Skip to content
JevDirectory.org
CommunityTools & Integrations340 starsVerified 2026-09-22

Mobile Jev

Standalone Android agent and React studio for Mobilerun, powered by Jev: Jev selects operations and observed targets, code rejects stale actions, and a CLI, execution traces, and latency measurements ship in the repo. No ADB connection required.

Category
Tools & Integrations
Published by
Community
Author
droidrun
Added
2026-09-22
Tagscommunityjavascriptagentsandroid

Highlights

  • Jev chooses OPEN_APP, TAP, TYPE_TEXT, scrolling, navigation, WAIT, DONE, or BLOCKED; code validates the target before Mobilerun executes.
  • Operation and compatible-target questions share one request, so unused target answers cannot execute.
  • The dark-theme demo re-reads the screen and verifies the switch is on instead of trusting a model DONE.
  • The recorded Uber demo shows about 21 seconds for 9 actions; a completed booking is not demonstrated.
  • No ADB connection is required, and the studio keeps account API keys on the server.

Quickstart

bash
git clone https://github.com/droidrun/mobile-jev.git
cd mobile-jev
corepack enable
pnpm install --frozen-lockfile
cp .env.example .env.local
pnpm devices
pnpm doctor
pnpm dev

Watch out

MIT-licensed. Needs Node.js 22.16+ (24 recommended), pnpm 10.30.1, curl 7.70+, a ready Mobilerun Android device, and both MOBILERUN_API_KEY and TYPESAFE_API_KEY; CI runs offline and does not control a phone.

More like this

3.1kGitHub stars
An Android overlay that reads visible WeChat, QQ, and X conversations through accessibility, asks Jev for intent, danger, and the best action, then drafts three replies and fills one in without ever sending it.
Tools & Integrations#community#kotlin#android
A structured decision plugin for agent harnesses: Jev recommends among currently available and permitted tools, skills, and agents, and evaluates output quality, returning choices, probabilities, and confidence while the host agent keeps planning and execution.
Tools & Integrations#community#javascript#agents
71GitHub stars
Unofficial browser automation where the calling LLM states the outcome and Jev decides each element, action, and value from a Playwright page snapshot. Ships as a library, CLI, and MCP server.
Tools & Integrations#community#javascript#browser
Communityjev-browser
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

A really smart switch statement

hype-free explanation of jev: jev does not replace gpt / claude jev is just a *really* smart switch statement like if 2016 ml classifiers got 2026 levels of intelligence it's a new* type of tool that will make a lot of workloads insanely fast, cheap, and accurate * = and by Show more

Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Reply

When a designer gets Jev

Full Jev video tutorial

The case against Jev-scored compaction

This is a terrible compaction strategy that fundamentally doesn't understand how compaction and context management work. Seems like a lot of people are confused so let's break this down. 1. Compaction isn't a filter The role of compaction is to clean up history to keep the Show more

tamara
tamara
@tamarajtran

found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant

Reply

Classifying rows in DuckDB

A playable 16-judgment demo