Kev

Apache-2.0 tiny Jev-like decision models you train and serve locally

AI Agents / Agents · Apache-2.0 · 9.3k

Reviewed 2026-09-22 · last push 2026-10-16 · repo checked 2026-10-19

What's Good

Apache-2.0 (jaredpalmer/kev). Pretrained weights, training code, frozen eval suites, and a local serve path (`uv sync --extra serve`) that speaks a System One-compatible API so TypeSafe's Python SDK can point at your box. CUDA/ROCm/Apple Silicon notes; HF Spaces demo for trying order-sensitivity without an install. Useful when agent loops need cheap structured decisions instead of another LLM judge call.

The Catch

Vs jevals/TypeSafe Jev cloud and ordinary LLM-as-judge evals: Kev is the self-host decision-model family + training repo, not OpenLayer's jevals product wrapper and not a free hosted Jev API. 4B/9B want serious local VRAM/RAM (README cites ~32 GB Mac bf16 class for larger models); first serve downloads base + adapter weights. Decision quality still depends on your question design and calibration — local does not mean calibrated for your domain.

Verdict

Apache-2.0 self-host Jev-like decision models. Keep when you want typed agent decisions without paying per LLM-judge call; budget GPU/RAM honestly.

Embed

Maintainer? Add the badge to your README. It is free, links to this review, and there is no paid version.

Markdown

[![Reviewed on Stack Gems](https://stackgems.com/badge/kev.svg)](https://stackgems.com/gems/kev)

HTML

<a href="https://stackgems.com/gems/kev"><img src="https://stackgems.com/badge/kev.svg" alt="Kev reviewed on Stack Gems" height="20"></a>

AI Agents →

Related