研究与评测
查找探索决策模型及 Jev 相关方法的研究与评测项目。
- 2085jev-demoDecision Arena: TypeSafe's Jev vs open-source Laya playing highway-env, Snake and Blackjack with zero training, plus benchmarks and a Claude Code watchdog
nadeem4/jev-demo · TypeScript
00arenabenchmarkclaude-codedecision-modelevaluationhighway-env - 2087jev-demoIndependent demo of TypeSafe's Jev model: typed decisions with probabilities, measured side by side with OpenAI on support-ticket triage. Live local app plus a recorded replay page.
ogamircs/jev-demo · HTML
00llm-benchmarkopenaistructured-outputshtml - 2089jev-demoJEV Studio is a small Next.js evaluation lab for turning natural-language input into structured signals with the Typesafe SystemOne API.
darrenli6/jev-demo · TypeScript
00ai-agentstypescript - 2090jev-demoHistorical paper-trading simulator for evaluating TypeSafe AI JEV decisions
co1smos/jev-demo · Python
00python - 2091jev-demosDemos to test the effectiveness of TypeSafe's "Jev" System One Model
Bud-ro/jev-demos · Dart
00dart - 2092jev-dev同じ発言を jev と LLM の両方に判定させ、感情の変動値のズレと応答速度を1画面で見比べるデモ(affectus + Vercel AI Gateway)
n-yokomachi/jev-dev · TypeScript
00typescript - Researching shared-axis comparison of independent divination readings with Jev / TypeSafe AI.
mori-ikuri/jev-divination-lab · TypeScript
00typescript - Jev (TypeSafe AI System One) 生态调研:开源复现规模、JevBench v1.4.2.2 全量解读、可获取性与许可证陷阱、router 生态、Jev+安全科研切入点
freezetheflame/jev-ecosystem-research · HTML
00ai-securitybenchmarkdecision-modelllm-routerprompt-injectionragpython - Architecture for running many semantic decisions through one validated path, with a labelled 111-case benchmark comparing TypeSafe Jev against a Claude baseline, and a dashboard for inspecting any single decision. Experimental, not production.
ghubnab99/jev-enterprise-decision-fabric · C#
00agent-toolsai-safetyaspnetcorebenchmarkc#decision-makingdotnet - 2121jev-evalMeasure and calibrate TypeSafe AI's Jev on your own labeled data, and get the confidence cut-points to gate on.
CMaintz/jev-eval · Python
00python - 2122jev-eval在自己的数据上评测 TypeSafe Jev 的准确率、概率校准和可用阈值
gooooloo/jev-eval · Python
00python - 2126jev-experimentsjev-experiments: TypeSafe Jev ecosystem repository.
harlanljones/jev-experiments · JavaScript
00javascript - 2127jev-experimentsExperiments with Jev, TypeSafe's RLCD-trained decision model. 01: Jev as a tool router for MCP agents (MCP-Atlas, MCP-Bench, MCP-Universe vs OpenAI's decision model)
NeelakandanNC/jev-experiments · Python
00python - 2128jev-experimentsSmall experiments with Jev by TypeSafe
nak1b/jev-experiments · TypeScript
00ai-experimentstypescript - 2129jev-experimentsjev-experiments: TypeSafe Jev ecosystem repository.
pavan142/jev-experiments · TypeScript
00typescript - 2136jev-fanout-benchMeasured: asking TypeSafe Jev N questions in one call bills the state once. 2,976 real requests, raw data, exact billing check.
blowxian/jev-fanout-bench · Python
01benchmarkllm-costopenrouterpython - 2143jev-field-testsTwelve field tests for TypeSafe's Jev model: calibration, guardrails, résumé screening, interview rubrics and its failure modes. Bring your own API key.
fly2abhishek/jev-field-tests · Python
00classificationllm-evaluationpython - 2144jev-field-trialA pre-registered field trial of Jev (TypeSafe's judgment model) on a second brain and Claude Code history: 20 tests, bars written first, failures included, and the tools to repeat it.
NaluKicks-808/jev-field-trial · Python
00ai-agentsclaude-codeevaluationsecond-brainpython - 用 Jev 把一句自然语言设计指令拆成几道选择题,再由代码在 Figma 里画出来 · Jev decides, code draws: a Figma plugin that turns one sentence into multiple-choice questions for Jev (System One)
voidning/jev-figma-design-plugin · TypeScript
00design-automationdesign-toolsfigmafigma-pluginnatural-language - typesafe.ai model jev finance benchmark
hifizz/jev-finance-benchmark
00 - 2153jev-footballjev-football: TypeSafe Jev ecosystem repository.
gon9/jev-football · Python
00python - Testing TypeSafe Jev 1.13/1.14 image support on front/back ID card matching: accuracy, latency and cost on 56 PRADO specimens
HRyohni/jev-front-back-id-matching · Python
00python - 2160jev-game-labBloons TD 6 agent: TypeSafe Jev picks each purchase through a MelonLoader bridge, with rules in code and an optional Claude strategist
greenlittleapple/jev-game-lab · JavaScript
00bloons-td-6btd6claude-codegame-aillm-agentsmelonloadertower-defense - Compare règles, Jev et un serveur Shieldstral sur les mêmes cas français.
gbesse/jev-guardrails-fr-arena · JavaScript
00francepreuvesjavascript - 2181jev-hankoMeasuring TypeSafe AI's Jev on 41-clause contract review (CUAD, 20,500 decisions) against fast, cheap LLMs — latency, cost and F1
matu79go/jev-hanko · Python
00benchmarkcontract-reviewcuadlatencylegal-aillmopenrouter - 2182jev-harnessHarness for TypeSafe's Jev decision model: typed questions over datasets via OpenRouter, JSONL answers, summary reports.
cyanheads/jev-harness · TypeScript
00bunclassificationclicyanheadsdecision-modelharness - 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.
Gaurav-Gosain/jev-headline-bench · Go
00go - 2189jev-hftjev-hft: TypeSafe Jev ecosystem repository.
aimer1319-lgtm/jev-hft · TypeScript
00typescript - jev-integration-report: TypeSafe Jev ecosystem repository.
piratchai/jev-integration-report
00 - jev-jp-accounting-bench: TypeSafe Jev ecosystem repository.
shunmoridev/jev-jp-accounting-bench · Python
00python - 2229jev-labjev-lab: TypeSafe Jev ecosystem repository.
tanayvasishtha/jev-lab · JavaScript
00javascript - 2233jev-labTypeScript experiments, evaluations, and latency benchmarks for TypeSafe's Jev model
Menny1337/jev-lab · TypeScript
00typescript - 2242jev-lifeThe Chess of Life × Jev — an experimental game: write a new ruleset, then watch a decision model play it. | 生命棋 × Jev:实验性游戏设计——写一套新规则,然后看 Jev 怎么玩
ARCJ137442/jev-life · TypeScript
00typescript - jev-llm-benchmark: TypeSafe Jev ecosystem repository.
Chronona/jev-llm-benchmark · TypeScript
00typescript - 2248jev-llm-judgeCan a decision model replace an LLM as an eval judge? Same rubrics, scored by Jev and by an LLM, side by side.
nadheesh/jev-llm-judge · Python
00agent-evaluationevaluationllm-as-a-judgellm-evaluationpython - 2275jev-mnistHandwritten Digit Recognition on the MNIST Dataset with Jev
kaitoy/jev-mnist · Python
00mnistpython - 2287jev-nflBefore every NFL snap, a decision-only AI model (TypeSafe Jev) calls run or pass and go/punt/kick on fourth down, graded live against the coach.
gregjonesio/jev-nfl · JavaScript
00javascript - 2288jev-no-enemReproducible benchmark evaluating TypeSafe AI's Jev (System One paradigm) on Brazil's ENEM 2025 standardized exam. Evaluates typed decision-making, domain-specific accuracy, and RLCD uncertainty calibration against open LLM baselines with an interactive GitHub Pages dashboard.
patryckalves/jev-no-enem · Python
00benchmarkbrasilenemllmrlcdpython - jev-noul-vs-choice: TypeSafe Jev ecosystem repository.
TakumiNoguchi2004/jev-noul-vs-choice · Python
00python
第 251–300 条,共 389 条