ai-cli

Vercel Labs terminal CLI that can point evaluate at Jev instead of another vibes-based judge.

What it does

ai-cli in the Jev ecosystem. Vercel Labs terminal CLI that can run Jev as the evaluation model for its evaluate command. Glue code for gateways, agents, and platforms that should stay typed instead of chatty. Tags in the wild: integrations, eval.

Skim the repo for setup, then open the demo when you want proof before you merge anything.

Vercel Labs CLI tooling in the same orbit as modern AI SDK workflows. Check the repo for how evaluate-style paths line up with gateway-hosted Jev.

Related products

Hand-picked neighbors with rich profiles or overlapping tags.

IntegrationsTypeScript5,253

DemoFeatured

eve

Vercel's agent framework with Jev wired into the experimental evaluate path, so scoring stays typed.

integrationsagentseval

Details Demo

Official205

OfficialDemoFeatured

TypeSafe agent skills

Official Claude Code / Codex skill pack for Jev primitives, patterns, and evaluation shape.

officialagentseval

Details Demo

IntegrationsPython141

Demo

pg-jev

pg-jev is a Postgres extension for people who already filter rows in SQL. The jev() function judges each row in plain language without embeddings or a vector index. Zachi's launch clip judged 129 rows in about one second for about $0.0009, with cache hits near 6 ms on a second run.

integrations

Details Demo

Agent toolingTypeScript141

pi-jev (y0usaf)

TypeSafe Jev as a decision layer for the Pi coding agent: a measured tool-call gate plus jev_ask for typed, calibrated answers.

agent-toolingagentspi

Details