Jev builds & demos
Explore how people use Jev in browser tasks, routing, evaluation and other workflows. Follow each case to its source; reported results belong to the original authors unless a first-hand test is explicitly identified.
@lomeshdutta
Lomesh Dutta Skill Router
A Claude Code session-start hook uses Jev to rank installed skills against the user's goal.
@Frozune
Gavin's Jev Codex Model and Effort Router
A macOS Codex wrapper uses Jev to choose a model and reasoning effort from the task.
@roshanchandna
Auto-Guard for Coding Agent Tool Calls
Jev scores a proposed tool call and the user's request before code allows, escalates or blocks execution.
@qkalCanny - Supervision Layer Preventing Agent Completion Claims
Deterministic hooks and Jev guidance preventing coding agents from claiming work without evidence.
@ellipsis-devBlink - Natural Language Codebase Search with Jev Walkers
Ensemble of filesystem walkers guided by Jev to pinpoint files in large codebases.
@jerryjliu0
DocJev - Intelligent Document Splitting & Routing
Open-source document classification and packet splitting with Jev and LiteParse.
@sarah_edo
WebMCP Side Panel - Keystroke Tool Selector
A Chrome side panel that uses Jev to select and fill tools exposed by the current page through WebMCP.
@iam_zachi
pg-jev - Natural-Language Filtering in PostgreSQL
A PostgreSQL extension for filtering, ranking and classifying rows with Jev.
Jev Browser
A Jev-driven browser agent exposed as an MCP server, CLI, or library.
@TypeSafeAITypeSafe Agent Skills
Official skills that teach coding agents how to design and compose TypeSafe decision workflows.
Jev MCP
Eleven typed Jev judgment tools exposed through MCP for verification, screening, routing and review.
@tamarajtran
Instant Context Compaction
A community demonstration of using Jev to score which coding-agent context should be kept, reviewed, or dropped.
CUA-S1 Form Automation
An open 706k-parameter System 1 model specialized for mapping user data into web form inputs in 50ms.
Mastra Agent Guardrail Middleware
A single-file Mastra input processor that uses Jev to moderate the latest user message.
Pi-Heed Tool Call Auditor
An agent security supervisor that audits side-effecting tool calls against the user's explicit request.
Jev Skill Router
A fast semantic dispatcher that selects the right agent skill from large catalogs without prompt bloating.
Firehose Stream Judge
Filters live social firehoses post-by-post at $0.00003 per item, triaging high-value signals for deep analysis.
Jev-RA Reactive Browser Agent
A browser-use layer where Jev chooses the operation and target element for coding agents.
Pi Context Curator
A Pi extension that asks Jev which context units remain essential before an LLM call.
Jev Model Router
Uses Jev confidence thresholds to select among two or three configured LLM tiers.
Skillbox Tool Matcher
A self-hosted skills library with optional task-aware Jev recommendations.
@gregpr07
Flight Search with Browser Use
A browser agent searching real-world flights at 1× speed with Jev choosing each next action.
@awlevin
TypeSafe Computer Use
Open-source macOS desktop control loop with bounded Jev decisions at every single step.
@manofsteel3129
AskJev (MCP Agent)
Claude handles conversational intent while Jev directs browser navigation across live websites.
@instructa
Switchloom
A Codex model-routing experiment whose author reports no advantage in two pilots.
Jev Harness Router
One batched Jev call selects model tier, tools, skill, and effort level for each turn.
@jackbarunzJev Tool Router
Narrows MCP tool discovery for Codex using Jev and explicit fallbacks.
Jev Tool Runner
Jev selects one of a few bounded native Codex tool calls before the coding model runs.
SkillRanker (Rust CLI)
A high-performance Rust CLI where Jev ranks available agent skills for the next action.
Jev MCP Dispatcher
Executes plain-language MCP tool calls with zero general LLMs, driven entirely by Jev.
@clownwareBouncer
A Claude Code tool-call judgment hook with deterministic hard rules and Jev for ambiguous cases.
Compact Adviser
Uses Jev to recommend whether the current agent session is safe to compact.
Codex Context Diet
A Codex plugin where Jev trims bulky tool results before they pollute the agent context window.
@heyman333Jev CLI for Claude Code & Codex
A zero-dependency Jev CLI and skill for narrow coding-agent judgments.
Jev Review Action
A GitHub Action that applies typed Jev judgments to PR or catalog evidence.
Jev MCP Coding Loop
A local MCP server exposing typed Jev judgments to coding agents.
Stagehand on a remote browser
we built blazing fast computer/browser use with Jev + @Stagehanddev.
jev-trader
I built a trading bot with Jev!
jev-e2e
JEV is changes the world of E2E testing!
YouTube sponsor skipper
Just trying out Jev, I made a Chrome extension that:
@MajoSayo
LogJev
An open-source Jev-style decision layer that accepts text, images, or audio and returns bounded choices or scores.
@AIandDesignToken Saver
A Codex workflow that delegates bounded work and uses Jev Context to select relevant source excerpts before the main agent reads them.
@chriscmathewfast-jev-codex
A Codex plugin that scores tool history and restores verbatim context after compaction.
@dkhan
Jev Codex Router
Routes coding prompts to Luna, Sol, or Astra with an appropriate reasoning level.
@felpsdev07
Jev Classifier
A tool-selection layer for Codex and Claude Code that filters the available tools before expensive model calls.
@TraffAlexNewsJack
A news-intelligence workflow that uses Jev to triage stories before expensive brand-specific synthesis.
@crypto1618Jev System Architect
A coding-agent skill for finding places where fuzzy semantic logic should become an explicit Jev decision boundary.
@themsquaredJev Benchmark
A community benchmark project for testing Jev as a guardrail over risky agent tool calls.
@ersinkoc
JevBenchmarkLab
An open benchmark harness for testing Jev decision consistency, adversarial failures, option-order bias, and latency.
@hqmank
Jev Browser Skill (jb)
A standalone Playwright Chromium CLI that uses Jev to choose in-page browser actions.
Augustus
An agent skill for designing systems around Jev’s judgments.
browser-ai
A Jev browser agent in pure Go, attached to a real Chrome.
Building with Jev
A skill for writing and fixing programs that call Jev.
call-coach-ai
A sales-call coach where Jev scores what was said.
Clarity Judge
Writing checked on separate named axes, each with its own verdict.
clay-jev-people-ranker
Lead scoring in Clay, ranked by Jev instead of a prompt.
crush-monitor
Reads a WeChat thread and scores emotion, intent and reply quality.
dsh-jev-tools
Judgment, not generation, inside DeepSeek Harness.
@FBddcz
EmbodiedJev
A MuJoCo workbench for robot decisions, with Jev in the loop.
@agent-labs-dev
fastbrowse
Jev picks each action; an LLM plans; every claim cites the page.
home-assistant-typesafe
Home Assistant routes what you said through Jev, not an LLM.
@Kelbie
Hunch
Code review against rules you write in plain English.
Interlock
A gate on every agent tool call, with Jev as one of its sensors.
is-malicious
A codebase scanner that helps you not run malicious code.
@NiazMorshed2007
JCR · Jev Capability Resolver
Turns a vague agent request into a deterministic command.
@backmeupplzJev Anti-Spam Bot
A Telegram bot that deletes only the spam Jev is sure about.
@shiftynick
jev-axi
A shell CLI for agents: pick, rate, check, rank, triage and guard.
jev-browser (Playwright)
One Jev and Playwright core behind a typed SDK, a CLI and an MCP server.
Jev Browser Use
A Codex skill: Jev clicks, Codex thinks and checks the result.
jev-browser
Browser automation where an LLM plans and Jev decides.
jev-cua
A local computer-use fast path for Codex and Waku.
jev-desktop
Jev picks the action inside Codex Computer Use.
@RomanSlack
jev-drone
A simulated drone that asks Jev for a judgment 2.5 times a second.
jev-flash-router
An MCP server so coding agents stop spending tokens on small choices.
jev-harness
Every tool result is filtered by Jev before the model reads it.
jev-judgment
An agent skill that sends a coding agent’s closed judgments to Jev.
jev-mobile
Android control loops with Jev and Mobile MCP.
Jev Moderation Bot
A Discord moderation bot with Jev making the calls.
@1jehuangJev PR Labeler
GitHub PR labels chosen by Jev, with size measured as scope, not lines.
@tamaratranjev-pruner
Trims long Bash output with Jev before Claude reads it.
Jev Recruiter
A LinkedIn recruiting agent that browses profiles and saves the evidence.
jev-reflex
Claude thinks, Jev reacts: browser tasks at about 100 ms a decision.
@choxos
Jev Reviewer
Systematic-review data from trial reports, every answer a verbatim quote.
@plattypuusjev-router
A per-turn router that sends easy Claude Code or Codex work to a fast model and hard work to a stronger one.
@EliaAlberti
jev-rules
Jev picks which of your rules apply, so Claude only sees those.
@mukiwuJev Search MCP
Plain-language web search where Jev picks the sources.
jev-seo
An agent-first SEO and GEO CLI in Rust, with DuckDuckGo and Jev.
jev-skill-router
Skill routing for an agent, decided by Jev.
jev-superpowers
A skills framework for coding agents, with Jev gates and vetting.
jev-use
Say it, and your Mac does it, with no vision model.
jev-use (voice)
Voice control for macOS where Jev is the fallback, not the router.
jev-voice-browser
A browser you control by voice, from Moritz Kremb’s Jev tutorial.
@RubyBrewsday
jevcumber
Cucumber tests from the .feature file alone. No step definitions.
jevgrep
Semantic code search for agents: find behaviour, not strings.
jevmod
Moderation with a probability per category and thresholds you set.
jevwire
A decision layer for agents: MCP server, library and Claude Code plugin.
LinkedIn NoSlop
A Chrome extension that blurs low-value LinkedIn posts.
@droidrun
Mobile Jev
A mobile agent on a real Android phone, with Jev making each decision.
NanoJev
A 0.6B replica: parallel decisions in one forward pass, no decoding.
Notra
Turns your work into content, with Jev classifiers for GEO.
openjev-sglang
A public Jev-compatible API on an open model: 64 tasks in under a second.
@nourhelmipi-jev-compaction
Automatic context clearing for Pi, without losing the conversation.
@safzanpiranipi-jev-skill-picker
Ranks the Pi agent’s skills for the task in front of it.
@madeyepi-jev
A Pi extension: Jev picks the file excerpts, a local model writes the code.
playjev
Typed browser automation: Playwright acts, Jev decides.
@lykycy123
RoboJEV
Two-stage Jev control of a Franka Panda arm in MuJoCo.
Simple Jev
An open-source library that turns any Hugging Face model into a Jev-style endpoint.
Sniff Test
A prose linter for AI writing tells: regex rules plus Jev for judgment.
solari-reflex
A speed layer for computer use: one Jev decision per step.
ST-jeved
A SillyTavern extension that measures each reply before it lands.
super-jev
A small decision-to-action harness for Jev.
taste-lint
Catches AI slop in a diff before it ships.
tenbin
Split a judgment into Choice, Score and Noul, lint it, then measure it.
TipTour
A pointer companion for the Mac, with Jev driving the cursor.
Tocsin
22.8M log lines grouped into patterns, then one question each.
@plattypuustypesafe-mcp
An MCP connector that gives Claude Code, Claude Desktop, and Codex typed Jev judgments.
eve
Vercel’s open agent framework, with Jev as its default evaluate model.
@GhalebDweikatwinnow
A context sieve for Claude Code: Jev judges each tool result before it lands.
@thruwireForeman - Jev Supervision for Autonomous Codex Sessions
Software factory foreman based on TypeSafe's Jev model supervising autonomous Codex runs.
@irfndiPrism - Autonomous LP Trading Agent with Jev Market Regimes
Autonomous DLMM liquidity rebalancing with Jev detecting toxic flow and market pressure.
@vercel-labsjson-render - Generative UI Component Assembly with Jev
Vercel Labs' generative UI framework using Jev for discrete component and layout selection.
@lahfirAgent Desktop - Reliable OS Accessibility Automation in Rust
Desktop computer use via OS accessibility trees with Jev choosing stable UI targets.
@fhshaiktypesafe-mario - Direct Emulator RAM State Control with Jev
Plays Super Mario Bros. by reading structured emulator RAM without computer vision.
@emrickgarrettOneVOneJev - 1v1 Browser FPS Arena Powered by Jev
Fast-paced Three.js quickscope arena with Jev making real-time tactical decisions.
@jexpneo4jev - Graph Traversal & Relationship Classification with Jev
Navigating Neo4j graph structures by classifying the most promising edge at each node.
@AkashPriyadarshiijev-curate - High-Throughput Dataset Sifter in Rust
High-throughput synthetic and pretraining dataset sifter for TypeSafe Jev.
@montedurokillmyidea - Startup Idea Evaluation & Roaster with Jev
Input a startup idea and Jev scores it from multiple angles, outputting KILL, FIX, or SHIP.
@sharzikiSemDecide - Typed Semantic Decisions for Unix Pipelines & CI
Turn Jev into a command-line tool: classify, score, and filter directly in the Shell.
@mrnuggetjev-shell-history - Fish-Style Zsh Autosuggestions with Jev
Ranks and autosuggests past shell commands in zsh using Jev semantic relevance.
@ChetasLuajevmeter - Live Video Sentiment & Perspective Scoring Overlay
Scores statements in video transcripts sentence-by-sentence and renders a live meter edit.
@DevMortimerpi-warden - Non-Intrusive Guardrails & Loop Protection for Pi Agents
Enforces project rules on every write, catches loops, and halts unverified done claims.
@AboveColinJev for Home Assistant: Sensors, Automations & Assist
HA-Jev turns typed answers into Home Assistant sensors, automation actions, and Assist conversation decisions.
@standardagentsjevpilot - Three.js Driving Simulator with Jev Autopilot
Playable Three.js driving simulator with Jev selecting route options and speed regimes.
@TheoLeeCJSemIf - Direct Choice Probability Extraction from Open Models
Independent research reading choice probabilities directly from open model logits.
@replynodesReplyNodes - SaaS Website Messaging & Clarity Audit with Jev
Audits SaaS landing pages for product clarity, target audience fit, and conversion triggers.
@MarissaFamularoPaper Trellis - Scientific Citation Validation with Jev
Verifies whether cited papers actually support the claims made in academic text.
Jev Agent Toolkit
A portable coding-agent Skill with an optional Jev MCP bridge.
JarvisCore Jev Routing
Jev decisions for RAG classification and agent/model routing.
@ctatedev
json-render + Jev: Instant Generative UI
Chris Tate combines json-render with Jev to generate UI components, actions, and entire design system layouts in milliseconds.
JevHarness
LLM-written Jev harnesses, with reward reflection over the full trajectory.
ego-jev
One ~0.4 s typed decision per DOM step, instead of an LLM turn.
dsh-jev-prune
Context compaction for DeepSeek Harness, judged by Jev.
Agent Chaperone
Screen an agent's tool calls with Jev before they run.
JevLoop
An agent loop where the decisions cost no LLM call.
Hawk or dove?
Fed press conferences scored word by word, Jev against chat models.
jevocks
A stock terminal: Valyu brings the evidence, Jev gives the status.
fedjev-bench
Does Jev hear a rate rise coming in an FOMC statement?
codex-jev-router
Route Codex work through a Jev decision.
jev-chat-jarvis
A reply co-pilot for phone chat apps: it reads the screen and drafts, you send.
Jev-Compatible
Make an existing SGLang or vLLM deployment answer as a decision service.
jev-chat-windows
A WeChat reply helper for Windows: screenshot, local OCR, three drafts.
jev-rs
A Rust, Jev-compatible /v1/systemone engine, one prefill per judgement.
jev-test-filter
Score every test against a git diff, then emit the runner arguments.
jev-calibrate
Tune your Jev questions against your own labels, then confirm on held-out data.
jevgraph
Knowledge graphs built from typed relation decisions, with the evidence kept.
Laya
Open weights that answer typed questions in one forward pass, 33 ms on a T4.
jev-papers
A thousand arXiv papers, one Jev decision each, checked by an LLM judge.
rizzo-flow
The open, local take on Jev: typed decisions without generating a token.
JevSEO
An open-source SEO, AEO and GEO auditor that separates fixed rules from Jev judgments.
jevguide
Curated Jev showcases from X, by category, with media previews.
twitter-jev-guard
Low-quality, spam and ad posts get a translucent watermark.
hookmeter-jev
Millisecond viral hook telemetry, in a Chrome extension.
toxic-filter
Chosen expressions on X get blurred out.
Jev-as-Policy
One-click simulation setup with Jev as the control policy.
Jev Pong
Pong where the ball moves one step per model decision. Jev against the LLMs.
jev-piano
Jev can’t write a note, but with the right questions it improvises piano.
TypeEvacSafe
A fire evacuation simulation with a Jev-style decision for each person.
A leveling agent that gets cheaper as it runs
A guide-directed WoW agent designed to spend less the longer it plays.
LLM Chess: jev-latest
Jev played 80 games in a chess benchmark and made no illegal move.
@hrishirc1990jev-browser-wingman
A bounded browser-action tool for Claude Code and OpenCode on a real logged-in Chrome session.
@Pakgowithaijev-browse
One-call browser sub-tasks for Claude Code and Codex, with Jev choosing each low-level action.
@0xShikharJEV Fuse
A governed execution layer that turns Jev probabilities into deterministic policy actions.
jev-kit for Claude Code
A Claude Code kit that wires Jev into guards, sub-agent sizing, search, browsing and review.
CasaJev
A local Jev harness that builds, verifies and reuses narrow tools across agent tasks.
@AgriciDaniel
Jev SEO Audit by Daniel Agrici
A Claude Code skill and CLI that audits a live site, keeps rule checks in code, and uses Jev for typed page judgments.
@br_huni
ClearJev — Codex Prompt Model Routing
An independent Codex CLI skill where Jev selects a model for each prompt.
@miu21590Astra-Ares — Adaptive Reasoning in Codex
An experimental patched Codex CLI that uses Jev to adjust GPT-6 Astra reasoning effort mid-task.
@mika_systems
Jev Semantic Code Reading for Claude Code
A Claude Code plugin that uses Jev to locate relevant code and narrow large reads before the agent consumes context.
@svpino
Hotel Review Filtering with Jev
Compare hotels by the review details that matter to you: Wi-Fi and noise.
@mikenevermiss
Jev Skills for Routing, Guardrails and Fan-out
Reusable community skills for adding Jev decisions to agent workflows.
@jetwaniavinash
Claude Code Project Memory with jevmem
Keep useful decisions between coding sessions instead of saving every message.
@PageIndexAI
Long-Document Search with Jev and PageIndex
Find answer pages in long PDFs through a document tree.
@kraayenJon
Search and Organize Saved LinkedIn Posts
Find useful posts again in a categorized bookmark board.
@tsale
Reconstruct an Incident Timeline with Jev
Start with a confirmed malicious event and review which related activity belongs to the same incident.
@Sumanth_077
Review Data Questions and SQL Answers with Jev
Ask a SQLite question and review the generated SQL and its evidence.
@eduardo_builds
Find Answer Passages on a Web Page with Jev
Ask a page a question and jump to passages that answer it.
@dumbfook
Filter Your X Timeline with Jev
Choose unwanted topics and let Jev judge each post.
Label GitHub Issues and Pull Requests with Jev
Select existing repository labels from issue and pull-request evidence.