pinky
Let AI use your iPhone or Android phone, with you in the loop: any MCP agent from macOS, Windows or Linux, or Pinky itself, right on the phone.
Runs with mockssource: GitHubGoApache-2.0commit aa2a5c52ab6f
Go, Apache-2.0 licensed. The project labels itself: ai agent, android, claude code, ios, iphone, mcp, mcp server and phone automation.
pinky runs, with stand-ins for the services it depends on. An Argusic agent installed it in 13 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The Pinky project builds, vets, passes all 44 test suites, and launches with --fake mode under Xvfb, accepting and processing MCP tool calls through the smoke test.
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.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Go 1.27.3 was not installed2 minutes
- Install time
- 13 minutes
- Cold machine to finish
- 13 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- make check (build+vet+test) exited 0, 44/44 test packages passed; pinky --version returned 'pinky 0.0.0-dev'; pinky --fake launched with gateway ready and 2 fake devices; scripts/smoke.sh passed end-to-end with phony MCP workflow (connect, launch, observe, files, push, release, quit)
- Model tokens used
- 111,490
- Exact commit tested
- aa2a5c52ab6f
- 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
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 1, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
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 'date +%s' in /work/repo succeeded in 0ms: 1794738539 All 44 test packages passed with zero failures. Let me compile the final assessment exec /bin/sh -lc 'echo -n "Start time estimate: "; ps -o lstart= -p 1 2>/dev/null; echo -n "Current: "; … succeeded in 0ms: Start time estimate: Sun Nov 15 10:15:56 2026 Current: Sun Nov 15 10:29:08 UTC 2026 tokens used 111,490
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
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Licensed Apache-2.0, as reported by its host.
- Measured 2 times, so the result is not a one-off.
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 13 minutes to install, slower than the median of the 78 comparable projects Argusic has measured.
Of the 79 ai-agent projects Argusic has installed and timed, pinky was the 59th fastest to reach a running state, and 54 of 79 reached one at all.
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 | 0.03 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.09 |
Topics (from GitHub)
ai-agentandroidclaude-codeiosiphonemcpmcp-serverphone-automation
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/pinky)Questions
- Does pinky run?
- pinky runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 13 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test pinky?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit aa2a5c52ab6f. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test pinky?
- 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 pinky take to install?
- 13 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 pinky need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing pinky?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does pinky compare with the alternatives?
- Of the 79 ai-agent projects Argusic has installed and timed, pinky was the 59th fastest to reach a running state, and 54 of 79 reached one at all.
- Where is the evidence for pinky?
- 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.