Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

jev-fit

Hosted checker where Jev reads a software idea and says whether plain code, Jev or a reasoning LLM fits it best.

Serviceproduction
Open source ↗Live demo ↗

This summary is based on how curated lists describe the project; its README was not available to review.

Overview

jev-fit is a hosted page and API where you paste a software idea and Jev answers a fixed typed rubric in one call. A Choice picks whether the idea is best served by plain code, Jev, or a reasoning LLM, behind a Noul gate that filters out non-tasks. Code vetoes Jev when the idea needs images, and low confidence returns 'not sure'. Results show probabilities.

It is unofficial and closed source, with a free page and API. No README was available, so details beyond the list summaries are unknown.

What the decision model decides

TypeQuestionAnswers
Yes / noIs this a real software task?—
ChoiceWhich approach fits this idea?plain code · Jev · reasoning LLM

How it works

  1. Paste a software idea
  2. Jev answers the fixed rubric in one call
  3. Code applies an image-need veto and a confidence floor
  4. Show the recommendation with probabilities or 'not sure'

Strengths

  • Quick sanity check of whether a decision model fits a use case
  • Free page and API

Caveats

  • Closed source
  • No README; method details limited to summaries

Getting started

Visit https://jev-fit.com.

At a glance

Type
Service
Status
production
Runtime
Hosted web page and API

Use cases and integrations

How curated lists describe it

  • Developer tooling: hosted fit checker that sends a pasted software idea and a fixed typed rubric to Jev in one call, where a `Choice` picks plain code, Jev or a reasoning LLM behind a `Noul` gate for non-tasks, code vetoes Jev when the idea needs images, and low confidence returns "not sure"; closed source, free page and API.

    yibie/awesome-jev

  • Paste a software idea; Jev answers a fixed typed rubric in one call and the page says plain code, Jev, or a reasoning LLM, with probabilities. Unofficial, closed source, free page and API.

    AnotiaWang/awesome-decision-models

Frequently asked questions

What does Jev decide?

Whether an idea is best built with plain code, Jev or a reasoning LLM.

Why would it say 'not sure'?

When confidence is low, or code vetoes Jev because the idea needs images.

Is the code available?

No, it is closed source.

Related projects

  • jev-research

    Guide and small prototype for using Jev with Herdr to route tasks to coding agents like Claude, Codex and Hermes under code-owned policy.

    Projectprototype
  • jev-handson

    Korean course code for attaching Jev to Claude Code, Codex and OpenClaw: skills, hooks, routers and open-model comparisons.

    ProjectproductionJavaScript
  • jev-intro-to-decision-models

    Companion code for the ZazenCodes course on decision models: primitives notebook, use-case examples and a Pi model-router build.

    ProjectproductionPython
  • Learn Jev end to end

    Free 12-notebook course building 13 agent tools with Jev as the fast decider and an LLM as the slow writer, for under $0.20.

    ProjectproductionPython
  • Jev demos

    Six side-by-side demos where Jev makes the decision, Claude or Kimi writes the words, and code owns control flow.

    AppprototypeTypeScript
  • jev-agent-harness

    Beginner manual, video script and three small examples for building an agent harness with Jev via langchain-typesafe.

    ProjectprototypePython