← all repositories
v-modal/awesome-jev-tools

A field guide to AI that decides instead of chats

This awesome list catalogs public projects and patterns built on Jev, TypeSafe AI's model that emits typed decisions—booleans, scores, choices—rather than chat text.

awesome-jev-tools
Collecting fresh signals — velocity needs a few days of history.
collecting data…
star history

What it does

awesome-jev-tools is a curated directory of public projects built on Jev, TypeSafe AI’s “System One” model. Unlike a chat LLM, Jev consumes unstructured state alongside a typed question and returns a structured decision—say, a boolean, a choice, or a score—tagged with a confidence rating. The list sorts entries into categories like routing, guardrails, scoring, and agent decisions, acting as a central index for a community whose discussion was previously scattered across launch threads and social posts.

The interesting bit

The maintainers treat curation as active skepticism, not endorsement. They explicitly warn that many entries—especially bulk submissions sharing identical scaffolds—may be “considerably more prose than code” and should be treated as unproven leads. That honesty makes the list unusually useful: it maps where Jev is actually being wired into production APIs versus where it is merely being discussed.

Key highlights

  • Over 200 entries across 13 active categories, including code review, home automation, finance, and content moderation.
  • Strict gatekeeping: generic classifiers or pure theory are excluded; entries must demonstrate concrete Jev usage.
  • Two guiding questions for every entry: is this in live production, and is the decision pattern transferable?
  • Explicit warnings about bulk AI-assisted submissions that ship identical README scaffolds with little runnable code.
  • Gaps are shown, not hidden: the “Scientific Pipelines” category currently has zero entries.

Caveats

  • Several categories are still thin—Data Labeling & Curation has only 2 entries, Compliance & Legal has 1, and Scientific Pipelines has none.
  • The README repeatedly warns that inclusion does not mean a project compiles, passes tests, or contains much code; many entries are starting points, not validated tools.

Verdict

Worth a scan if you are evaluating Jev or designing typed-decision layers for agents and routing. Skip it if you need a vetted software marketplace; this is a leads board with a conscience, not a catalog of guaranteed solutions.

Frequently asked

What is v-modal/awesome-jev-tools?
This awesome list catalogs public projects and patterns built on Jev, TypeSafe AI's model that emits typed decisions—booleans, scores, choices—rather than chat text.
Is awesome-jev-tools open source?
Yes — v-modal/awesome-jev-tools is an open-source project tracked on heatdrop.
How popular is awesome-jev-tools?
v-modal/awesome-jev-tools has 553 stars on GitHub.
Where can I find awesome-jev-tools?
v-modal/awesome-jev-tools is on GitHub at https://github.com/v-modal/awesome-jev-tools.

heatdrop uses Google Analytics to see which pages get read — nothing else. Your call. How we handle data.