Jev directory
Jev for Verification
306 curated Jev resources. Check claims, citations, and outputs against a source, a schema, or a rubric.
By format
306- Docs15
- Repos & sites231
- Videos2
- Posts8
- Articles43
- Playgrounds7
Updated
All 306 Jev AI model resources for Verification
Search the full list, or filter by category, format, and tag.
InfoWorld covers a HiddenLayer report finding Jev more vulnerable than traditional LLMs to adversarial text and prompt injection, with analysts calling the methodology sound but debating whether flaw reports this early are premature.
Jev Media & TalksArticle#community#press#security
Community
The Register covers HiddenLayer's tests of Jev and a decision-tuned Qwen model: a planted ad stole a browser agent's click on a simulated store page, and tokenbreak edits snuck toxic prompts past verification. TypeSafe did not immediately respond.
Jev Media & TalksArticle#community#press#security
Community
HiddenLayer researchers tested Jev and an in-house System One-style model: on a simulated checkout page an attacker-controlled ad made the browser agent click away from the purchase, and TokenBreak-style edits lowered toxicity scores for prompts both models had flagged.
Jev Guides & ArticlesArticle#community#press#security
Community
HiddenLayer's insight post walks security teams through its Jev tests: on a simulated checkout page Jev gave the attacker ad's button 91% against 9% for Place order, and TokenBreak edits cut one prompt's toxicity score by more than two thirds so Jev stopped flagging it.
Jev Guides & ArticlesArticle#community#press#security
Community
Pillar Security analyzes Jev and System One models: a smart-home demo answered three typed questions in about 200 ms with no language model in the loop, while prompt scanning, output filtering and chain-of-thought monitoring all have nothing to inspect. TypeSafe's docs say state is not treated as hostile by default.
Jev Guides & ArticlesArticle#community#press#security
Community
Rogue Security's post uses Jev and System One models to frame agentic security as a decision problem: the same send_file action should be allowed, blocked or reviewed depending on who requested it and where the data goes, illustrated with policy case files rather than product results.
Jev Guides & ArticlesArticle#community#press#security
Community
The Injection's brief on HiddenLayer's tests: a browser agent powered by jev-ultrafast followed instructions planted in a web page and picked an attacker's ad over the real checkout button, and TokenBreak edits let toxic prompts slip past Jev's scoring. The post records no fix or response from TypeSafe.
Jev Media & TalksArticle#community#press#security
Community
VentureBeat's Louis Columbus reports Jev is spreading into agent infrastructure faster than enterprises can audit it. In one Octomind test a planted field cut a block probability from 0.76 to 0.48, and TypeSafe and Pydantic both warn inputs can steer answers.
Jev Guides & ArticlesArticle#community#press#security
Community
A Spanish-language analysis of Jev's five-day rise to critical infrastructure, the documented injection finding that moved a block verdict, and the six controls it says to add before production.
Jev Media & TalksArticle#community#press#security
Community
A calibrated image-capable 27B decision model that fits an 8 GB GPU: the JEV LoRA-and-head recipe trained on Prism ML's ternary Bonsai 2, returning typed probabilities with no generated text.
Jev Models & Reimplementations#community#open-models#local
Community
Patronus Studio's 151M-parameter Jev-like decision model for AI-agent security: given a serialized agent scene, a security question and answer options it returns calibrated probabilities in one pass, reporting 92.8 balanced accuracy on 10,576 held-out decisions.
Jev Models & Reimplementations#community#open-models#security
Community
The first v1 checkpoint of the Strands decider line from the Strands Agents team: a LoRA adapter and readout head on Qwen3.5-2B-Base that answers typed decisions with calibrated confidence, reporting 0.7792 JevBench public accuracy (180/231).
Jev Models & Reimplementations#community#open-models#local
Community
A Q8_0 GGUF of knowlet's Gemma-4-12B-Unified-System-One with a native System One decision runtime and an independently fitted GGUF temperature, shipped with an F16 mmproj for the model's native image and audio projections.
Jev Models & Reimplementations#community#open-models#quantized
Community
Perplexity AI's 27B decision model fine-tuned from Qwen/Qwen3.8-27B, producing option probabilities through a custom head instead of generated text; the card reports 85.71% overall across 11 benchmarks against Jev's 84.51%.
Jev Models & Reimplementations#community#open-models#multimodal
Community
A multiple-choice visual QA dataset for candidate-dependent evidence, published under the tudo-vn account: each item has one image, one question and two candidate sets of 3 to 10 options, each set needing a different evidence region. For research and development only; annotations are CC BY 4.0.
Jev Benchmarks & EvaluationsDocs#community#evaluation#vision
Community
Metamorphic coherence benchmark for typed probabilistic decision models: 240 synthetic cases and 2,240 questions checked by 50 probability laws, with released reports for 21 open models and 4 reference models.
Jev Benchmarks & EvaluationsDocs#community#evaluation#calibration
Community
A visual grounding dataset for decision training: 694,255 train, 24,137 validation and 6,254 test records over COCO 2017 boxes and Visual Genome attributes, with five task types and images downloaded separately.
Jev Benchmarks & EvaluationsDocs#community#evaluation#multimodal
Community
The public track of a multimodal agentic-judge benchmark for Jev-style models: 3,208 items from 16 benchmarks across five judge roles, scored on option probabilities rather than a top answer, under evaluation-only terms.
Jev Benchmarks & EvaluationsDocs#community#evaluation#calibration
Community
A self-hosted server that removes ads from podcasts before you hit play: it transcribes locally with faster-whisper or Parakeet, detects and cuts ad segments with your choice of LLM or System One, and learns sponsors across episodes.
Jev Tools & CLIs#community#github#python
Community
ttlequals0/minuspodPython
ttlequals0/minuspodPythonA local deep-research tool that turns your own PDF, DOCX, PPTX, image, TXT, or Markdown files into a structured report, using TypeSafe's Jev to rerank Qdrant chunks and verify evidence coverage while an LLM plans and writes.
Jev Tools & CLIs#community#github#python
Community
oqura-ai/deepdocPython
oqura-ai/deepdocPythonA local-first tool from Neatlogs for watching what your AI agent did: it ingests the traces your agent already sends, checks every run, and gives coding agents 23 MCP tools to read, explain, search, compare, and replay runs.
Jev Tools & CLIs#community#github#typescript
Community
neatlogs/neatrootsTypeScript
neatlogs/neatrootsTypeScriptNatural-language lookup over the US App Store top charts: describe an ambiguous feature, a look, or a name and get matching apps with how likely each one is, scored by a single Jev request over a local shortlist.
Jev Tools & CLIs#community#github#appstore
Floating real-time translated subtitles for Japanese and English video and livestreams on Android, macOS, and Windows: speech recognition runs fully offline with bundled models, translation uses your own OpenAI-compatible endpoint, and optional TypeSafe Jev helpers refine the result.
Jev Tools & CLIs#community#github#subtitles
Community
korenkrita/simul-subtitleKotlin
korenkrita/simul-subtitleKotlinAn open-source platform for creating, distributing, and running sovereign EU-compliant LLMs: one Rust binary with OpenAI- and Ollama-compatible APIs, decisions answered as probabilities in milliseconds, and an audit trail designed for the EU AI Act.
Jev Tools & CLIs#community#github#local-llm
Community
eullm/eullmPython
eullm/eullmPythonA local workbench that pairs OpenCV vision with Laya or Jev decision models: images are segmented and measured, hard rules settle the numbers, and the model gives the verdict, with one-click installers and an "open-source JEV" training path served at /v1/systemone.
Jev Tools & CLIs#community#github#python
Community
uu889/laya-opencvPython
uu889/laya-opencvPythonA source-available visual UI testing agent in Go: point it at a URL, describe the test, and a six-stage pipeline drives a real Playwright browser while Jev optionally validates requests, picks DOM targets and checks outcomes, falling back to an LLM below 0.9 confidence.
Jev Tools & CLIs#community#github#go
Community
ownweights/argusGo
ownweights/argusGoA very WIP tool for jev-ification from Harry Solovay: lessons from coding sessions become approved Markdown traits, and a configurable decision model evaluates code one trait at a time while an MCP server handles group-aware approval.
Jev Agents & MCP#community#github#typescript
Community
harrysolovay/traits-pocTypeScript
harrysolovay/traits-pocTypeScriptRead-only Go CLI that semantically checks your files against your own rules with Jev, locally or in CI, printing text or JSON and caching results between runs.
Jev Tools & CLIs#community#github#go
Community
Alurith/jeffGo
Alurith/jeffGoLocal-first MCP memory server for IDEs: tree-sitter indexing into a local ChromaDB store, plus an optional Jev layer that screens retrieved passages for relevance, evidence, contradiction and prompt injection.
Jev Agents & MCP#community#github#python
Community
KikeVen/zerikai_memoryPython
KikeVen/zerikai_memoryPythonA local stdio MCP server from bgivenb that runs whole browser and macOS goals for your agent: your agent supplies the goal, exact values, and completion conditions, and Flick loops observe, decide, and act with TypeSafe Jev. TypeScript core with Playwright and Swift drivers.
Jev Agents & MCP#community#github#mcp
Community
bgivenb/flick-computer-useTypeScript
bgivenb/flick-computer-useTypeScriptAn open-source turtle-soup (situation-puzzle) game where Jev hosts: every yes, no or irrelevant answer and the final verdict on a reconstruction come from Jev live, with confidence gating a cannot-be-sure reply. Single-player, 8-player rooms and UGC submissions.
Jev Demos & Experiments#community#github#game
A fast, typed Python framework from TrustifAI for evaluating LLMs, RAG pipelines and agents with decision models: Jev by default, Microsoft Decision-1 on OpenRouter or OpenAI's Decisions API through the same backend. It returns typed scores, thresholds and status, with optional human-label calibration.
Jev Benchmarks & Evaluations#community#github#python
Community
trustifai/typed_evalsPython
trustifai/typed_evalsPythonA single-binary gate for Impatient Programming that fails a pull request when an experienced reviewer would ask for the change to be simplified: it asks Jev about each changed file and tells the coding agent what to fix, with no LLM or parser inside.
Jev Tools & CLIs#community#github#go
Community
tools4imps/qualmGo
tools4imps/qualmGoA type-aware TypeScript linter that pins a public typescript-go compiler module and runs syntax- and type-aware rules in one AST pass per root file; its semantic mode reads changed files and asks TypeSafe Noul questions over bounded spans and candidates per policy.
Jev Tools & CLIs#community#github#typescript
An unofficial Claude Code plugin that checks 'done' claims and small judgement calls with TypeSafe Jev and keeps receipts: its done-gate can reject 'all tests pass' and ask for a real check, so evidence beats eloquence.
Jev Integrations & Adapters#community#github#claude-code
Community
ismaildasci/claude-refereeTypeScript
ismaildasci/claude-refereeTypeScriptA fast, single-pass 2B System 1 model for robots' physical judgment: it reads a short text of what a robot senses and returns probabilities for the questions that matter in the moment, scoring 0.81 on its own benchmark against TypeSafe Jev's 0.28.
Jev Models & Reimplementations#community#github#python
Community
STEERIX-home/robo-jevPython
STEERIX-home/robo-jevPythonDjaevin, a calibrated, local-first decision layer from Icaro0310 that runs behind a Devin ACP backend with no API key. It ships as an MCP server published in the official MCP Registry and installs from PyPI as poordjaevin; the repo topics name calibration, conformal prediction and NLI.
Jev Agents & MCP#community#github#python
Community
icaro0310/devin-judgePython
icaro0310/devin-judgePythonTurkish-language companion repo to the 'AI Agents Masterclass' videos: four toggleable Claude Code plugins, including a jev mod that does classification, filtering and judging with TypeSafe Jev and ships a keyless fake mode, plus pdf, hafiza and drive mods. Disabled plugins load nothing.
Jev Agents & MCP#community#github#javascript
A local Node app that asks whether an image is AI-generated: the browser measures 16 windows and a lens-fringe field and runs a bundled CLIP ViT-B/16 detector, then sends only a fixed fact dossier to JEV through OpenRouter for a verdict of likely_ai, likely_real or uncertain.
Jev Tools & CLIs#community#github#javascript
Community
GPTchatly/slop-scopeJavaScript
GPTchatly/slop-scopeJavaScriptA Pi extension that checks each agent reply against a list of skills: a classifier model, Jev by default, scores adherence from 0 to 1, and when a reply does not adhere the agent is prompted to edit it until it does.
Jev Agents & MCP#community#github#pi
Community
amalavet/pi-reply-guardTypeScript
amalavet/pi-reply-guardTypeScriptA Pi extension that watches a coding agent's transcript for five common failure modes, including loops, drift and broken requirements, and nudges the agent when it sees one. TypeSafe's Jev, a classifier model, judges the transcript rather than an LLM.
Jev Agents & MCP#community#github#pi
Community
dbreunig/pi-mast-steerTypeScript
dbreunig/pi-mast-steerTypeScriptA Python script that scores an AI agent's documented security finding with TypeSafe's Jev model, returning JSON with is_vulnerability, impactful and an impact_score from 0 to 1. It accepts structured JSON or a full text or Markdown report and can be imported by another agent.
Jev Tools & CLIs#community#github#security
Community
mhaskar/JevImpactPython
mhaskar/JevImpactPythonA beginner-friendly RAG app that answers questions about your documents using only what is written there: rag.py finds the right chunks, asks Jev to check them and gets the answer from OpenAI, while a Streamlit page shows the result with Jev's scores.
Jev Demos & Experiments#community#github#python
A screenshot hotkey redactor for macOS, Linux and Windows that blacks out API keys, tokens, emails, phone numbers, names, internal hostnames and QR codes before the image reaches the clipboard; optional AI checks use the TypeSafe Jev API.
Jev Tools & CLIs#community#github#security
Community
brainstormity/jevsnapTypeScript
brainstormity/jevsnapTypeScriptA Chrome extension and web page that checks whether a public JavaScript or TypeScript repo's README matches its code: rules and five deterministic verifiers decide what is true, Jev labels README lines with calibrated confidence, and Haiku explains the findings.
Jev Tools & CLIs#community#github#javascript
A proof-of-concept Python scanner that maps a backend codebase's attack surface and ranks likely vulnerabilities down to the suspicious line, using Jev as the classifier for about one cent per repo. It reads Python, JavaScript and TypeScript, and a demo site shows read-only results on PyGoat and NodeGoat.
Jev Tools & CLIs#community#github#security
A bridge and Claude Code plugin that runs scripts of taps, typing and swipes on iOS simulators or Android devices and has Jev judge each checkpoint's screen text, returning passed, failed or inconclusive with screenshots and a log. Saved scripts rerun from the terminal with no Claude in the loop.
Jev Integrations & Adapters#community#github#ios
A small SeleniumBase project that sends a page's reduced HTML to Jev and gets back three structured answers: whether a CAPTCHA is present, a 0-100 confidence score and which of six types it is. The README warns scores vary between runs and are not calibrated probabilities.
Jev Demos & Experiments#community#github#captcha
Community
mdmintz/jev-testingPython
mdmintz/jev-testingPythonStart here with the Jev AI model
Featured entries for verification.
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
LiteLLM's Day 0 post for TypeSafe Jev 1.14: the proxy adds box questions, image input and long-context mode on both POST /v1/systemone and POST /v1/decisions, forwarding TypeSafe-Danger-Zone headers only to TypeSafe deployments.
Jev Integrations & AdaptersArticle#community#litellm#gateway
Community
The vision sibling: the same text-trained System 1 head on Qwen3.8-27B's image encoder, taking images zero-shot, ranked first of 20 vision decision models on the community Jev Decision Index 0.3.
Jev Models & Reimplementations#community#open-models#local
Community
Jev AI model articles
Original guides that go deeper on Jev verification.
Voice agents need decisions in milliseconds. How turn detection, intent, and escalation work in real time, and where a fast decision layer fits.
Jev Practices & Patterns#voice#realtime#agents
Read article
Model deprecations and price changes are operational risks. How to pin versions, read contracts, and plan a migration before you need one.
Jev Guides & Articles#operations#vendor-risk#sla
Read article
Middleware, gateway routing, and evaluation: where a decision model fits in Vercel's AI stack, and what the gateway changes.
Jev Integrations & Adapters#integrations#vercel#ai-sdk
Read article
From the Jev community
Watch walkthroughs, read the threads, and see what builders are posting.
YouTube: One terminal, three subscriptions, and Jev picking the model for Claude Code, Codex, and Cursor.
YouTube: A podcast segment on TypeSafe AI, its $40M raise, and the Jevons paradox behind the name.
YouTube: Gary Explains the catch: Jev understands natural language but answers with structured values and confidence.
Hacker News: Show HN for the decide CLI: brew install, file context, and multi-question shell scripts.
vsekhar2 pointsShow HN: Decide – Jev decisions in the shell, scripts, and agent skillsRead the thread on Hacker NewsHacker News: Pipeable onesie CLI with shell-safety exit codes and a calibrate mode over labelled commands.
frodikarlsson3 pointsShow HN: onesie – An expressive Unix-pipeable CLI for System One models like JevRead the thread on Hacker NewsHacker News: Spoken-language learning with video scenes branching on TypeSafe Jev.
j_rcht1 pointShow HN: Worklaude – learn by speaking; video scenes branch on TypeSafe JEVRead the thread on Hacker NewsHacker News: OpenAI's Luna Decisions API framed as a fast follow to TypeSafe's Jev wave.
matt_d6 pointsOpenAI Answers TypeSafe's Jev with a Decision API Built on LunaRead the thread on Hacker News