microduck
A Tiny biped duck robot 🦆
Runssource: GitHubhomepageRustApache-2.0commit a9ec4b2079ef
Rust, Apache-2.0 licensed.
microduck runs. An Argusic agent installed it in 22 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The full Rust workspace compiles and all 1515 tests pass on the host (x86_64 Linux) using a manually assembled sysroot of C library headers and runtimes for GLib, GStreamer, and libudev, extracted from Debian .deb packages since root was unavailable.
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, 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.
- C library dev packages missing (libudev-dev, glib-2.0-dev, gstreamer-1.0-dev, and transitive deps) — no root for apt-get install3 minutes
- Dangling .so dev symlinks in sysroot pointing to runtime sonames not present2 minutes
- Rust toolchain not found in PATH1 minute
- Install time
- 22 minutes
- Cold machine to finish
- 23 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- cargo test --workspace exited 0 with 1515 passed, 0 failed
- Model tokens used
- 148,603
- Exact commit tested
- a9ec4b2079ef
- 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.
61 52 succeeded in 56295ms: Total passed: 1515 exec /bin/sh -lc 'date -u' in /work/repo succeeded in 0ms: Tue Nov 3 20:37:18 UTC 2026 All 1515 tests pass with zero failures. Here's the final report: tokens used 148,603 All 1515 tests pass with zero failures. Here's the final report:
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 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
- Took 22 minutes to install, slower than the median of the 17 comparable projects Argusic has measured.
Of the 18 Rust projects Argusic has installed and timed, microduck was the 14th fastest to reach a running state, and 17 of 18 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.
Run history
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/microduck)Questions
- Does microduck run?
- Yes. microduck runs. Argusic installed and launched it on a clean machine in 22 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test microduck?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit a9ec4b2079ef. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test microduck?
- The run that produced this verdict cost $0.15: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does microduck take to install?
- 22 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 microduck need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing microduck?
- 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 microduck compare with the alternatives?
- Of the 18 Rust projects Argusic has installed and timed, microduck was the 14th fastest to reach a running state, and 17 of 18 reached one at all.
- Where is the evidence for microduck?
- 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.