Back to benchmarks & research
poorjev project preview
Benchmarks & research

poorjev

Open-source, local Jev alternative: a System One decision layer with provably calibrated confidence (ECE 0.170→0.071). Typed decisions, runs offline, no API key, no waitlist.

How it uses Jev

The poor man's Jev. An open source, local-first "System One" decision layer for LLM apps: typed decisions with provably calibrated confidence . No API key. No waitlist.

Getting started

One call, one model pass, four typed answers. No prompt engineering, no JSON parsing, no "the model returned prose."

Language
Python 100%
License
MIT
Latest release
poorjev 0.1.0
Last activity
Sep 2026
Added
2026-09-21
Stars at snapshot
4
Status
Community listing
calibrationclassificationconformal-predictionjevjev-alternativellm

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.