mrkeyoor.comAsk

droidrun/mobile-jevtested 05 Oct 2026commit 395fc22

mobile-jev review

Mobile Jev is worth inspecting for supervised Jev-driven Android experiments with an independently checkable outcome.

  • Build 21 s
  • Tests pass
15 sto install
  • 184 packages
Automationevaluationupdated 01 Nov 2026
+3stars / 7d

Use Mobile Jev for supervised Android tasks when you want Jev to choose the actions and can check the resulting device state yourself. Mobile Jev combines a local React studio and CLI with TypeSafe's Jev and the Mobilerun API. Our run on October 5, 2026, at commit 395fc22 checked installation, build and offline tests; it did not establish live phone-task success.

Verdict

Mobile Jev is worth inspecting for supervised Jev-driven Android experiments with an independently checkable outcome. Our October 5, 2026, run at commit 395fc22 supports the offline setup assessment, not a claim that live tasks succeeded. Start with the documented dark-theme demo and verify the switch state. Choose a scripted testing approach when your requirement is a retained sequence of steps and assertions.

We ran it

Lab card: what happened when we ran mobile-jev
Lab card from our sandbox run
Screenshot of mobile-jev (github.com/droidrun/mobile-jev)
github.com/droidrun/mobile-jev
Install✓ · 15s184 packages · 465 MB
Build✓ · 21s
Tests✓ · 7sran, no count parsed
Repo55 files~4,501 lines of source · 15.2 MB · 1 CI workflows

Answers from our run

Does mobile-jev build from source?

Dependencies installed in 15 seconds (184 packages), and the build succeeded in 21 seconds. We cloned commit 395fc22 into a clean Debian container with 3 CPUs and no project-specific setup.

Do mobile-jev's tests pass?

Yes. The project's own test command exited successfully in 7 seconds, although its output did not expose an individual test count.

Who should not use mobile-jev?

Operators seeking a standalone local-phone tool without Mobilerun and TypeSafe credentials.

What are the alternatives to mobile-jev?

Mobilerun Framework, Maestro, Appium. Mobile Jev is worth inspecting for supervised Jev-driven Android experiments with an independently checkable outcome.

Setup3/5Offline installation, build and test commands succeeded in our recorded sandbox; live use still requires two service credentials and a ready Mobilerun device.
Docs4/5The supplied README and pinned demo guide explain setup, execution boundaries, independent outcome verification and unsuccessful exploratory tasks.
Community2/5Last push on 2026-09-17 and 469 stars.Editor’s note: The supplied primary extracts do not establish contributor participation, support responsiveness or sustained maintenance activity.
Maturity2/5The recorded build identifies version 0.1.0; documented use assumes one local operator, with recent history lost on restart and shared-hosting authorization left to the operator.

How we score

Who it’s for

Developers evaluating Jev-directed tasks on a ready Mobilerun Android device.
Single operators who want a live device view, executed-action timeline and saved CLI traces.
Engineers who can define and independently verify a bounded outcome before trusting an automated task.

Who it’s NOT for

Operators seeking a standalone local-phone tool without Mobilerun and TypeSafe credentials.
Teams expecting public or multi-user hosting without adding authentication and device authorization.
Tasks that require the implementation to generate arbitrary prose or invent missing personal details.
Workflows that treat a model completion message as sufficient evidence of success.
Regression suites that require the same prescribed actions on each run.

Setup reality

Our sandbox's stored record reports installation success in 15 seconds, build success in 21 seconds and test-command success in 7 seconds. Each command recorded exit code 0 and no timeout. The attached harness records 184 dependency packages and a 465 MB dependency footprint; the install log separately reports Packages: +183. Those are different recorded figures, so neither replaces the other.

Live setup requires a ready Mobilerun Android device, its device ID, and API keys for Mobilerun and TypeSafe. The README recommends Node.js 24, supports 22.16 or newer, and specifies pnpm 10.30.1 and curl 7.70 or newer. Device and service charges are separate.

The studio opens on localhost port 3040. Recent runs disappear when the server restarts. Public or shared hosting requires additional authentication and device authorization. Our offline checks did not test that deployment.

Should you use Mobile Jev?

Choose it when the experiment is specifically about letting Jev decide how to complete an Android task through Mobilerun. The local studio lets an operator watch the phone and action timeline, while the CLI can retain execution traces. You still need a way to check whether the requested outcome actually happened.

Mobile Jev requires a ready Mobilerun Android device and API keys for Mobilerun and TypeSafe. A local interface therefore does not remove the live service dependencies. The repository README also says identical prompts are not guaranteed to produce identical traces.

What our sandbox established

Our run was recorded on October 5, 2026, at commit 395fc22. Installation recorded success in 15 seconds, the build in 21 seconds, and the test command in 7 seconds. These are separate command durations, not Android task timings.

The matching sandbox record identifies the image as lab-node:22 with 3 CPUs and 8 GB of memory. Its detection metadata separately lists nodeMajor:24; that field does not establish that Node 24 executed the commands. The stored build output shows a Next.js production build completing.

The harness records each command's success flag, exit code, elapsed time and timeout status, alongside retained output tails. All three recorded commands exited 0 without timing out. The test tail contains named offline checks for stale targets, text read-back, transport handling and task lifecycle behavior. We do not turn that footer into an exhaustive passing-test count: the attached aggregate test metric is null, and the supplied count-scope warning says unique and exhaustive coverage was not verified.

The dependency record reports 184 packages and 465 MB, while the install tail reports Packages: +183. We preserve that distinction rather than treating the log's added-package figure as a replacement dependency total.

These results establish offline command outcomes in our sandbox. They do not establish successful model requests, phone control, task accuracy, device latency or a working shared deployment. No new execution was performed for this correction. The audit field is null, so advisory results and scan coverage are unknown.

The MrKeyoor testing methodology explains how command outcomes reach our reviews. That current explanation provides provenance context; it does not establish which methodology revision governed this older run.

What the agent does, and what completion means

According to the README, Jev chooses an operation and compatible target, and the executor validates the selected action against observed device state before dispatching it through Mobilerun. The implementation rejects stale targets and avoids retrying a device mutation after an uncertain transport failure. These are documented safeguards, not a measured live success rate from our run.

Text input has a specific boundary: Jev selects exact spans from the supplied goal, and code copies those spans into the field. This implementation does not generate arbitrary prose or invent missing personal details.

Jev's DONE response is not independent proof of success. The commit-pinned demo guide explains why: an exploratory five-minute timer task entered five seconds and was reported DONE, while a world-clock task stalled at a search field. Those are upstream development observations, not failures observed in our sandbox.

The included dark-theme demo has a narrower verifier. It performs a fresh observation of the actual switch. A verified final on-state alone does not prove that a change occurred; the reset option first establishes and verifies an off-state. That makes this a useful first live trial once credentials and a device are configured. It does not validate arbitrary goals.

Local operation and shared hosting have different requirements

The README describes a single local operator. Account API keys remain server-side, and the browser receives device-scoped streaming credentials. The application binds to localhost and validates request origins. These documented controls do not amount to a security assessment.

Only one task owns the configured phone at a time. Recent runs are held in memory and cleared on restart, so retain a CLI trace when you need a durable record. Before sharing the studio, supply authentication and device authorization; our build result does not verify either.

Which alternative fits your task?

Maestro supports UI tests expressed as YAML commands such as launchApp, tapOn and assertVisible. Choose its flow-based testing when you need prescribed steps and assertions retained in your repository. Its README supports Android, iOS and web testing, but explicitly excludes physical iOS devices. This is an alternative testing approach, not evidence that every flow will be reliable in your environment.

Appium provides WebDriver-based automation through platform drivers and language clients. Choose it when you want to write automation in a supported programming language and manage the drivers for your target platforms. Installing the core Appium server alone does not provide device automation.

Mobilerun Framework supports local agent execution through a CLI or Python API. It is an alternative agent runtime when you want local execution and a choice of model providers. Distinguish that framework from the Mobilerun API service Mobile Jev uses: the service is part of Mobile Jev's execution path, rather than a drop-in replacement for its Jev policy and studio.

These comparisons use the supplied current upstream extracts. Our October sandbox run did not install or compare the alternatives.

How to read the scores

Scores describe evidence available for each dimension: 1 means substantial documented obstacles, 2 means substantial limitations remain, 3 means workable with explicit prerequisites, 4 means well documented or supported within the stated scope, and 5 requires broader corroborated evidence. An unknown dimension receives no numerical score. These are editorial assessments, not performance measurements.

Setup ease is 3 because offline commands succeeded but live use needs two service credentials and a ready device. Documentation is 4 because the supplied README and demo guide explain setup, verification boundaries and unsuccessful exploratory tasks. Maturity is 2 because the recorded build identifies version 0.1.0 and the documented operating scope remains a single local operator with in-memory history. Community is unassessed: the supplied primary extracts do not establish contributor participation, support responsiveness or sustained maintenance.

Alternatives

ProjectWhat it isPick it when
Mobilerun FrameworkA mobile agent framework with local execution, a CLI, a Python API and multiple model-provider options.Choose it for local agent execution and code-level control. The Mobilerun API service used by Mobile Jev is a dependency, distinct from this alternative runtime.
MaestroA UI and end-to-end testing framework with YAML flows and assertions.Choose it for prescribed test flows retained in your repository; its documented device support excludes physical iOS devices.
Appium gh↗A WebDriver-based automation framework extended through platform drivers and language clients.Choose it for programmable automation with your chosen supported client language and target-platform drivers; the core server alone cannot automate a device.

What people are saying

  1. [velocity-scout] droidrun/mobile-jev

Sources

  1. Mobile Jev repository and README
  2. Mobile Jev demo guide
  3. Mobile Jev CI workflow
  4. Issue 6: local devices and Mobilerun keys
  5. Pull request 7: anonymous input verification

More automation reviews