shipwithjev

GitHub

375 builds · page 2 of 10

bnsd55

github.com

Jev-style parallel constrained decisions for MLX models on Apple Silicon.

GitHubResearch & data

jevmlx

zwliJay

github.com

Auditable Qwen3.5-0.8B pipeline covering data synthesis, training, calibration, fixed evaluation, Jev-compatible serving, and public model and dataset artifacts; its metrics are…

GitHubResearch & data

JevForge

abhixhek

github.com

Fits and drift-checks confidence thresholds against labeled data.

GitHubResearch & data

jevcal

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.

GitHubResearch & data

jevcache

zhuyansen

github.com

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

GitHubResearch & data

jev-search-rerank-eval

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…

GitHubResearch & data

jev-reranker

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.

GitHubResearch & data

jev-rerank-bench

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.

GitHubResearch & data

jev-rag-benchmark

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…

GitHubResearch & data

jev-orderby-bench

mahlernim

github.com

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

GitHubResearch & data

jev-korean-benchmark

4esv

github.com

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

GitHubResearch & data

jev-eval

AbdelStark

github.com

Reproducible evaluation for calibration, selective risk, and latency.

GitHubResearch & data

jev-benchmarks

RINNECODER

github.com

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

GitHubResearch & data

jev-behavior-study

QuicqDev

github.com

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

GitHubResearch & data

Jev vs. ML

hr98w

github.com

Educational MLX/Qwen vision-language experiment sharing image context across candidate-scoring questions; its probabilities are not calibrated correctness estimates.

GitHubResearch & data

Jev Visual

logan-markewich

github.com

Self-hosted implementation of Jev's System One API on the 400M-parameter GLiFormer model.

GitHubResearch & data

jeff

FirasSX914

github.com

Measures when to use Jev versus other models and routes accordingly.

GitHubResearch & data

Janus

BoundaryML

github.com

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

GitHubResearch & data

feelings

NotXf1le

github.com

Scores a finite set of choices with a model you already run in llama.cpp and returns a typed decision with a probability distribution.

GitHubResearch & data

choosekit

bespokelabsai

github.com

Open data, training recipe, and a 9B model for Jev-style choice and true/false decisions on Apple Silicon or NVIDIA GPUs.

GitHubResearch & data

Bespoke Nimble

sorrycc

github.com

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

GitHubGames & real time

typesafe-snake

phyous

github.com

Original StarCraft shareware controlled with recorded Jev action probabilities.

GitHubGames & real time

tsai-sc

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…

GitHubGames & real time

Soupbase

monteduro

github.com

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

GitHubGames & real time

killmyidea

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…

GitHubGames & real time

Jevtown

Skyvern-AI

github.com

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

GitHubGames & real time

JevScape

standardagents

github.com

Three.js driving simulation where Jev chooses among candidate paths and speeds while local code handles vehicle dynamics and geometry.

GitHubGames & real time

JevPilot

thelau

github.com

Tetris where deterministic code enumerates every reachable placement, including tucks and spins, and writes each one as an English sentence; Jev returns a probability for all of…

GitHubGames & real time

jev-tetris

valentynkit

github.com

Pokemon Red on PyBoy where deterministic code owns the route and arithmetic and Jev picks only at branches, with every battle turn's faint prediction scored by Brier against the…

GitHubGames & real time

jev-plays-pokemon-red

amycardoso

github.com

Command-palette demo where a single Choice question over a 77-command catalog turns the returned probability distribution into the per-keystroke ranking for Portuguese or English…

GitHubGames & real time

jev-palette

Dimweaker

github.com

Fine-grained robot control on LIBERO tasks with physics previews and configurable task definitions.

GitHubGames & real time

jev-libero

dabit3

github.com

Collection of inspectable Jev demos, including scripted support conversations with typed intent, escalation, and suggested-response decisions.

GitHubGames & real time

jev-experiments

gaborishka

github.com

Voice and finger-pointing control of a tldraw canvas: Jev picks the action, target shape and place from each partial transcript plus the fingertip position; deterministic code…

GitHubGames & real time

jev-canvas

vinilana

github.com

A 2D top-down car in the browser that turns its sensors into a JSON state every 200 ms and executes four typed answers.

GitHubGames & real time

Jev Self-Driving Sim

khordoo

github.com

Multi-drone simulation where typed reflexes fly the fleet and an optional slower planner may advise but never takes control.

GitHubGames & real time

Jev Reflex Autonomy Lab

denikuchero

github.com

Recorded chess experiments with a candid result: Jev on its own still blunders pieces.

GitHubGames & real time

Jev Chess Lab

AbdelStark

github.com

Browser stealth game where Jev judges guards while deterministic code owns the world.

GitHubGames & real time

heist-one

taeold

github.com

Serves DiffusionGemma-Jev behind a compatible API on Cloud Run, with a small game demo on top.

GitHubGames & real time

djev-run

emrickgarrett

github.com

Three.js quickscope arena where Jev decides movement, aiming, ADS, firing, and jumping at roughly 9 Hz.

GitHubGames & real time

1v1 Jev