468 projects tested, and "Rust toolchain not installed" stopped 10: week of September 21, 2026

What it ran on

Argusic publishes other people's server prices every day. These are its own: the machines this week's work was rented on, at the rates actually paid, each one destroyed when its job finished.

Attempts on CPU machines

527 at 0.1162 USD an hour

Data centers used

EU-CZ-1, EU-NL-1, EU-RO-1, EU-SE-1, EUR-IS-1, US-CA-2, US-GA-2, US-KS-2, US-MD-1, US-MO-1, US-NC-1, US-NE-1, US-WA-1

What the week cost, broken down

A single total answers nothing for somebody working out whether they could do this themselves. The difference between the dearest and the cheapest project is how much fixing each needed, not a price anybody chose.

Model tokens

29.86 USD

Machines

25.33 USD

Per project measured

0.12 USD

Dearest project

neon at 1.03 USD

Cheapest project

XlsxWriter at 0.00 USD

What the pool looks like now

The state of the whole body of evidence at the end of this week, not only what the week itself added.

Projects measured in total

753

Of those, reached a working state

590

Most measured languages

Python (203), TypeScript (165), Go (101), Rust (92), JavaScript (68)

What kept breaking

Counted across projects, not across attempts, so one repository retried three times is one problem. Each label is the wording an agent actually used.

10 projects

Rust toolchain not installed

5 projects

Go not installed in container

5 projects

pnpm not found

4 projects

pip install failed

3 projects

Go compiler not found in container

The result most worth reading

onedev scored 100 of 100, after hitting 11 errors that the agent fixed with no human help.

OneDev builds and compiles from source with all 86 tests passing, and the server starts on localhost:6610 returning HTTP 200 with the setup initialization page.

The agent's own words, from its recorded report.

What this week does not tell you

Behavior over time

each attempt uses the smallest documented settings and a fixed time budget, so this measures whether a thing runs, not how it holds up under load

Anything not tested

only the 468 projects above were run this week; a project absent from this report was not measured, not judged

Real-service behavior for 91 of them

those ran against stand-in services, never the real ones

The report as written

Argusic installed and ran 468 projects on clean machines between 2026-09-21 and 2026-09-28, over 522 attempts, 151 more subjects than the week before.

347 were verified against the real thing, 91 only against stand-in services, and 84 could not be verified at all.

273 projects were tested here for the first time.

The same problems keep appearing across unrelated projects. The most common this week was "Rust toolchain not installed", which stopped 10 projects. Also recurring: "Go not installed in container" (5), "pnpm not found" (5), "pip install failed" (4), "Go compiler not found in container" (3).

The result most worth reading was onedev, which scored 100 of 100 after hitting 11 errors that the agent fixed with no human help. In the agent's own words: OneDev builds and compiles from source with all 86 tests passing, and the server starts on localhost:6610 returning HTTP 200 with the setup initialization page.

Running all of this cost 55.19 USD, of which 54% was model tokens rather than machines.

29.86 USD of that was model tokens and 25.33 USD was machines, which is 0.12 USD for each project measured.

The dearest project of the week was neon at 1.03 USD, the cheapest XlsxWriter at 0.00 USD. The difference is how much fixing each one needed, not a price we chose.

The work ran on machines rented by the hour and destroyed afterwards: 527 attempts on CPU machines at 0.1162 USD an hour. Those are the rates Argusic actually paid, not list prices. The pods came up in 13 data centers: EU-CZ-1, EU-NL-1, EU-RO-1, EU-SE-1, EUR-IS-1, US-CA-2, US-GA-2, US-KS-2, US-MD-1, US-MO-1, US-NC-1, US-NE-1, US-WA-1.

Across everything measured so far, 753 projects have been installed and run here, and 590 of them reached a working state. Most of them are written in Python (203), TypeScript (165), Go (101), Rust (92), JavaScript (68).

Every number above comes from a recorded run, and each one has its log and its terminal recording on this site.