android-ad-cleaner
关掉国产安卓手机系统里的广告、热搜、资讯推荐和营销推送。不 root，可还原，支持 AI 智能体一键执行。
Runssource: GitHubPythonMITcommit 90c267618b10
Python, MIT licensed. The project labels itself: adb, ai agent, android, coloros, debloat, hyperos, magicos and originos.
android-ad-cleaner runs. An Argusic agent installed it in 3 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Repo installs in .venv with uiautomator2 3.7.1 and runs its full 204-test suite green, the desktop GUI launches and stays up on the virtual display with its window and smoke checks passing, and all CLI help/devices commands answer correctly with adb 1.0.41 on PATH.
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 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page. 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.
- Qt xcb platform plugin failed: system libxcb-cursor0 missing; no root for apt2 minutes
- pip refused system install: externally-managed-environment (PEP 668)1.5 minutes
- pywebview had no GUI toolkit (no gi, no qtpy, no Qt)1.5 minutes
- No adb binary found; tool/run.py exits at import when adb is missing0.3 minutes
- Install time
- 3 minutes
- Cold machine to finish
- 5 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- PATH=/tmp/platform-tools:$PATH .venv/bin/python -m unittest discover -s tests -> Ran 204 tests, OK (skipped=2); .venv/bin/python gui/app.py --smoke-gui -> rc=0, 'GUI smoke: file 页面、教程图片、JS API 桥、读屏失败排查提示通过'; xwininfo on DISPLAY=:99 showed window '安卓去广告' 1080x780 up for 20s; run.py devices -> '没有连着的手机' rc=0
- Model tokens used
- 67,563
- Exact commit tested
- 90c267618b10
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
tokens used 67,563 Done. Final report: **Install** — `requirements.txt` (uiautomator2 3.7.1) installed in a fresh venv at `.venv/`. PEP 66… **Tests** — `PATH=/tmp/platform-tools:$PATH .venv/bin/python -m unittest discover -s tests` → **Ran… **App launch** — `gui/app.py --smoke-gui` (the documented source-mode check) → exit 0, "GUI smoke: … **Errors fixed** - No adb binary → installed Google platform-tools locally (no root, so no apt). - PEP 668 externally-managed environment → venv. - GUI toolkit missing (`ModuleNotFoundError: gi`, no qtpy) → pip-installed pywebview+qtpy+PySide6. - Qt xcb platform plugin failed: missing system `libxcb-cursor0` → extracted the prebuilt Ubuntu 24… Real-phone behavior (channel scans, suspend, recipe runs) couldn't be verified here — no Android de…
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.
- Installed in 3 minutes.
- Recovered from all 4 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.
What did not, or is not known
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
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 3 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
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/android-ad-cleaner)Questions
- Does android-ad-cleaner run?
- Yes. android-ad-cleaner runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test android-ad-cleaner?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 90c267618b10. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test android-ad-cleaner?
- The run that produced this verdict cost $0.08: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does android-ad-cleaner take to install?
- 3 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 android-ad-cleaner need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing android-ad-cleaner?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for android-ad-cleaner?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.