same SDK for generation and typed evaluation
  • Works with AI Gateway

Caveats

  • Top-level README is only a pointer; details unverified here
  • Custom licence per the listing

At a glance

Type
Library
Status
production
Language
TypeScript
Runtime
Node / edge / browser library
Has code
yes
Has tests
yes
License
Custom license

Use cases and integrations

How curated lists describe it

Frequently asked questions

How do I call Jev?

Through the SDK's TypeSafe provider and its evaluate interface, per the listing.

Is it official?

The AI SDK is Vercel's official SDK.

Where are the docs?

In packages/ai/README.md and the AI SDK documentation.

Related projects

  • 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
  • Elixir library for unified LLM calls across providers, with an evaluate interface that calls Jev via TypeSafe or OpenRouter.

    ProjectproductionElixir
  • Self-hosted multi-tenant AI agent platform listed as including optional TypeSafe client tools for classification, scoring and yes/no.

    LibraryproductionPython
  • Provider-agnostic TypeScript AI SDK; per list sources, an @tanstack/ai-typesafe adapter exposes Jev decisions through decide().

    ServiceproductionTypeScript