jev-align
Build calibrated AI Functions from human feedback using Jev and GEPA.
313 ★ on GitHub
What it is
jev-align is an experimental CLI from Sutro for building AI Functions with TypeSafe's Jev.
The homepage listed on the repository, pypi.org, puts it like this: Build and optimize AI Functions with pluggable evaluators and GEPA
Getting started
From the README:
uv tool install jev-align
export TYPESAFE_API_KEY="..." # Or use Vercel or Cloudflare below
export OPENAI_API_KEY="..." # or ANTHROPIC_API_KEY / GEMINI_API_KEY
jevaWhere the decision sits
jev-align calls the hosted decision API rather than running its own weights. That keeps the project small and means its behaviour moves whenever the vendor ships a new model version. It also means an API key and a network round trip sit in the path of every decision.
Models it references: Jev.
How active it is
Created 2026-09-19, last pushed 2026-10-28, 313 stars and 25 forks when we read it on 2026-11-02. Everything in this category is weeks old at most, so a stale push date means something different here than it would on a mature project. Check the repository before you depend on it.
Find out what your data actually supports
We turn your historical decisions into a frozen test set, then tell you which model, which threshold, and how much of it you can safely automate.