iPhone-use
让 Codex 通过 USB 操作真实 iPhone：引导安装、App 自动化、实时屏幕与截图回退。
Runs with mockssource: GitHubPythonMITcommit 5cc2fa880818
Python, MIT licensed.
iPhone-use runs, with stand-ins for the services it depends on. An Argusic agent installed it in 6 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
The MCP server starts over stdio, accepts initialize/ping/tools/list, and reports 19 phone-control tools; all 462 Python unit tests pass (8 macOS-only skipped), all 57 UI widget tests pass, the screen widget builds, the package validates, and the plugin is installed into Codex.
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 92 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.
- Install time
- 6 minutes
- Cold machine to finish
- 6 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- MCP smoke test (python3 scripts/smoke_mcp.py): server returned initialize+19 tools+ping OK. Python test suite: python3 -m unittest discover -s tests -v returned OK (462 run, 8 skipped). UI widget tests: python3 scripts/check_screen_ui.py returned TAP 57 passed. install.sh ran without errors and registered the plugin.
- Model tokens used
- 51,713
- Exact commit tested
- 5cc2fa880818
- 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
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
**Node syntax checks**: `tooling/forward.mjs` and `tooling/screen-stream.mjs` both passed `node --c… tokens used 51,713 Here's the complete summary of what I found and verified. **Environment**: Ubuntu 24.04 x86_64, no macOS/Xcode, no iPhone via USB — this project requires all… **Install** (`sh scripts/install.sh`): registered the plugin as a local marketplace and installed i… **Build** (`npm run build --prefix ui`): `tsc --noEmit` and `node build.mjs` produced `phone-screen… **MCP smoke test** (`python3 scripts/smoke_mcp.py`): server named `iphone-use` at version `0.3.12`,… **Full Python test suite** (`python3 -m unittest discover -s tests -v`): 462 tests ran, **all passe… **UI widget tests** (`python3 scripts/check_screen_ui.py`): 57 node tests, **all passed** (0 failed… **Packaging validation** (`python3 scripts/package.py --validate-only`): "Plugin manifests, 2 skill… **Node syntax checks**: `tooling/forward.mjs` and `tooling/screen-stream.mjs` both passed `node --c…
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
- Nothing broke on the way: zero errors between clone and running.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Took 6 minutes to install, slower than the median of the 41 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 42 Python projects Argusic has installed and timed, iPhone-use was the 26th fastest to reach a running state, and 21 of 42 reached one at all.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.03 |
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/iphone-use)Questions
- Does iPhone-use run?
- iPhone-use runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 6 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test iPhone-use?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 5cc2fa880818. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test iPhone-use?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does iPhone-use take to install?
- 6 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 iPhone-use need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing iPhone-use?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does iPhone-use compare with the alternatives?
- Of the 42 Python projects Argusic has installed and timed, iPhone-use was the 26th fastest to reach a running state, and 21 of 42 reached one at all.
- Where is the evidence for iPhone-use?
- 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.