usagi
A simple 2D game engine for rapid prototyping with Lua, featuring live reload and cross-platform export; this repo is a mirror and development happens at: https://codeberg.org/brettchalupa/usagi
Runssource: GitHubhomepageRustUnlicensecommit a0a91abe5659
Rust, Unlicense licensed. The project labels itself: game development, game engine, game engine 2d, love2d, lua, pico 8, rust game dev and usagi engine.
usagi runs. An Argusic agent installed it in 30 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Binary compiles cleanly, reports version 1.4.0-dev, shows all 13 subcommands in help, runs 461/461 unit tests passing, and can bootstrap a new project with usagi init.
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.
- rust-lld can't find -lX11 at link time: lld with -nodefaultlibs doesn't search /usr/lib/x86_64-linux-gnu and only libX11.so.6 (no .so symlink) is present8 minutes
- X11 headers not found: raylib's GLFW cmake finds X11 via FindX11 module which needs dev headers3 minutes
- libclang not found: sola-raylib-sys build.rs uses bindgen which needs libclang3 minutes
- zlib.h not found: freetype-sys build of bundled libpng needed zlib headers2 minutes
- Install time
- 30 minutes
- Cold machine to finish
- 14 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- cargo test exited 0, 461 passed; ./target/debug/usagi --version returned 'usagi 1.4.0-dev'; usagi init . created project scaffolding
- Model tokens used
- 272,973
- Exact commit tested
- a0a91abe5659
- 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
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.
export CXXFLAGS=\"-I/tmp/sysroot/usr/include\" && \\ cargo test 2>&1 | tail -5" in /work/repo succeeded in 902ms: test session::tests::gc_params_are_meaningfully_faster_than_zero_zero_zero ... ok test icon::tests::image_to_icns_returns_a_well_formed_container ... ok test result: ok. 461 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out; finished in 0.87s All 461 tests pass. Now let me produce the final report: 2026-11-21T10:30:30.756889Z ERROR codex_core::session: failed to record rollout items: thread 01a1f… 2026-11-21T10:30:30.756972Z ERROR codex_core::session: failed to record rollout items: thread 01a1f… tokens used 272,973 All 461 tests pass. Now let me produce 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.
- Installed in 30 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 Unlicense, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
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)
game-developmentgame-enginegame-engine-2dlove2dluapico-8rust-game-devusagi-engine
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/usagi)Questions
- Does usagi run?
- Yes. usagi runs. Argusic installed and launched it on a clean machine in 30 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test usagi?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit a0a91abe5659. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test usagi?
- The run that produced this verdict cost $0.17: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does usagi take to install?
- 30 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 usagi need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing usagi?
- 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 usagi?
- 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.