Catalog, page 7

- Jev is a fundamentally different kind of evaluator. It returns typed answers directly instead of generating text like an LLM judge. - Jev was dramatically more consistent on…

The project combines TypeSafe Jev, GitHub Copilot CLI over the Agent Client Protocol (ACP), and a native VS Code chat participant. Together, they create a diagnostic layer for…

Eric Kang Posted on Sep 20 # Agents Make Three Decisions All Day: 18 JEV Use Cases and When Not to Use It A production agent makes the same three kinds of calls all day: pick one…

# Jev: AI Decisions as a Typed Function Call What I learned using TypeSafe's Jev for code review, and why its more surprising uses are browser control and generative UI.…

sosopop

github.com

↗

Experiment in forecasting Hong Kong stock direction: it builds a past-only state from market data, asks for an up, flat or down call, and renders a standalone report.

brainstormity

github.com

↗

Crypto terminal that reads up to 1,000 posts about a ticker alongside market and funding data and turns them into a buy, sell, hold, or take-profit call.

jomatsu

github.com

↗

Pairs local Zod shape validation with Jev semantic validation.

saibimajdi

github.com

↗

.NET SDK for Jev.

zhirschtritt

github.com

↗

Idiomatic Go SDK for the TypeSafe API.

krzyzanowskim

github.com

↗

SwiftPM client whose behaviour follows the official JavaScript SDK.

m0rphtail

github.com

↗

Security alert triage as a Unix filter: JSONL alerts in, typed decisions out.

sharziki

github.com

↗

Typed semantic decisions for Unix pipelines and CI.

kunobi-ninja

github.com

↗

Rust client, published on crates.io.

AboveColin

github.com

↗

Async Python client for typed Jev questions and probabilities.

valentynkit

github.com

↗

Neovim plugin that splits the buffer into functions with Treesitter, scores each against a plain-language question with Jev, and ranks answers by probability in the quickfix…

mrnugget

github.com

↗

Ranks existing zsh history entries for inline completion; accepting a suggestion does not execute it.

dannote

github.com

↗

Elixir/OTP client designed around GenServer replies and pattern matching.

Alurith

github.com

↗

Read-only Go CLI that checks files against rules such as unclear responsibility or weak error handling with Jev, locally or in CI.

pithings

github.com

↗

Small type-safe client for asking Jev questions about datasets.

andrelandgraf

github.com

↗

Neon Function proxy for the Neon AI Gateway.

abhixhek

github.com

↗

Fits and drift-checks confidence thresholds against labeled data.

hyperspaceai

github.com

↗

Local decision cache keyed on (model, schema, state), with redaction and canonicalisation before hashing, for cheaper repeats and deterministic replay in CI.

zhuyansen

github.com

↗

Chinese/English retrieval evaluation comparing Jev reranking with lexical, embedding, and fusion baselines, including judge-circularity analysis.

hotchpotch

github.com

↗

Retrieval and RAG: uses Jev Noul judgments to assess retrieved documents for relevance and usefulness as answer evidence, then sorts results and optionally filters them using a…

anessbelbati

github.com

↗

Fourteen-dataset reranking study with saved raw responses, paired bootstrap intervals, order-sensitivity checks, and no-relevant-document tests; comparisons remain study-specific.

erendikmenn

github.com

↗

Reproducible experiments on whether reranking with Jev improves a small RAG system, on a locked Turkish dataset, with quality, latency and cost reported together.

yodablocks

github.com

↗

Measures whether ORDER BY over a Jev probability is defensible (inversion rate, Score ordinality against a human grade, calibration, wording invariants, sort-key ties) under a…

mahlernim

github.com

↗

Small Korean/English sample study with recorded responses, including medical-text questions; not a clinical validation.

4esv

github.com

↗

Independent Jev versus GPT-5.6 Terra comparison on three labeled classification tasks, reporting accuracy, calibration, latency, and cost.

AbdelStark

github.com

↗

Reproducible evaluation for calibration, selective risk, and latency.

RINNECODER

github.com

↗

Independent synthetic-task study of Jev 1.13.0 framing sensitivity and failures, with raw responses and offline report checks.

QuicqDev

github.com

↗

Compares a typed decision model with classical classification pipelines across eight datasets, with a published protocol and an interactive report.

BoundaryML

github.com

↗

BAML language support for an AI if-statement: `.feels()` as a real, typed method backed by a decision model.

sorrycc

github.com

↗

Snake autoplayer with one typed decision per tick and code-generated legal moves.

fhshaik

github.com

↗

Super Mario Bros.

phyous

github.com

↗

Original StarCraft shareware controlled with recorded Jev action probabilities.

spoonnotfound

github.com

↗

Jev `Choice` judgments answer lateral-thinking puzzle questions and assess proposed solutions, while application code requires supported facts, a coherent explanation, and…

monteduro

github.com

↗

Startup-idea evaluator that chooses kill, fix, or ship.

gaborishka

github.com

↗

Town of 10,000 computed personas where Jev scores a post, listing, product, or headline against about 60 audience attributes to plan who sees it, then answers one batched Choice…

Skyvern-AI

github.com

↗

RuneBench-based RuneScape harness that maps Jev choices to a bounded game-action catalog and records tick-level results.