A free GitHub project directory for the TypeSafe Jev / System One model.Explore official SDKs, agent tools, open-source alternatives and Jev news.

Data updated

Research & evaluation

Find research and evaluation projects exploring decision models and Jev-related approaches.

  • Small demos of Jev (TypeSafe) through the Vercel AI Gateway: wiki race, town of agents, bullet chess, and more

    az9713/jev-projects · JavaScript

    00
    javascript
  • Put Jev in the pilot's seat of a web quiz. A Python CLI that lets TypeSafe's Jev navigate quizzes in your Chrome and logs every pick, so you can measure how it does.

    juanfabrega/jev-quiz-pilot · Python

    00
    benchmarkbrowser-automationclillm-evaluationopenrouterplaywrightpython
  • Reproducible Chinese RAG reranking benchmark for Jev (TypeSafe System One) — private during build, protocol + scripts + full logs. EN/中文.

    vicfei/jev-rag-zh-benchmark · Python

    00
    benchmarkchineseragreproducible-researchrerankingt2ranking
  • RAG evaluation with typed decisions: sentence-level hallucination verdicts with offsets and citations, passage and answer relevance, in one Jev call per answer. Benchmarked against Ragas, DeepEval, an LLM judge and HHEM.

    gabazureus/jev-ragcheck · Python

    00
    benchmarkfaithfulnesshallucination-detectionllm-as-a-judgellm-evaluationportuguesepython
  • Local Jev evaluation workbench: datasets, typed questions, threshold simulation and run comparison

    Tomdachs/jev-replay-lab · TypeScript

    00
    typescript
  • Jev-driven research engine for coding agents: query understanding, RRF reranking, shadow next-best-source, benchmarks

    Yaro60/jev-research · JavaScript

    00
    javascript
  • Score declared writing dimensions and cite only exact source spans for weak results.

    gbesse/jev-roast · JavaScript

    00
    content-qualityexplainable-ainodejstext-evaluationwriting-analysisjavascript
  • Probabilistic soft-constraint evaluation for volunteer scheduling using TypeSafe Jev, with deterministic application policy.

    WINEEL/jev-scheduling-evaluator · Python

    00
    decision-modelfastapillmnextjspythonscheduling
  • Title and abstract screening for systematic reviews with Jev: explicit criteria, include/exclude/maybe with reasons, PRISMA counts, RIS export, recall against human screeners.

    gbesse/jev-screen · Python

    00
    evidence-synthesishuman-in-the-loopliterature-screeningprismapythonsystematic-review
  • Terminal-based Jev intent triage with typed decisions, explicit simulation mode, review policy and JSON exports.

    suprkco/jev-serp-opportunity-lab · Python

    00
    evaluationpythonseostructured-output
  • A small second eval for shadcn-ui/lint that uses TypeSafe's Jev to judge the linter's own output.

    blas0/jev-shadcn-lint-eval · JavaScript

    00
    javascript
  • Test whether TypeSafe Jev answers your questions correctly before you let it decide anything.

    jonkthomas/jev-shadow · JavaScript

    00
    javascript
  • A cached Jev prior for active learning: reusable rank fusion, matched ASReview controls, and a no-key evidence replay.

    joaovaleri/jev-shortlist · Python

    00
    active-learningasreviewpythonreciprocal-rank-fusionreproducible-researchsystematic-review
  • Head-to-head Snake benchmark racing Jev against frontier LLMs from OpenRouter — same board seed, same 40-second clock, entirely in the browser.

    TranBaVinhSon/jev-snake · JavaScript

    00
    javascript
  • Tiny inputs. Instant decisions. A small experimental playground for exploring fast, probabilistic decisions with Jev.

    takafumikobayashi/jev-snap-lab · TypeScript

    00
    typescript
  • Hands-on measurements of TypeSafe's Jev via OpenRouter: integration, Chinese-language behaviour, and game loops. Every figure in the reports is reproducible by the scripts here. Reports in Chinese. ~1,430 API calls, ~$0.15.

    xiaohuaxi/jev-study · Python

    00
    python
  • Playground for TypeSafe's Jev System One model (Next.js)

    Dillettant/jev-test · TypeScript

    00
    typescript
  • Pruebita usando Jev: AI slop detector en Twitter

    frontend-army/jev-test · JavaScript

    00
    javascript
  • Empirical benchmarks, task telemetry, and engineering thesis for Jev (TypeSafe AI) System One in autonomous agentic organizations

    shaifulshabuj/jev-test · Python

    00
    python
  • Reproducible zero-shot Jev benchmark on all seven LexGLUE tasks

    chepyle/jev-test · Python

    00
    python
  • Reproducible Tetris decision benchmark comparing TypeSafe Jev with Claude Haiku

    planstack-ai/jev-tetris-benchmark · TypeScript

    00
    ai-evaluationnextjstetrisvercel-ai-gatewaytypescript
  • Demo tự chạy lại cho series Jev thực chiến (TypeSafe Jev)

    thieung/jev-thuc-chien · JavaScript

    00
    javascript
  • Applying Jev to zero-shot tool calling on the Berkeley Function Calling Leaderboard (BFCL)

    will-rice/jev-tool-calling · Python

    01
    benchmarkbfclevaluationfunction-callingllm-agentstoken-classificationtool-calling
  • 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

    sypherin/jev-trace-classifier · Python

    00
    python
  • Live demo showing why loop-speed classification matters: Jev vs LLMs on the same events, same clock, honest scorecard.

    yshraj/jev-traffic-race · TypeScript

    00
    typescript
  • Experimental PoC for Jev translation checking: bilingual benchmarks, prompt comparisons, re-verification, and MAGI voting.

    mshk/jev-translation-checker · JavaScript

    00
    javascript
  • Sample code for the Qualiteg Blog article: Jev (TypeSafe AI) hands-on, 244 API calls measured from Python

    qualiteg/jev-typesafe-demo · Python

    00
    python
  • jev-typesafe-spike: TypeSafe Jev ecosystem repository.

    frquintero/jev-typesafe-spike · Python

    00
    python
  • Testing TypesafeAI's "Jev" model using System One API

    joaomloureiro-daredata/jev-typesafeai-test · Python

    00
    python
  • 2477jev-ui
    Using jev for intelligent UI list filtering

    chrisyerga/jev-ui · TypeScript

    00
    typescript
  • Do you need TypeSafe's Jev, or is cosine similarity enough? A $0, reproducible benchmark on Banking77 intent routing.

    Madheshvivekanandan/jev-vs-cosine · Python

    00
    python
  • jev-vs-llm-benchmark: TypeSafe Jev ecosystem repository.

    sriram-um/jev-vs-llm-benchmark · Python

    01
    python
  • Side-by-side showcase: traditional LLM vs TypeSafe Jev (System One) on stock order policy decisions

    sheshisheri-hi/jev-vs-llm-stock-policy · Python

    00
    python
  • Benchmark: TypeSafe Jev vs traditional LLM on support-ticket routing accuracy, latency, and cost

    SarathChandraBellam/jev-vs-llm-ticket-router · Python

    00
    python
  • Reproducible Jev vs Luna review-classification benchmark with measured accuracy, latency, and costs.

    mameli/jev-vs-luna · Python

    00
  • Does a System One model actually beat keyword matching? A reproducible benchmark on catching disguised duplicate thesis titles. 24 cases, real production baseline, raw data and charts included.

    devnolife/jev-vs-tfidf-benchmark · TypeScript

    00
    benchmarkindonesiainformation-retrievalllmplagiarism-detectionstructured-outputtf-idf
  • A frozen decision model (JEV) as an LLM agent's world model, compared with zero-shot and LoRA-fine-tuned generative LLMs in TextWorld. Code, logs, analysis and manuscript for KIIS 2026 Fall (oral). LLM 에이전트의 월드모델: 결정모델과 범용 LLM의 비교

    thddydgnl/jev-world-model · Python

    00
    decision-modelllm-agentsloraqwen3reproducible-researchresearch-papertextworld
  • 2523jeval
    jeval: open-source evaluations for AI outputs and agents, judged by Jev

    vrash/jeval · TypeScript

    00
    typescript
  • 2524Jevals
    Jevals (jevals.com): independent benchmark of TypeSafe's Jev vs LLMs

    Jevals/Jevals

    00

301–350 of 389