apkstart
Windows 上的安卓应用运行器:双击 APK 即装,应用以独立窗口与桌面图标运行,自持 QEMU 运行时
Runssource: GitHubJavaScriptMITcommit b8771d06b0aa
JavaScript, MIT licensed. The project labels itself: android, android x86, apk, electron, emulator, freeform, qemu and windows.
apkstart runs. An Argusic agent installed it in 10 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
npm install completed with all dependencies resolved (including native @napi-rs/lzma-linux-x64-gnu binding). All 3 Node.js test suites passed (117/117 tests). The Electron/desktop app and Windows-specific features (shortcuts, file assoc, emulator) cannot be tested on Linux.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 96 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Node.js v18.19.1 installed but project requires >=20; nvm not available natively3 minutes
- package.json restricts os to win32, blocking npm install on Linux2 minutes
- @napi-rs/lzma-linux-x64-gnu native binding missing after npm install (optional dependency not fetched)2 minutes
- Install time
- 10 minutes
- Cold machine to finish
- 2 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- npm test exited 0: 8 tests in run-tests.js, 25 tests in engine-test.js, 84 tests in auto-test.js, total 117 passed, 0 failed
- Model tokens used
- 84,517
- Exact commit tested
- b8771d06b0aa
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
exec
/bin/sh -lc 'cd /work/repo && export NVM_DIR="$HOME/.nvm" && [ -s "$NVM_DIR/nvm.sh" ] && . "$NVM_DI…
exited 2 in 0ms:
/bin/sh: 1: Syntax error: "(" unexpected
exec
/bin/sh -lc 'cd /work/repo && diff package.json package.json.bak && echo "identical" || echo "diffe…
succeeded in 0ms:
identical
Good, the package.json is completely restored to its original state.
tokens used
84,517
Good, the package.json is completely restored to its original state.Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 10 minutes to install, slower than the median of the 29 comparable projects Argusic has measured.
Of the 30 android projects Argusic has installed and timed, apkstart was the 18th fastest to reach a running state, and 23 of 30 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 10 minutes after the clone.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.05 | |
| Argusic Runner | 1/3 | Runs | 100.00 | 0.04 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/apkstart)Questions
- Does apkstart run?
- Yes. apkstart runs. Argusic installed and launched it on a clean machine in 10 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test apkstart?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit b8771d06b0aa. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test apkstart?
- The run that produced this verdict cost $0.04: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does apkstart take to install?
- 10 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does apkstart need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing apkstart?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does apkstart compare with the alternatives?
- Of the 30 android projects Argusic has installed and timed, apkstart was the 18th fastest to reach a running state, and 23 of 30 reached one at all.
- Where is the evidence for apkstart?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.