jevcal

Stop guessing confidence thresholds: calibrate, threshold, and drift-check typed decision models (TypeSafe Jev) against an LLM teacher.

Explore repository

How it uses Jev

Built for Jev (TypeSafe's System One model), and for anything else that returns answers with probabilities.

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

Language: Python 100%
License: MIT
Last activity: Sep 2026
Added: 2026-09-18
Stars at snapshot: 10
Status: Community listing

calibrationconfidence-thresholdsjevllm-evalssystem-onetypesafe

Is this your project?

Add the badge to your README to link back here.

[![Listed in Jev Library](https://jevlibrary.dev/api/badge/abhixhek-jevcal)](https://jevlibrary.dev/projects/abhixhek-jevcal)

Something wrong, or rather not be listed? Tell us.

Keep exploring

Similar to jevcal

Browse all

typesafe-jev-calibrate-for-code-review

Benchmarks & research

About calibrating Jev for code reviews

SMade bySelmar3

jev-agent-failure-benchmark

Benchmarks & research

Benchmarking Jev (Typesafe.ai) against a strong LLM on the Who&When Pro agent-failure-attribution benchmark (text subset).

TMade byTokenTrim2

poorjev

Benchmarks & research

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.

RMade byrupeshpoojary97

jev-spec

Agent tooling

⚡ Catch spec drift on every commit: check your code against your Markdown specs with TypeSafe AI's Jev model.

NMade bynozomi-koborinai6

clear-head

Agent tooling

Claude Code Stop hook that checks an AI assistant's claims against what it actually read this session, using TypeSafe's Jev as the judge

VMade byVladyslavHontar2

jev-agent-skill-router

Agent tooling

Typed, confidence-aware agent skill routing with TypeSafe Jev.

GMade byGodsBoy17

System One adapter (Python)

Official

Official drop-in TypeSafeClient replacement backed by OpenAI, Anthropic, and compatible LLM APIs, for comparing Jev against chat models.

TMade bytypesafe-ai287

zod-jev

SDKs & clients

Zod validates the shape, Jev validates the meaning: semantic checks on request bodies become calibrated probabilities you threshold in code.

JMade byjomatsu8

jev_local

Jev alternatives & open source

Replicating Jev with a local LLM

AMade byArgos111135