biscuit

biscuit is a native, extensible, AI code editor. lightweight <20 mb in size. install and start using in seconds.

Runssource: GitHubhomepagePythonMITcommit 85c5beb0c624

Python, MIT licensed. The project labels itself: agents, ai, code editor, copilot, cursor, debugger, extensions and hacktoberfest.

biscuit runs. An Argusic agent installed it in 12 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

The Biscuit code editor (v3.5.0) installs from source, all 312 tests pass, the CLI responds to --version and --help, and the GUI launches on the virtual display creating the full editor window tree including menu bar, status bar, editor tabs, panels, and sidebars.

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

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.18 (measured)
recorded runs
1
last tested
stars
265
forks
34
open issues
0
watchers
2
size
10 MB
created
last push

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.

Time lost to each failure while testing biscuit, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • Python 3.12 system build lacks _tkinter module (Tk not compiled in)4 minutes
  • tkextrafont declared win32-only in pyproject.toml but imported unconditionally in src/biscuit/settings/settings.py; cannot install on Linux (requires scikit-build + C toolchain)2 minutes
  • Tk event binding '<Control-\\>' is invalid keysym in headless Xvfb1.5 minutes
  • pytest-asyncio listed in dependency groups but not installed by pip install -e .[dev]0.5 minutes
  • biscuit-extensions subrepo cloned at runtime contains tests/e2e/conftest.py with wrong paths, breaking pytest collection0.5 minutes
Install time
12 minutes
Cold machine to finish
12 minutes
Errors hit and fixed
5 hit, 5 fixed with no human help
How the result was proved
pytest (--ignore=extensions/tests) exited 0, 312 passed, 6 skipped; biscuit --version prints 'Biscuit v3.5.0'; biscuit --help prints usage; biscuit open . creates 47 Tk windows on DISPLAY=:99 (verified with xwininfo -root -tree)
Model tokens used
548,455
Exact commit tested
85c5beb0c624
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 attempt that decided the verdict above. 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.

tokens used
548,455
12 minutes total. Now writing the final summary.
Let me also double-check the errors we encountered and the fixes:
1. **Missing Tkinter**: Python 3.12 lacked `_tkinter`. Fixed by extracting pre-built shared libs fr…
2. **Missing tkextrafont (win32-only dep imported unconditionally)**: Fixed by guarding the import …
3. **Backslash keysym binding**: `"<Control-\\>"` is invalid Tk event syntax in this Xvfb; fixed to…
4. **Missing pytest-asyncio** (listed in pyproject.toml but not auto-installed): Fixed by explicit …
5. **Extensions e2e conftest breaks collection**: Not a repo bug per se — the biscuit-extensions su…
Now generating the final answer:
```
```

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 5 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

  • Took 12 minutes to install, slower than the median of the 40 comparable projects Argusic has measured.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 41 agents projects Argusic has installed and timed, biscuit was the 29th fastest to reach a running state, and 29 of 41 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.

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 byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs100.000.18

Topics (from GitHub)

agentsaicode-editorcopilotcursordebuggerextensionshacktoberfestidelspnativetext-editor

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/biscuit.svg)](https://argusic.com/subject/biscuit)

Questions

Does biscuit run?
Yes. biscuit runs. Argusic installed and launched it on a clean machine in 12 minutes, hitting 5 errors on the way, and recorded the session.
How did Argusic test biscuit?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 85c5beb0c624. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test biscuit?
The run that produced this verdict cost $0.18: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does biscuit take to install?
12 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 biscuit need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing biscuit?
5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does biscuit compare with the alternatives?
Of the 41 agents projects Argusic has installed and timed, biscuit was the 29th fastest to reach a running state, and 29 of 41 reached one at all.
Where is the evidence for biscuit?
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.

Discussion