The full directory

All Jev AI model resources

Entries for TypeSafe AI's flagship System One model — official docs and SDKs alongside community clients, tools, and write-ups.

Entries: 3,919
Categories: 11
Official: 102
Community: 3,817
Source sites: 293
Deep dives: 3,919

By format

3919

Docs169
Repos & sites3102
Videos74
Posts104
Articles392
Playgrounds78

Updated Nov 6, 2026

Browse the Jev AI model by category

11 ways into the ecosystem. Each category page leads with its own shortlist of starting points.

Browse the Jev AI model by use case or industry

The same directory, sliced by what you are building and who you are building it for.

Jev use cases13 ways to put Jev to work, from classification and routing to decision gating and evaluation.

Jev industries14 sectors building with Jev, from software and security to healthcare and robotics.

All 3919 Jev AI model resources

Search the full directory, or filter by category and tag.

Showing 865–912 of 3919 resources

systemone Sidecar by vstaln

A sidecar plugin that puts fast typed-decision models such as TypeSafe Jev and Laya behind two tools over one wire format (POST /v1/systemone): judge asks typed questions about a state and returns probabilities, while semantic_find scores file chunks against a plain-language query.

Jev Agents & MCP#community#github#rust

Community

vstaln/systemoneRust

Jev Context Selector

A local experiment bench that uploads PDFs, extracts and chunks their text, then generates Full, Jev and RAG comparison records for consecutive questions, storing workspaces, chunk rules and answer history in a SQLite file at .runtime/jev_context.sqlite3.

Jev Tools & CLIs#community#github#python

Community

wdwd200/jevPython

jev_test Guardrail Benchmark

A guardrail benchmark that ports the policy types of Amazon Bedrock Guardrails - six content filters, denied topics, word filters, sensitive information and contextual grounding - to TypeSafe's System One model Jev, then measures latency, cost and classification quality per case.

Jev Benchmarks & Evaluations#community#github#benchmark

Community

woojin-heo/jev_testHTML

Jev Plugin for Claude Code

A Claude Code plugin that hands Claude Code's small, frequent decisions to Jev at six points: four event hooks and two routing decisions, each a roughly one-second call that reduces permission prompts, warns when fetched content addresses the agent, re-checks done, and routes effort and model.

Jev Agents & MCP#community#github#claude-code

Community

yinjs/claude-jevTypeScript

SystemOneAffordance

A research workspace exploring visual System One models on 2D affordance tasks, predicting interaction regions for robot execution, with a five-document primer covering concepts, candidate models, prior work and first-round debugging of methods A and D.

Jev Practices & Patterns#community#github#robotics

Community

yutian929/SystemOneAffordancePython

Systemone (Hugo theme)

A Hugo theme that abstracts the editorial look of typesafe.ai and the community OpenJev site into hand-written CSS with no build step, webfonts or runtime dependencies. It is an independent design homage named after System One and does not call Jev.

Jev Tools & CLIs#community#github#hugo

Community

zetxek/systemoneCSS

Convex Evaluation Visualizer

The web visualizer for Convex Evals hosted on Netlify: browse experiments, models and recent runs, with Coding and Decision sections. The page is client-rendered, so the captured HTML shows only the shell and a loading state.

Jev Benchmarks & EvaluationsPlayground#community#benchmark#evaluation

Community

Decision Models — Jev-compatible decision API

A hosted decision API serving open-weights models behind a Jev-compatible request shape: one answer per option with probabilities for s1-fast, s1-pro and s1-vision, on a Peer-to-Peer tier or an EU tier built for GDPR. Not affiliated with TypeSafe.

Jev Tools & CLIs#community#api#hosted

Community

OpenDecision

The documentation site for OpenDecision, an open-source decision engine that runs locally and answers typed questions about text, JSON, documents and images, exposing Python, HTTP and TypeSafe-compatible interfaces with Choice, Noul, Score and Relation primitives.

Jev Guides & ArticlesDocs#community#docs#local

Community

ASSAY-001 — independent verification of Jev

Jourdan Labs' pre-registered, independently rescored audit of Jev's two launch claims: calibrated on CLINC150 (ECE 0.0204) but not on Banking77 (ECE 0.0936), and zero type errors across 8,576 responses. Protocol and receipts published in full.

Jev Benchmarks & EvaluationsArticle#community#calibration#evaluation

Community

Jev isn't tricked by ordering, and the others are.

Kyle Wild's October 13, 2026 post testing whether decision models inherit the primacy and recency effects of the LLMs underneath: Jev was not tricked by option ordering, while the other decision models he tested were. Reproduction code is linked on GitHub.

Jev Practices & PatternsPost#community#order-bias#evaluation

Community

JevChess — 3D Chess vs Jev

A 3D chess game played against TypeSafe Jev, described as realistic and mobile-friendly with Beginner, Pro and Legendary levels, free in the browser. Only the page's metadata could be recovered; the game itself is client-rendered.

Jev Demos & ExperimentsPlayground#community#game#chess

Community

Jev vs GPT-4.1 on a synthetic survey

An independent evaluation asking jev-1.13.0 and GPT-4.1 to stand in for the same 300 Twin-2K-500 respondents across 108 questions: asked as Noul, Jev led GPT-4.1's probabilities on all six measures at $4.02 versus about $136, with no arm predicting individuals.

Jev Benchmarks & EvaluationsArticle#community#evaluation#survey

Community

Jev Does Not Play Dice

Kanta Hayashi's calibration check using a hidden fair die: across 400 trials Jev picked '1' every time at an average 83% probability while being right 19% of the time, and handing forecast documents through Choice shrank a stated 30% risk to about 5%.

Jev Practices & PatternsPost#community#calibration#evaluation

Community

jevclient (PyPI)

The PyPI page for jevclient 1.3.1, an independent async Python client for TypeSafe Jev: typed Noul, Choice, Score and Box questions batch into one request, with image assets, billing tables and error classes documented in the README.

Jev Tools & CLIsDocs#community#python#sdk

Community

System-One Control Bench

A benchmark asking how well individual decisions add up to a completed task: decision and chat models steer an agent through 100 grid puzzles, where Jev chooses an optimal move in about 90% of fixed exam positions yet finishes only 57 of 100 games.

Jev Benchmarks & Evaluations#community#benchmark#agent

Community

Jev: For the Builders AND Dreamers (Jev 1.14)

The Jev Day release post: Jev 1.14.0 under jev-preview plus three danger-zone features — composable images on both models, the box question type on 1.14 only, and opt-in 262k context.

Jev Guides & ArticlesArticle#official#release#vision

Official

Images and Assets (Dreamer-Ready)

The experimental image-input reference: PNG or JPEG files in a top-level assets map, referenced by string anywhere in state, instructions, or criteria, behind the TypeSafe-Danger-Zone-Images header.

Jev Practices & PatternsDocs#official#docs#vision

Official

Box Questions (Dreamer-Ready)

The box question type: one bounding box per question, returned as four edges that are fractions of the image, plus confidence, with no criteria field and no not-found value.

Jev Practices & PatternsDocs#official#docs#vision

Official

JevCoder: When Does Decision Delegation Pay Off in Code Repair? (arXiv 2610.19596)

A code-repair workflow that delegates bounded decisions to Jev as a low-cost probabilistic judge: across 400 SWE-bench tasks it cuts mean repair-model token use by 21.6-50.6% with higher observed repair rates on three models.

Jev Practices & PatternsArticle#community#research#arxiv

Community

Are AI Decision Models Biased? A Case Study of Jev (arXiv 2610.19619)

A 41,500-response bias audit of Jev across cognitive reflection, five bias paradigms, and a pricing experiment: selected answers look robust, but probabilities move with irrelevant numbers, option order, and framing.

Jev Benchmarks & EvaluationsArticle#community#research#arxiv

Community

AgriJev: Efficient Agricultural Candidate Scoring with Multi-Scale Adapted Models (arXiv 2610.19478)

A family of adapted Qwen3.5 models from 0.8B to 9B that scores agricultural candidates in one forward call: AgriJev-9B reaches 75.44% mean accuracy across 17 test views and narrows the gap to hosted Jev 1.13.0.

Jev Models & ReimplementationsArticle#community#research#arxiv

Community

Jev-Guided Strategy Bandit: Multi-Dimensional Judge Feedback for Query-Efficient Jailbreak Attacks (arXiv 2610.19971)

A jailbreak framework that uses multi-dimensional probabilistic judge feedback to guide prompt optimization: 89.8% average HarmBench attack success across ten open-source settings under a 10-query budget.

Jev Practices & PatternsArticle#community#research#arxiv

Community

Clef Flash on Ollama

Cloudflare's 9B multimodal decision model on Ollama: text, JSON, or images in one non-autoregressive forward pass, Apache-2.0, and the lowest measured latency of any decision model in Cloudflare's Decision Index runs at 38.8 ms median.