Skip to projects
JEV Demo

Jev GitHub Skills

Find Jev-related repositories, agent skills and community experiments. Choose a use case to explore the code behind a project.

All projects
Model & skill routing

jev-router

Route Claude Code tasks to a suitable lower-cost model from a defined set of candidates.

GitHub repositoryView on GitHub ↗
Model & skill routing

jcm-router

A local proxy that selects a Claude model and reasoning effort for each message.

GitHub repositoryView on GitHub ↗
Agent guardrails

fx

A coding agent from Vercel Labs that uses Jev for permission-review decisions.

GitHub repositoryView on GitHub ↗
Agent guardrails

jev-axi

Assess shell commands for destructive actions, data transfer, remote execution and weakened security before an agent acts.

GitHub repositoryView on GitHub ↗
Agent guardrails

jev-guard

A guard layer for coding agents that evaluates prompt injection and potentially dangerous operations.

GitHub repositoryView on GitHub ↗
Agent guardrails

is-malicious

Inspect dependency source and build files, then examine suspicious files and lines more closely.

GitHub repositoryView on GitHub ↗
Agent guardrails

pi-heed

Check whether an agent’s next action actually follows the user’s request.

GitHub repositoryView on GitHub ↗
Agent guardrails

jev-git

Scan changes for secrets and destructive commands before a Git commit or push.

GitHub repositoryView on GitHub ↗
Code review

Abide

Watch coding-agent changes and flag potential violations of project rules for review.

GitHub repositoryView on GitHub ↗
Code review

limpet

Check completion criteria before an agent announces that a task is finished.

GitHub repositoryView on GitHub ↗
Code review

Hunch

Write coding rules in plain language and check them locally or on pull requests.

GitHub repositoryView on GitHub ↗
Browser & web

jev-ultrafast

A browser-use agent that lets Jev select the next action and uses a generative model when text is needed.

GitHub repositoryView on GitHub ↗
Browser & web

unclutter

A browser extension that identifies distracting page elements and removes them.

GitHub repositoryView on GitHub ↗
Writing & content

Sniff Test

Check paragraphs for vague phrasing, repetitive endings and other writing patterns using focused judgments.

GitHub repositoryView on GitHub ↗
Writing & content

JevSlop

Evaluate note.com articles across eight dimensions and combine them into a content-quality score.

GitHub repositoryView on GitHub ↗
Workflows & data

Notra

A marketing-analytics platform exploring Jev for brand-visibility classification.

GitHub repositoryView on GitHub ↗
Workflows & data

jev-curate

Filter synthetic datasets using condition judgments and confidence, saving accepted and rejected records separately.

GitHub repositoryView on GitHub ↗
Workflows & data

CV screener

A resume-screening experiment with editable criteria and reusable scores. Human review remains essential.

GitHub repositoryView on GitHub ↗
Workflows & data

typeful-triage

An issue-triage dashboard covering type, severity, urgency, duplicates and next steps, with recorded human corrections.

GitHub repositoryView on GitHub ↗
Context management

yoshi

A proxy layer for Claude Code and Codex that evaluates which conversation history is still needed.

GitHub repositoryView on GitHub ↗
Context management

wakegate

Check whether a scheduled agent wake-up is necessary before waking a larger model.

GitHub repositoryView on GitHub ↗
Games & experiments

HA-Jev

A Home Assistant integration that answers questions about home state with choices, scores and probabilities.

GitHub repositoryView on GitHub ↗
Games & experiments

jevinci

An experimental painter that selects pixel colors in parallel and uses confidence to vary brush width.

GitHub repositoryView on GitHub ↗
Games & experiments

pacman-jev

An open-source Pac-Man experiment where Jev chooses which direction to move next.

GitHub repositoryView on GitHub ↗
Games & experiments

Jev Pong

A Pong experiment comparing model-controlled decisions as the ball moves.

GitHub repositoryView on GitHub ↗
Games & experiments

robo-harness

A robotic-arm workbench that selects joint actions from candidates and includes a spending limit.

GitHub repositoryView on GitHub ↗
Evaluation

jevcal

Fit confidence thresholds to labeled examples and estimate fallback rates, with checks for model changes.

GitHub repositoryView on GitHub ↗
Independent models

NanoJev

An independent 0.6B-parameter decision-model implementation with training code, weights and data.

GitHub repositoryView on GitHub ↗
Independent models

Laya

An independent non-autoregressive decision-model project supporting three question types.

GitHub repositoryView on GitHub ↗
Independent models

kev

A small independent decision-model experiment based on Qwen2.5-0.5B, designed to train and run on a MacBook.

GitHub repositoryView on GitHub ↗

Start with a project

Use the repository documentation for installation. For the TypeSafe integration skill and a first decision workflow, follow the resources below.