A Python toolkit for Jev requests, batch evaluation, calibration and MCP access.
Real data. Real impact.
Emerging
Developers
git clone https://github.com/docxology/daf-jev.gitPer week
Excellent
One command unlocks capabilities that would take hours to build.
A Python toolkit for Jev requests, batch evaluation, calibration and MCP access.
Builds Noul, Choice and Score questions, then combines returned probabilities through local functions.
Reuses request, failure-recording and evaluation interfaces across experiments.
Source and docs cover the client, Evaluator and MCP tools; the author’s batch-performance results were not reproduced here.
Jev is TypeSafe AI's System One decision model: it returns typed scores and choices (not free text), so agents can route, filter and gate at low latency and cost.
Source: docxology/daf-jev — 6 stars, MIT. Listed by Awesome Jev.
MIT
4,600+ AI skills, agents & workflows. Install in 60 seconds. Part of the Torly.ai family.
© 2026 Torly.ai. All rights reserved.