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

jev-console

Desktop GUI and CLI for asking Jev Noul, Choice and Score questions by hand and reading the probabilities.

ProjectprototypeMIT
View on GitHub ↗

Overview

Jev Console is a small Tkinter desktop app and command-line tool for using Jev without writing code. You paste a state, add a few typed questions, press one button and read the returned probabilities. The CLI accepts Noul, Choice and Score questions as flags or from JSON files and can list the models your key can call.

It is for people exploring how Jev responds to their own data before building an integration. The UI is in Chinese because it was written for personal use. It depends only on the Python standard library and calls the documented endpoint POST https://api.typesafe.ai/v1/systemone directly. The README is explicit that it is not a chat client, not meant for arithmetic or date ordering, and not affiliated with TypeSafe.

What the decision model decides

TypeQuestionAnswers
OtherAny user-defined Noul, Choice or Score question about a pasted state—

How it works

  1. Set TYPESAFE_API_KEY in the environment or a .env file
  2. Paste a state and define questions in the GUI or as CLI flags
  3. Send one request to the System One endpoint
  4. Read each answer's value and probability distribution

Strengths

  • No third-party packages; standard library only
  • Quick manual experimentation before coding
  • JSON output mode for scripting

Caveats

  • GUI labels are in Chinese
  • Personal tool; not affiliated with TypeSafe
  • Requires a TypeSafe API key

Getting started

Set TYPESAFE_API_KEY, then run `python jev_gui.py` or `python jev_cli.py --state "text" --noul "urgent=Does this message convey urgency?"`.

At a glance

Type
Project
Status
prototype
Language
Python
Runtime
Tkinter desktop app and CLI
Has code
yes
License
MIT

Use cases and integrations

How curated lists describe it

  • Jev does not generate text. You send it a \*\*state\*\* plus a set of \*\*typed questions\*\*, and it answers each one with a typed value and a calibrated probability:

    logicrw/awesome-jev-projects

Frequently asked questions

What does it do?

It lets you send a state and typed questions to Jev by hand and see the probabilities.

Do I need the TypeSafe SDK?

No. It uses only Python's standard library and calls the HTTP endpoint directly.

Is it a chat app?

No. Jev does not generate text, so the console only shows typed answers.

Related projects

  • typesafe.pro

    Server behind api.typesafe.pro, a free anonymous System One-compatible endpoint that forwards to TypeSafe on the operator's key.

    Serviceproduction
  • jev-builder

    Browser form for building Jev requests from pasted text without hand-writing JSON, then rerunning to see how steady the answers are.

    ProjectbetaJavaScript
  • jev-repl

    Terminal REPL for shaping System One requests before writing code, with lessons, a sketch editor, conversation turns and offline simulation.

    ServicebetaTypeScript
  • jev.nu

    Nushell module for TypeSafe's System One API: pipe content in, ask noul, choice and score questions, and filter on the numbers.

    ServicebetaNushell
  • here-we-go-jev

    One-page playground and test bench for Jev with TypeSafe, OpenRouter, LLM-baseline and mock backends behind one /v1/systemone contract.

    ServiceprototypeTypeScript
  • jev-ai (alexsasha2750)

    Static browser interface for making structured Jev decisions through the Pollinations API, with multilingual READMEs.

    ServiceprototypeJavaScript