NanoJev
TianyuCodings/NanoJev
Open 0.6B Jev replica with parallel decisions, complete probability distributions, training pipeline, weights, dataset, and live demos.
★ 1,988
JEV ECOSYSTEM / CATEGORY
Benchmarks & research
99 open source Jev projects in this category, part of AionEdge's independent index of the Jev ecosystem.
jevlike
vinnylarouge/jevlike
Train a small model that chooses among a changing list of text options, one probability per option in a single pass. Includes Doom, chess, and Wikispeedia demos.
★ 1,231
decider
Mapika/decider
One-pass typed decisions with calibrated probabilities (System One style model), fine-tuned from Qwen3.5-2B.
★ 311
jev-visual
hr98w/jev-visual
An educational Jev-like visual inference experiment on Apple Silicon: shared context, direct candidate scoring, and local visual demos.
★ 240
reflex
kshetrajna12/reflex
A small open decision model: state + typed questions -> calibrated probabilities. A Jev / System One re-creation on Qwen3.5.
★ 119
jev-eval-agent
vinilana/jev-eval-agent
Personal-assistant agent built on Vercel's eve with 100 mocked tools, measuring how many steps it takes when Jev picks the tool versus the LLM.
★ 105
open-jev (daseinlabs)
daseinlabs/open-jev
One-pass option scoring with a local Gemma 3 4B on Apple silicon via MLX, inspired by jevlike, with a Doom demo.
★ 102
jevbench
fstandhartinger/jevbench
JevBench v1 - a benchmark for Jev-class typed decision models: smart, cheap, fast, reliable, open.
★ 80
WindTunnel
nekuda-ai/WindTunnel
WebMCP benchmark comparing browser-agent interfaces, with Jev included as one of the evaluated configurations.
★ 78
★ 72
Verdict-open-jev
Heman10x-NGU/Verdict-open-jev
Non-autoregressive decision engine on ModernBERT (151M) with calibrated uncertainty (RLCD), TypeSafe AI Jev benchmark audit, and in-browser WebGPU playground.
★ 68
jevmlx
bnsd55/jevmlx
Jev-style parallel constrained decisions for any MLX model on Apple Silicon. Typed, schema-valid JSON in one forward pass.
★ 57
open-alternative-jev
ikermoel/open-alternative-jev
Open alternative to Jev: typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with benchmarks.
★ 50
mini-jev
r-ms/mini-jev
Mini-Jev: what a Jev-style typed-decision interface looks like on a frozen Qwen3-4B — read the option letter's logits instead of generating JSON. Preregistered experiment, results, teaching bench.
★ 45
LitJev
zhengxuyu/litjev
A reproduction of Jev that turns any Qwen model into a fast decision model, serving the same /v1/systemone schema (Choice, Score, Noul) with no training and no generated answer text.
★ 41
TypeAR
TypeLLM/TypeLLM
Type-safe one-decision-per-token decoding engine for autoregressive LLMs, inspired by Jev.
★ 38
typesafe-ai-benchmark
iammrduncan/typesafe-ai-benchmark
Compares Jev with other structured-output models on shared application tasks, recording errors, latency, Tokens, and estimated cost.
★ 38
jevfire
kikoncuo/jevfire
JEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks.
★ 35
system-one-open
mithalouni/system-one-open
Open replica of TypeSafe's Jev: typed calibrated decisions in one forward pass, on Gemma 4 E2B / Gemma 3 270M (Modal).
★ 32
Jev_apps
JackZeng/Jev_apps
看看 Jev 能做什么：用中英文讲清热门应用、工作原理和各自优缺点。Explore Jev apps with plain-language examples, explanations, and comparisons.
★ 31
openjev (zhihz)
zhihz/openjev
Local bilingual probability decisions from context, questions, and candidate answers. Independent research preview inspired by TypeSafe Jev.
★ 31
system-one
sgoedecke/system-one
Batched single-token choice inference for open language models, compatible with TypeSafe.
★ 29
jev-curate
AkashPriyadarshii/jev-curate
A Rust dataset-filtering experiment using Jev scores to keep or reject text records.
★ 26
jevify
altryne/jevify
An Agent Skill for finding suitable Jev decision points and designing questions and comparison experiments.
★ 24
jev-on-a-laptop
rorshopping/jev-on-a-laptop
Unofficial study: Jev-style parallel typed decisions on stock 1.5B-8B models on an Apple Silicon laptop. Benchmarks, research notes, and a Hugging Face Space demo.
★ 23
jev-column-race
goodrahstar/jev-column-race
Jev vs Gemini 3.8 Flash: labelling 1,000 app reviews, 4.1× faster and 7× cheaper.
★ 22
jevgpt
Bewinxed/jevgpt
A chatbot built on a model that cannot generate text (TypeSafe AI's Jev, driven autoregressively).
★ 21
jev-benchmarks
AbdelStark/jev-benchmarks
A benchmark comparing Jev and GLiNER on text classification, probability calibration and selective automation.
★ 17
jevbetter
olanotolu/jevbetter
A stronger one-pass scorer over a variable list of text options: hashed n-gram encoder, rival-aware attention, gated head, temperature scaling, benchmarked against jevlike.
★ 14
★ 13
jev_stock
sosopop/jev_stock
An experimental JEV-powered framework for forecasting short-term stock price direction from structured market data.
★ 12
jev-harness
AntonioCoppe/jev-harness
Decision harness for TypeSafe Jev — confidence gates, shadow mode, recipes, and evals. Claude CLI 48.9s → Jev 1.3s on the same row-filter job.
★ 10
jevcal
abhixhek/jevcal
A toolkit for evaluating Jev probabilities on labeled data, selecting confidence thresholds and checking model drift.
★ 10
typesafe-local
aabolfazl/typesafe-local
Inspired by TypeSafe Ai, Ask a local LLM typed questions, get calibrated probabilities instead of text. Structured output without generation or parsing. MLX / Apple Silicon.
★ 8
jev-rerank-bench
anessbelbati/jev-rerank-bench
Can a decision model beat dedicated rerankers? TypeSafe Jev vs Cohere Rerank 4 vs ZeroEntropy zerank-2 vs a chat-model baseline: 14 datasets, every raw API response, bootstrap ranges on every gap.
★ 6
trade-jev
justinhe16/trade-jev
Backtest Jev (TypeSafe) as a BUY/SELL/HOLD trader on NQ L10 order-book data.
★ 6
jev-korean-benchmark
mahlernim/jev-korean-benchmark
Reproducible early-access evaluation of Jev on Korean understanding and medical text, with runtime and cost evidence.
★ 6
jev-benchmark
wondertwins/jev-benchmark
Benchmarks and a playground for TypeSafe's Jev (System One) model: chess, and who-is-the-player-talking-to for speech-to-text game NPCs.
★ 6
jev-lm
y0usaf/jev-lm
A word-level generation experiment that asks Jev to select words or verify locally drafted continuations.
★ 6
jev-search-rerank-eval
zhuyansen/jev-search-rerank-eval
Does a TypeSafe Jev rerank beat embedding search? Graded relevance eval (9,831 pairs, 164 zh/en queries) over the Agent Skills Hub catalog, with the judge-circularity bias measured.
★ 6
daf-jev
docxology/daf-jev
A Python toolkit for Jev requests, batch evaluation, calibration and MCP access.
★ 5
LegalForecastBench
johnhughes3/LegalForecastBench
LegalForecast-MTD benchmark alpha and official evaluation workflows.
★ 5
jev-little-airways
lbotinelly/jev-little-airways
An island-airport simulator using Jev for routes, yielding, emergency broadcasts and landing order.
★ 5
mcts-agent
lhemerly/mcts-agent
Discriminative Monte Carlo Tree Search using TypeSafe Jev System One Primitives and Gemini.
★ 5
jev-ood-calibration
scienthoon/jev-ood-calibration
Reproducible evaluation of Jev calibration on synthetic support tickets and public classification benchmarks.
★ 5
system-one-gemma
akash-kamat/system-one-gemma
Open-source Jev-style System One decision model. Gemma 3 270M with a scoring head — fast, calibrated decisions in a single forward pass. No text generation. Inspired by TypeSafe.ai's Jev.
★ 4
jev-phishing-bench
anisselbd/jev-phishing-bench
Jev (TypeSafe) vs Claude Haiku 4.5 on 2 000 phishing emails: accuracy, calibration, latency, cost. Reproducible benchmark.
★ 4
typed-decisions
kotoba-lang/typed-decisions
Jev-shaped typed-decision models with measured latency, accuracy, calibration, and training cost.
★ 4
qwen-rlcd
shamazharikh/qwen-rlcd
Jev-style calibrated decision model (Choice/Score/Noul) on Qwen3.5-0.8B.
★ 4
openjev (DECRUX9812)
DECRUX9812/openjev
Open, local reimplementation of a Jev-style decision layer for job postings.
★ 3
jev-for-engineers
Foadsf/jev-for-engineers
Eight mechanical and electrical engineering experiments using Jev for task routing, log checks and component selection.
★ 3
jev-gate
MongLong0214/jev-gate
Not every coding task needs your best model. Experimental Jev-powered model routing for Claude Code — V3 prototype runs today, V4 routes at the task boundary.
★ 3
jev-behavior-study
RINNECODER/jev-behavior-study
An independent Jev 1.13.0 behavior study recording successes and failures across question framing, input conditions and games.
★ 3
jev-exploration
SamuelSacco/jev-exploration
A research repository tracking Jev claims and limitations, with calibration experiments and runnable examples.
★ 3
jev-chat
adhyaay-karnwal/jev-chat
A chatbot from typed Jev decisions: hierarchical speculative decoding over System One probabilities.
★ 3
jev-dspy-lab
jmanhype/jev-dspy-lab
Reproducible calibration and selective-risk benchmarks for Jev/TypeSafe decisions in DSPy workflows
★ 3
calibre
FirasSX914/Janus
Calibration and confidence-based routing measured on Banking77: 80.2% accuracy at $0.103 per 500 decisions.
★ 2
jev-sec-bench
Gaurav-Gosain/jev-sec-bench
Blind security benchmarks for Jev, TypeSafe's System One model: prompt injection and vulnerable code detection, built on jev-go.
★ 2
jev-agent-failure-benchmark
TokenTrim/jev-agent-failure-benchmark
A benchmark using Jev to attribute multi-Agent failures to an Agent, step and error type.
★ 2
jev-routing-experiment
TokenTrim/jev-routing-experiment
Benchmarking TypeSafe's Jev decision model as a cost-efficient LLM router on RouterArena.
★ 2
jev-research-eval
jgridifier/jev-research-eval
Reproducible Jev Ultrafast research-browser eval harness + field note (QC’d cases, suite runner, report generator). Not investment advice.
★ 2
paper-package
CompleteDotTech/paper-package
Reproducible Jev research manuscript, evidence, and paper package.
★ 1
jevals-data
Jevals/jevals-data
Independent benchmark data for TypeSafe's Jev (System One model) vs LLMs: accuracy, calibration, cost. Boards + per-decision logs, CC-BY-4.0
★ 1
PocketJev
NullPo-jp/PocketJev
On-device iPhone visual decision tool using MLX and Qwen3-VL direct option logits.
★ 1
jev-synergy-screening
PistachioAIHQ/jev-synergy-screening
A Jev title-and-abstract screening experiment compared with Cohen Abstract Triage labels for an ADHD review.
★ 1
decisionbridge
grishahq/decisionbridge
A Jev-inspired decision interface for existing LLMs. Explicit choices, scores, calibration, and review thresholds.
★ 1
★ 1
jev-freeform
kesku/jev-freeform
An observable raw-character chat experiment powered entirely by TypeSafe Jev Choice.
★ 1
kyotsu-ai-bench
shibadogcap/kyotsu-ai-bench
AI benchmark on Japan's 2026 Common Test: Jev vs luna-none vs luna-low (static dashboard).
★ 1
jev-secret-detection
teyhouse/jev-secret-detection
Measures how well TypeSafe's RLCD-Jev model spots real secret credentials in file snippets.
★ 1
openjev-experiments
zefir1990/openjev-experiments
Experiments with openjev, an open Jev-style option-logit runner, on local models.
★ 1
padflow-jev-evals
zsavage8/padflow-jev-evals
Typed-decision benchmark from PadFlow (land development SaaS): schemas, anonymized labeled rows, and a runner for confidence-calibrated models like TypeSafe Jev.
★ 1
Typesafe_chess_eval
AliceRoselia/Typesafe_chess_eval
An evaluation of typesafe AI chess. As it turns out, the AI isn't doing really well even though chess is not a particularly open-ended game. Still, it's only a prototype and this probably wasn't optimzied for games.
★ 0
jev-alpha-bench
Gaurav-Gosain/jev-alpha-bench
Does Jev predict stock returns from news? It reads the news well; there is no tradeable alpha. Three arms separate reading from recall.
★ 0
jev-headline-bench
Gaurav-Gosain/jev-headline-bench
Can Jev pick the winner of a real headline A/B test? 64.5% across 10,984 Upworthy randomized experiments, 74.7% when the difference was decisive.
★ 0
jev-report
HackSing/jev-report
发明 RLHF 的人，这次做了个不会说话的模型：Jev 独立研究报告。52 页 PDF + 50 条中文实测复现包 + 143 条可回溯数据表.
★ 0
jev-lab
Menny1337/jev-lab
TypeScript experiments, evaluations, and latency benchmarks for TypeSafe's Jev model.
★ 0
jev-spam-eval
bitnovus/jev-spam-eval
Zero-shot spam filtering with TypeSafe Jev Noul questions, compared with TF-IDF baselines.
★ 0
jev-shadcn-lint-eval
blas0/jev-shadcn-lint-eval
A small second eval for shadcn-ui/lint that uses TypeSafe's Jev to judge the linter's own output.
★ 0
system-one-adapter-rust
codeitlikemiley/system-one-adapter-rust
Rust port of TypeSafe system-one-adapter (LLM-backed system_one evaluations).
★ 0
jev-deferred-crispification
dnakhoa/jev-deferred-crispification
Position paper: the Hidden-Markov and fuzzy primitives missing from TypeSafe AI's Jev and System-One decision models. Two lemmas, one principle (Deferred Crispification), one architecture (BSF-S1).
★ 0
jev-playground (hegargarcia)
hegargarcia/jev-playground
Benchmarks Jev against other evaluation models in games with explicit states, legal actions, and measurable outcomes.
★ 0
★ 0
jev-calibration-audit
jujumilk3/jev-calibration-audit
Audits Jev calibration, option-wording effects and Korean judgments through public APIs and datasets.
★ 0
labs
kiarina/labs
Research workspace containing reproducible TypeSafe Jev evaluation and safety-judgment experiments.
★ 0
jev-anotacao-sentencas
lab-dados/jev-anotacao-sentencas
Jev (TypeSafe) vs. Gemini 3.8 Flash vs. GPT-5.6 Luna na anotação estruturada de sentenças do TJSP: qualidade, tempo e custo.
★ 0
jev-vs-luna
mameli/jev-vs-luna
Reproducible review-classification comparison measuring Jev and Luna accuracy, latency, and cost.
★ 0
misereru-slide-jev
myokoym/misereru-slide-jev
Ongoing Japanese research deck on Jev and System One models, maintained as Markdown slides.
★ 0
shade-arena-jev-monitor
nican2018/shade-arena-jev-monitor
Evaluating TypeSafe's Jev as a fast monitor and action gate for agent sabotage in SHADE-Arena, compared with Gemini 2.5 Flash/Pro.
★ 0
jev-certify
nikkoxgonzales/jev-certify
Research toolkit applying conformal risk control and prediction-powered inference to certify Jev routing thresholds.
★ 0
jev-eval
onlyoneaman/jev-eval
TypeSafe's Jev vs gpt-5.4-mini and gpt-5.6-luna on four public classification sets: cases, per-item answers, scoring, charts
★ 0
jev-jp-address
smasato/jev-jp-address
Jev (TypeSafe) 性能評価プロジェクト — 日本郵便 KEN_ALL をマスタに、AI SDK 経由の Jev が住所のあいまい一致にどこまで使えるかを検証.
★ 0
jev-trace-classifier
sypherin/jev-trace-classifier
Application of TypeSafe Jev (noul judgment primitive) on the collusion.wiki corpus: agent vs human page authorship, head-to-head vs local Qwen3.8-Flash-Next.
★ 0
FinancialPredictionJev
thodoh1/FinancialPredictionJev
Using Jev to test how well it predicts financial markets(just like most llms as of september 2026, it doesnt do that good).
★ 0
typesafe-oracles
trophee-bot/typesafe-oracles
Evaluating TypeSafe's System One primitives (Choice/Score/Noul) — where a typed oracle beats an LLM call.
★ 0
jev-pick-and-place-study
tryaksh/jev-pick-and-place-study
A small reproducible MuJoCo pilot comparing Jev, Claude Haiku, and reactive rules for pick-and-place.
★ 0
thaiexam-jev-charts
vehas/thaiexam-jev-charts
Charts: TypeSafe Jev evaluated on Thai standardized exams vs 110 other models.
★ 0
jev-evaluation
willkelly/jev-evaluation
Adversarial Jev evaluation suite with preregistered predictions, request logs, and reproducible experiment artifacts.
★ 0
jev-orderby-bench
yodablocks/jev-orderby-bench
Does ORDER BY over a Jev probability put rows in a defensible order? Independent ranking, calibration and invariant measurements of TypeSafe AI's Jev: passes six pre-registered gates on 360 labeled rows, fails four of six on graded product relevance.
★ 0