Skip to content

Jev directory

Jev Tools & CLIs

770 curated Jev entries. Standalone Jev CLIs, desktop apps, playgrounds, and utilities you run directly, from shell history and semantic search to dashboards and meters.

By format

770
  • Docs10
  • Repos & sites722
  • Videos5
  • Posts8
  • Articles16
  • Playgrounds9

Updated

All 770 Jev Tools & CLIs

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

Showing 289–336 of 770 resources

0GitHub stars
A pre-action gate for tool-using agents that decides allow, confirm or block with deterministic rules before a neural decider, plus a CDP browser loop whose decider swaps between hosted Jev and a local System One-compatible server through environment variables alone.
Jev Tools & CLIs#community#catalog-import#yibie
0GitHub stars
A CLI that produces repository-aware implementation plans from two or more agents drafting independently, then has Jev score completeness, feasibility and risk coverage, decide whether cross-review is worth it, and select a finalizer that merges the strongest ideas.
Jev Tools & CLIs#community#catalog-import#logicrw
0GitHub stars
Local spam and phishing triage for a Proton Mail Bridge inbox on macOS: Jev answers two questions per new message, answers are recorded in dry-run by default, and mail moves to a Jev Review folder only if you turn that on. Nothing is ever deleted.
Jev Tools & CLIs#community#catalog-import#yibie
0GitHub stars
A Manifest V3 Chrome extension that sends each LinkedIn feed post's text to TypeSafe's Jev with a rubric of narrow yes/no and 0–2 questions, then blurs only the posts that plain code marks as filter — uncertain and failed checks stay visible, with one-click reveal.
Jev Tools & CLIs#community#catalog-import#madewithjev
0GitHub stars
A local Telegram conditional filter: FastAPI and SQLite listen on 127.0.0.1:18721, tasks batch one account's messages to TypeSafe Jev or a local Laya model, and only hits are shown, with a UI in Traditional Chinese, Simplified Chinese, and English.
Jev Tools & CLIs#community#catalog-import#logicrw
0GitHub stars
A browser 3D interior level designer that furnishes itself: Microsoft's Decision-1 yes/no model answers calibrated probabilities in one cheap batched call while deterministic code handles geometry, and completed layouts export as JSON plus a multi-mesh GLB.
Jev Tools & CLIs#community#catalog-import#madewithjev
An Android heads-up display that reads visible on-screen text through an AccessibilityService, asks TypeSafe's Jev whether a manipulative UI pattern looks likely, and shows a floating badge above 0.9 confidence — password fields are never sent and card or PIN screens are skipped.
Jev Tools & CLIs#community#catalog-import#madewithjev
Wayne Sutton's askjev.ai, built on Convex: type a question and Jev judges it rather than answering it. The site is client-rendered and thin, so this entry is grounded on its meta description and title alone.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
Blink enforces your team style guide, like AGENTS.md, by checking every file edit made by Claude Code and Codex and handing findings back to the agent inside the session in under half a second; it is mostly powered by Jev. Free public beta.
Jev Tools & CLIs#community#catalog-import#yibie
Community
Ian Nuttall's free internal linking tool crawls up to 2,000 pages, maps every internal link, and uses Jev to classify each page and its search intent before recommending link placements with anchors. Runs up to 100 pages are free.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
A syntax highlighter where code does the tokenizing and Jev does the judging: paste a file and typesafe-ai/jev names the language, colours every word, and reports which of nine lint rules the file breaks.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
A marketplace for paid services credited to Georgios Konstantopoulos: give Mercator an outcome-shaped task and it finds the right services, composes the workflow, and pays per call through MPP or x402, with Jev credited in the listing.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
A revenue-focused AI product manager that watches growth metrics across your data, investigates why numbers moved, and answers questions in Slack, over MCP or in its own charts. Self-hosting in your own cloud is offered alongside a free trial.
Jev Tools & CLIs#community#catalog-import#yibie
Community
A free Chrome extension for LinkedIn, built by Tom Frazier, that scores posts with Jev and folds suspected slop into a 44px strip you can unfold in one click. The nine-tell Slopprint shows which writing habits triggered the verdict.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
A free, no-signup tool from SuperX: pick a niche and Jev reads the last three days of X posts, asks five questions per post in one pass, and sorts each one into Read, Skim or Pass with a clarity percentage.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
A free browser-based Texas Hold'em game where Quick Play seats you against five AI poker bots, or you can build a custom table for two to six players and share its link. Supported opponents include Equity Rules, TypeSafe Jev and configurable LLM bots.
Jev Tools & CLIs#community#catalog-import#yibie
Community
KITE queries a typed behavioral kernel once per unique state, then runs populations of any size from the table, reserving an expensive flagship model for sparse paired anchors. On Epstein experiments with 9,070 participants, anchors covering 1.7% of states cut effect error by 41%.
Jev Tools & CLIsArticle#community#research#arxiv
JEV-IDS is an open experimental network intrusion detector that serializes one flow per request and asks Jev for a binary attack probability and a finite-choice traffic category. On a 300-flow NSL-KDD pilot it reports F1 0.859 and novel-attack recall 0.838.
Jev Tools & CLIsArticle#community#research#arxiv
Community
COGNIT-Guard is a safety guardrail that pairs a calibration-tuned CPU gatekeeper with confidence-gated escalation to an NPU-resident 322M direct-decision model, Laya-322M. It reports 98.85% accuracy and 0.42% benign false-positive rate on DUCS-Bench, with experience replay recovering out-of-distribution accuracy.
Jev Tools & CLIsArticle#community#research#arxiv
Community
JevSoup is a training-free framework that separates System One expert routing from System Two execution: Jev picks two LoRA experts through structured probabilities and their updates are merged with orthogonal projection. Across 14 PorTAL tasks it gains up to 1.19% task-macro accuracy over external baselines.
Jev Tools & CLIsArticle#community#research#arxiv
A system that joins coded and narrative views of 5,601,890 Texas crashes from 2017 to 2025 into population estimates: Kumo Tabular reads coded records, Jev reads narrative samples, and human judgments recalibrate the probabilities. Phone use appears in 15,074 injury crashes in narratives versus 7,340 in coded fields.
Jev Tools & CLIsArticle#community#research#arxiv
A semantic database system that answers filters, joins, classification, and ranking with fast typed decision models and escalates uncertain cases to LLMs. JEVDB-Flash posts the lowest latency on all 21 SemBench queries, and Semantic Bloom Filters remove 87.4% of join candidates on Shelob.
Jev Tools & CLIsArticle#community#research#arxiv
Community
A population-scale surveillance study in which Jev reads every Texas police crash narrative from 2017 through 2025, 5,018,079 in total, under an eight-question schema. It estimates 5,467 crashes with a documented pregnancy, including 58 documenting fetal harm.
Jev Tools & CLIsArticle#community#research#arxiv
A diagnosis-guided repair agent whose CWE classification comes from Jev. Jev beats six open-weight models on every classification and ranking metric and runs at 6.27x lower median latency than GPT-5.6-Sol; with Jev diagnosing, repair lifts the detector-measured security pass rate from 63.5% to 70.7%.
Jev Tools & CLIsArticle#community#research#arxiv
Community
A StarCraft II controller combining fast JEV action selection with persistent GPT-6 planning that defeats the strongest non-cheating built-in AI, Lv7. The combined system wins four full games at Lv5-Lv7 at a mean estimated cost of USD 3.71 per game, with a median JEV response time of 0.422 s.
Jev Tools & CLIsArticle#community#research#arxiv
An integration of Jev's decision API into edge service orchestration that extracts four to eight bounded intent fields per request. Across 33 test conditions Jev cuts median decision latency by 22.7-64.5% versus the fastest LLM, and on a live admission path it keeps 0.91-0.95 of requests exact and on time.
Jev Tools & CLIsArticle#community#research#arxiv
Community
An instrumented spatial predator-prey framework for studying communication and collective dynamics in AI agents, separating the evolving world, request scheduling, controller adapters, and experiment records. A case study reports a signals-on minus signals-off rabbit-abundance difference of -0.0095.
Jev Tools & CLIsArticle#community#research#arxiv
Community
Jev-Mobile moves mobile GUI agents to low-frequency VLM planning and high-frequency lightweight execution: the VLM specifies local goals, the accessibility tree defines a structured action space, and Jev selects actions. On AndroidWorld it reaches 79% task success against 78% for SeeAct-V.
Jev Tools & CLIsArticle#community#research#arxiv
Community
Jev-Mem is an agentic memory architecture that gives a System-One control plane charge of memory typing, query routing, retrieval budgets, graph traversal, candidate scoring, and adaptive stopping, invoking System Two only for complex reasoning and synthesis. On LoCoMo it scores 0.777.
Jev Tools & CLIsArticle#community#research#arxiv
Community
150GitHub stars
A grep that finds lines by what they mean: TypeSafe Jev answers typed questions about each line, so one query matches across Japanese, French, Russian and Chinese, and meanings combine with AND, OR and NOT.
Jev Tools & CLIs#community#javascript#cli
69GitHub stars
A drop-in proxy that distills a repeated Jev classification call into a local model as it runs: it learns from Jev's own probability distributions, then answers most requests itself while uncertain ones and a 2% audit slice keep going to Jev.
Jev Tools & CLIs#community#python#distillation
57GitHub stars
A UI testing framework where Jev scores candidate elements instead of generating next-step prose: natural-language YAML cases run through pytest and a browser agent, with Allure reports and a 458 ms median per decision.
Jev Tools & CLIs#community#python#testing
8GitHub stars
A local-first studio for building and regression-testing Jev-powered conversational state machines: define states visually, watch Jev's typed choice meet your threshold, and export runnable TypeScript.
Jev Tools & CLIs#community#typescript#state-machine
7GitHub stars
A live long-only US equities dashboard that reads Moomoo OpenD quotes and one-minute candles, runs a deterministic seven-factor setup, and asks Jev every five seconds before gating simulated or live orders.
Jev Tools & CLIs#community#python#trading
1GitHub stars
A headless Python voice-assistant daemon for Arch/Hyprland desktops and macOS: middle-click summon, DeepSeek-Flash reasoning, xAI Grok voice, about two dozen desktop tools, and optional Jev triage over memory.
Jev Tools & CLIs#community#python#voice
A logistics exception gate that reads carrier codes and free-text driver notes in one scan event and decides whether a shipment needs a human, which exception class it is, and how severe the delay looks.
Jev Tools & CLIs#community#python#logistics
Community
A localization pre-review gate that pairs source and target strings and judges meaning, terminology, tone, and placeholders as separate questions, so one failing dimension blocks a release without blending scores.
Jev Tools & CLIs#community#python#localization
Community
A podcast chaptering tool that labels transcript windows and marks boundaries as separate local judgments, classifying content, sponsor, and housekeeping segments without generating prose for the titles.
Jev Tools & CLIs#community#python#media
Community
An insurance claim triage tool that classifies loss type, scores documentation completeness, and flags fraud indicators in a first-notice-of-loss narrative, routing claims without denying any or setting a payout.
Jev Tools & CLIs#community#python#insurance
Community
A clinical intake router that picks a care pathway from a patient's reported reason for contact and flags whether the message needs a same-day response, without ever assigning a condition or a treatment.
Jev Tools & CLIs#community#python#healthcare
Community
5GitHub stars
macOS command palette that reads the frontmost app's menu tree through the accessibility API, asks Jev one Noul per menu item against a plain-language request, and presses the top match above a confidence threshold, falling back to a ranked list otherwise.
Jev Tools & CLIs#community#macos#command-palette
4GitHub stars
Python harness for GUI grounding: it divides a screenshot into grid tiles, has a vision model describe each tile neutrally, then asks typesafe-ai/jev to choose among the descriptions. Local confidence and margin gates decide whether to descend or refuse, and it emits only a point and bounding box.
Jev Tools & CLIs#community#gui-grounding#computer-use
0GitHub stars
Claude Code PreToolUse hook that asks Jev one Noul on whether a Bash command is strictly read-only and auto-approves at p of 0.95 or higher. It can only allow or stay silent, never deny, so unknown or risky commands fall back to Claude Code's normal permission prompt.
Jev Tools & CLIs#community#claude-code#hooks
Claude Code plugin whose UserPromptSubmit hook asks Jev a Choice over /effort levels (low, medium, high, max, unclear) plus a Noul on whether a hands-off request has a fuzzy spec, then offers a one-key switch before Claude starts when the tip clears its confidence threshold.
Jev Tools & CLIs#community#claude-code#plugin
Terminal agent for Polymarket's BTC Up or Down five-minute markets. Roughly every five seconds it asks Jev whether BTC finishes UP or DOWN versus the window open, then abstains or buys once and holds to resolution. Defaults to dry-run; live orders are opt-in.
Jev Tools & CLIs#community#trading#prediction-markets
OpenClaw plugin that checks every outgoing agent message against its destination channel tier, running local key-format and term rules and then five Jev Noul questions in one call through OpenClaw's decisionModel, which can point at hosted Jev or a local Kev.
Jev Tools & CLIs#community#openclaw#guardrails
A dependency-free JavaScript library that maps uploaded CSV columns onto your destination schema: a strict normalized-name pass first, then one Jev boolean per remaining source-destination pair plus a guard question per column, leaving uncertain fields visible instead of guessed.
Jev Tools & CLIs#community#csv#data-import
3GitHub stars
A bring-your-own-key Chrome extension that asks Jev one slop/not_slop Choice per X or LinkedIn post as it scrolls into view, then blurs and stamps anything at or above a configurable threshold. Scrolling never blocks, and each post is scored once from a local cache.
Jev Tools & CLIs#community#chrome-extension#moderation

Index of all 770 entries

Start here with the Jev AI model

Featured entries in tools & clis.

23.2kGitHub stars
Browser Use's ultrafast agent: Jev picks an operation and an element from an indexed action space in one request, and a small LLM writes text only when the action is TYPE_TEXT.
Jev Tools & CLIs#community#python#browser
7.7kGitHub stars
A Claude Code plugin and npm library that replaces transcript summarization with Jev keep-or-drop judgments, deleting stale tool calls and results while kept text stays verbatim.
Jev Tools & CLIs#community#typescript#claude-code
772GitHub stars
A Python asyncio runtime that puts Jev in a supervision loop above Codex or OpenCode workers: it judges completion, test sufficiency, and stuck loops, then steers, retries, or stops the job.
Jev Tools & CLIs#community#python#coding-agent

Jev AI model articles

Original guides that go deeper on Jev tools & clis.

How Home Assistant conversation agents, macOS voice pipelines, and an advisory sentinel put a fast typed decision in the loop — one call per utterance, thresholds in code, and a daily token budget.
Jev Tools & CLIs#home-assistant#voice#automation
Read article
Jev-based SEO tools split the crawl from the call: deterministic crawlers count and parse, while typed judgments rank fixes, place internal links, score search results, and track AI-answer mentions — with costs and caveats attached.
Jev Tools & CLIs#seo#search-visibility#audits
Read article
The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.
Jev Tools & CLIs#gateway#vercel#cloudflare
Read article

From the Jev community

Watch walkthroughs, read the threads, and see what builders are posting.

YouTube: AICodeKing tests support routing, refund detection, prompt-injection resistance, and browser automation.

YouTube: Retriever AI tests Jev on real browser tasks: where it worked, where it struggled, and what comes next.

YouTube: One terminal, three subscriptions, and Jev picking the model for Claude Code, Codex, and Cursor.

Hacker News: Software Bombe and live Enigma demo where Jev ranks cribs and judges plaintext.

ag_212 pointsShow HN: Jev as the Bletchley Park Analyst: A Software Bombe on EnigmaRead the thread on Hacker News

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 News

Hacker 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 News