89 curated builds·evidence labeled
COMMUNITY & PRODUCTION DIRECTORY

Real Jev Agent Implementations

Live demonstrations, open-source repositories, and sourced benchmarks where developers put Jev into production loops. Filter by architecture pattern or explore video breakdowns below.

Showing 41 sourced implementations (github)
Clear filters ×
JO
Joey Kudish
Jev Browser
DEMO

Jev Browser

A Jev-driven browser agent exposed as an MCP server, CLI, or library.

Latency: ~4s end-to-end for that reported exampleCost: $0.0016 for one reported Wikipedia navigation example
Browser AgentsJevPlaywrightGitHub
TY
TypeSafe AI

TypeSafe Agent Skills

Official skills that teach coding agents how to design and compose TypeSafe decision workflows.

MCP / SkillsClaude Codeskills.shGitHub
JO
Joey Kudish

Jev MCP

Ten typed Jev judgment tools for verify, screen, find, rerank, classify, decide, compare, extract, review, and gate.

Latency: Project reports roughly 150–500ms for most judgments
MCP / SkillsMCPJevGitHub
CU
Cua
CUA-S1 Form Automation
DEMO

CUA-S1 Form Automation

An open 706k-parameter System 1 model specialized for mapping user data into web form inputs in 50ms.

Latency: ~50 ms per form fill pass
Browser AgentsCua S1PlaywrightGitHub
CO
CodeAlive

Mastra Agent Guardrail Middleware

A single-file drop-in middleware for Mastra agent workflows that screens prompts and tool parameters in ~400ms.

Latency: ~0.4 s median latency
GuardrailsMastra AIJev ChoiceGitHub
BO
Bowen Xu

Pi-Heed Tool Call Auditor

An agent security supervisor that audits side-effecting tool calls against the user's explicit request.

GuardrailsPi AgentJev ScoreGitHub
DE
Dewaldt Huysamen

Jev Skill Router

A fast semantic dispatcher that selects the right agent skill from large catalogs without prompt bloating.

Tool SelectionJev ChoiceAgent RuntimeGitHub
LE
Leo Mata

Firehose Stream Judge

Filters live social firehoses post-by-post at $0.00003 per item, triaging high-value signals for deep analysis.

Cost: ~$0.00003 per post
Agent RoutingBluesky AT ProtocolJev ChoiceGitHub
BR
Brian Kim

Jev-RA Reactive Browser Agent

A fast browser automation loop where Jev decides the next interaction in ~300ms.

Latency: ~300 ms per step
Browser AgentsJevPlaywrightGitHub
SH
Shashank H

Pi Context Curator

An active memory curator that scores and prunes agent working context to prevent context drift and bloat.

Agent EvaluationPi AgentJev ScoreGitHub
RA
Raj Dhakad

RouteKit Complexity Router

Classifies task complexity in milliseconds to route between small utility models and frontier reasoning agents.

Agent RoutingJev ChoiceOpenAI / Anthropic SDKGitHub
KI
Kitze

Skillbox Tool Matcher

A self-hosted agent skills library with Jev-powered semantic recommendation and tool catalog routing.

MCP / SkillsMCPJev ChoiceGitHub
Gregor ZunicGregor Zunic@gregpr07
Flight Search with Browser Use
DEMO

Flight Search with Browser Use

A browser agent searching real-world flights at 1× speed with Jev choosing each next action.

Run time: ~7 sCost: ~$0.004
Browser AgentsBrowser UseJev ChoiceGitHub
BR
Browser Use

Jev Ultrafast

Browser Use's open-source ultra-fast browser agent harness powered by Jev decisions.

Browser AgentsBrowser UseJev ChoiceGitHub
Andrew LevinAndrew Levin@awlevin
TypeSafe Computer Use
DEMO

TypeSafe Computer Use

Open-source macOS desktop control loop with bounded Jev decisions at every single step.

Cost per step: ~$0.0002Latency: <50ms
Browser AgentsmacOSPythonGitHub
RanjanRanjan@manofsteel3129
AskJev (MCP Agent)
DEMO

AskJev (MCP Agent)

Claude handles conversational intent while Jev directs browser navigation across live websites.

Browser AgentsClaude DesktopMCP ServerGitHub
InstructaInstructa@instructa
Switchloom
DEMO

Switchloom

Deterministic model routing for coding agents, featuring an installable skill for Codex.

Correct: 96/100Volume: 1,500 testsSpeed: 100 in 1.42s
Agent RoutingCodex SkillJev ChoiceGitHub
JO
Joaquin Marcoff

Jev Harness Router

One batched Jev call selects model tier, tools, skill, and effort level for each turn.

Agent RoutingTypeScriptJev APIGitHub
jackbarunzjackbarunz@jackbarunz
Jev Tool Router
DEMO

Jev Tool Router

Selects the exact MCP tool for Codex to prevent tool overload and context degradation.

GitHub Stars: 4Decision Latency: ~40ms
Tool SelectionCodexMCPGitHub
MI
Mihajlo Micic

Jev Tool Runner

Jev selects developer tools while Codex writes code, creating a clean separation of roles.

Tool SelectionCodexJev APIGitHub
JE
Jeff Emanuel

SkillRanker (Rust CLI)

A high-performance Rust CLI where Jev ranks available agent skills for the next action.

Tool SelectionRustJev APIGitHub
AB
Abhishek Ashok Kumar

Jev MCP Dispatcher

Executes plain-language MCP tool calls with zero general LLMs, driven entirely by Jev.

MCP / SkillsMCPJev ChoiceGitHub
ClownwareClownware@clownware
Bouncer
DEMO

Bouncer

A judgment layer checking every Claude Code tool call against customizable organizational policies.

Cost: ~$0.04/dayPolicy Check: 100%
GuardrailsClaude CodeJev ChoiceGitHub
KU
Kun Chen

Compact Adviser

Evaluates active agent context windows and signals the optimal moment to perform conversation compaction.

Agent EvaluationClaude Code / CodexJev ScoreGitHub
KO
Konstantinos Botonakis

Codex Context Diet

A Codex plugin where Jev trims bulky tool results before they pollute the agent context window.

MCP / SkillsCodex PluginJev ChoiceGitHub
HE
heyman333

Jev Router (Skill)

A dual Claude Code and Codex skill that automatically picks the right model for any prompt.

Agent RoutingClaude Code SkillCodex SkillGitHub
WA
wang2

Jev Review Action

A lightweight GitHub Action that reviews, labels, and classifies pull requests with Jev alone.

Agent EvaluationGitHub ActionsJev APIGitHub
BU
burnigtm

Jev MCP Coding Loop

An MCP server placing Jev directly on the inner coding loop in Cursor, Claude Code, and Codex.

MCP / SkillsMCP ServerCursorGitHub
Kyle JeongKyle Jeong@kylejeong
Stagehand on a remote browser
DEMO

Stagehand on a remote browser

we built blazing fast computer/browser use with Jev + @Stagehanddev.

Cost per task: ~$0.001
Browser AgentsJev APITypeScript / PythonGitHub
Jarrod WattsJarrod Watts@jarrodwatts
jev-trader
DEMO

jev-trader

I built a trading bot with Jev!

Decision window: 300 ms blocks
Agent RoutingJev APITypeScript / PythonGitHub
Jason LuJason Lu@jasonlu_ai
jev-e2e
DEMO

jev-e2e

JEV is changes the world of E2E testing!

Jev: 47 s / $0.0067Sonnet 5: 79 s / $0.4062
Agent EvaluationJev APITypeScript / PythonGitHub
Tony DinhTony Dinh@tdinh_me
YouTube sponsor skipper
DEMO

YouTube sponsor skipper

Just trying out Jev, I made a Chrome extension that:

Cost per video: ~$0.005
Browser AgentsJev APITypeScript / PythonGitHub
@M
@MajoSayo

LogJev

An open-source Jev-style decision layer that accepts text, images, or audio and returns bounded choices or scores.

MCP / SkillsNode.jsPythonGitHub
@A
@AIandDesign

Token Saver

A Codex workflow that delegates bounded work and uses Jev Context to select relevant source excerpts before the main agent reads them.

Agent RoutingCodexMuseGitHub
@C
@chriscmathew

fast-jev-codex

A Codex plugin that scores tool history and restores verbatim context after compaction.

Agent EvaluationCodexJevGitHub
@D
@dkhan

Jev Codex Router

Routes coding prompts to Luna, Sol, or Astra with an appropriate reasoning level.

Agent RoutingCodexLunaGitHub
@F
@felpsdev07

Jev Classifier

A tool-selection layer for Codex and Claude Code that filters the available tools before expensive model calls.

Tool SelectionCodexClaude CodeGitHub
@T
@TraffAlex / project credited to @elvissun

NewsJack

A news-intelligence workflow that uses Jev to triage stories before expensive brand-specific synthesis.

Latency: 25 seconds in the cited 384-headline exampleCost: $0.19 in the cited 384-headline example
Agent RoutingJevNews intakeGitHub
@C
@crypto1618

Jev System Architect

A coding-agent skill for finding places where fuzzy semantic logic should become an explicit Jev decision boundary.

Agent RoutingCoding agentJev ChoiceGitHub
@T
@themsquared

Jev Benchmark

A community benchmark project for testing Jev as a guardrail over risky agent tool calls.

GuardrailsJevAgent tool callsGitHub
@E
@ersinkoc

JevBenchmarkLab

An open benchmark harness for testing Jev decision consistency, adversarial failures, option-order bias, and latency.

Agent EvaluationJevBenchmark suitesGitHub