Skip to content
MrJev

jev-cookbook

Fifteen runnable recipes calling Jev through OpenRouter - support triage, dedupe, PII column scanning, reranking, moderation and more - each shipping the output it produced beside it.

View on GitHub →

Checked, not fully reviewed

Fifteen runnable recipes, each shipping the output of the run that produced it. Checked, not fully reviewed: what the recipes record, not their answers.

Good for

  • Concrete starting points: triage, dedupe, PII scanning, reranking, moderation, lead scoring
  • Seeing a recipe's output before spending a cent on it

Watch out for

  • No test suite; every recipe needs an OpenRouter key to run
  • Each result rests on a few dozen hand-made rows

Tested Oct 4, 2026 at 3e0207dfcbab · Read of the repository and its fifteen result files; recipes not run, since every one needs a live key

Checked, not fully reviewed. Every recipe calls Jev through OpenRouter, so we read them and their recorded results rather than running them. No Jev calls.

Fifteen recipes, one folder each with a README, a script and sample data: support triage, database indexing, a file organiser, multi-label tagging, a taxonomy walk, record dedupe, a PII column scanner, transaction categories, extraction by picking, search reranking, log triage, moderation, lead scoring, a browser agent and a Gmail labeller.

The part worth copying is the receipts. Each recipe’s run is committed under results/ with the time it ran, the model requested and the model that answered, token usage, and what it got wrong — misses and per-field breakdowns, not only a headline. Every recipe routes on confidence and reports how many items it sent to review. The sample sets are small, a few dozen rows each and written for the recipe, so read the numbers as a smoke test of the method rather than of Jev; we do not republish them.

MIT, 35 stars. The best set of copyable examples we have seen, with the evidence beside each one.

See how it compares with other tools in Best Jev tools, tested hands-on.

Review updated Oct 4, 2026. Numbers quoted from the project are its author's own; we don't publish our own measurements of Jev.

More in Libraries & Integrations

agentrun

★ 423▲ 13

Parcha-ai/agentrun

A workflow DSL for agents with a Jev package for the steps that are decisions rather than generation.

TypeScript

switch

★ 420▲ 170

osolmaz/switch

TypeScript framework for decision-model harnesses: your program offers a short list of next steps and the model picks one at a time until it can answer, with chess, wikirace and rubric-judge examples run on Jev.

TypeScript

Ten Levels of Jev

★ 264▲ 10

disler/ten-levels-of-jev

Thirty worked uses arranged in ten levels, from one if statement to an agent that reaches for Jev itself, with a video walkthrough.

TypeScriptReviewed

Get new Jev projects every week

New Jev releases, pricing changes, and the best new projects, once a week. No spam; unsubscribe anytime.

Powered by Buttondown. See our privacy policy.