ai GitHub avatar by vercel

vercel /

SDK & Decision Frameworks

ai

The TypeSafe provider in AI SDK lets TypeScript applications call Jev through the shared evaluate interface.

GitHub
26,8355,158
License: Apache-2.0Language: TypeScriptLast push: 9/18/2026#multilanguage-sdk#typed-decisions

What Jev Does in this Architecture

Maps choice, score, and yes/no questions to TypeSafe System One requests and parses typed results.

Key Architecture Benefit

Reuses a common evaluation interface within AI SDK applications.

Review & Benchmark Note: The verified scope is one optional provider in the repository, not that all of AI SDK is powered by Jev or that all users use it.
Clone Repository
git clone https://github.com/vercel/ai.git

Inspect on GitHub

Check out the upstream repository README, issues, and commit log.

vercel/ai

Architecture Category

SDK & Decision Frameworks

Official & community SDKs, decision primitives, and Agent execution frameworks.

View all in this category →

Related Projects in SDK & Decision Frameworks

jev repository icon by dannote

dannote

jev

13
SDK & Decision FrameworksMITTypeScript

Integrates Jev as an asynchronous Elixir/OTP process whose replies are handled with GenServer pattern matching.

What Jev does here

Sends state and typed questions to TypeSafe, then delivers answers as messages.

Fits decision calls into existing message-handling and supervision patterns.

#multilanguage-sdk#typed-decisions
2 evidence links
Inspect details
zod-jev repository icon by jomatsu

jomatsu

zod-jev

7
SDK & Decision FrameworksMITTypeScript

Adds semantic rules to Zod validation, such as checking whether text matches a description or contains personal information.

What Jev does here

Combines semantic conditions from one parse into Jev Noul questions and maps probabilities to validation results.

Uses Zod’s error structure to attach semantic validation issues to fields.

#multilanguage-sdk#security-guardrails#typed-decisions
2 evidence links
Inspect details
daf-jev repository icon by docxology

docxology

daf-jev

3
SDK & Decision FrameworksMITPython

A Python toolkit for Jev requests, batch evaluation, calibration and MCP access.

What Jev does here

Builds Noul, Choice and Score questions, then combines returned probabilities through local functions.

Reuses request, failure-recording and evaluation interfaces across experiments.

#multilanguage-sdk#evaluation-benchmarks#mcp-integrations
2 evidence links
Inspect details