jevbooks

← All projects

clef-airy

ajdunn2/clef-airy

Desktop tester for Jev, System One, and decision APIs.

Evaluation & Benchmarking0.31Runner-up: Classification & RoutingQuestionnaire
Automated README summary

Automatically summarized from the README on 7 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A Mac/Windows Electron desktop app for developers to send decision requests to Jev, Ollama System One, and Cloudflare Workers AI decision APIs, compose requests via forms or JSON, and explore structured responses.

How it uses Jev

For Jev, configure the TypeSafe AI preset with URL https://api.typesafe.ai, model jev-latest, and Bearer auth with your TypeSafe key. Compose a request with state and yes/no, choice, or score questions; the app sends it to /v1/systemone and displays the response in Easy or JSON mode.

Primitives:choicescorenoul

Technique worth stealing

Presets fill in URL and auth for Local Ollama, TypeSafe AI, and Cloudflare Workers AI, so you can switch decision backends without reconfiguring.

Try it

Download the installer from GitHub Releases, open the app, save your API URL and model in Configuration, then open Compose a request.

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.13.0
Project signals
jev-1.13.0
Category
jev-1.13.0
Pattern tags
jev-1.13.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectnot found in the excerpt0.07
  • Shows a System One patternnot found in the excerpt0.07
  • Describes handling uncertaintynot found in the excerpt0.03
  • Reports measured numbersnot found in the excerpt0.04
  • Is a runnable toolFound in material0.98
  • Top-10 learning shortlist signalnot found in the excerpt0.17
  • Is a replica of the modelnot found in the excerpt0.03
  • Solves a common problem (0–2)score on a 0–2 scale1.02 / 2
  • About JevFound in material0.96
Signals
Jev is core to the project0.07Shows a System One pattern0.07Describes handling uncertainty0.03Reports measured numbers0.04Is a runnable tool0.98Top-10 learning shortlist signal0.17Is a replica of the model0.0300.51Solves a common problem (0–2)1.02 / 2012

no-judgment band (0.40–0.60)

Design patterns
Questionnaire0.8800.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 7 Oct 2026.