656 projects tested, and "Go compiler not found in container" stopped 8: week of October 5, 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

755 at 0.1192 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-MO-2, US-NC-1, US-NE-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

85.48 USD

Machines

199.90 USD

Per project measured

0.44 USD

Dearest project

ShahanPanel at 3.15 USD

Cheapest project

duckle 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

2065

Of those, reached a working state

1489

Most measured languages

Python (535), TypeScript (456), Go (290), Rust (230), JavaScript (199)

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.

8 projects

Go compiler not found in container

8 projects

Rust toolchain not installed

6 projects

pnpm not found in PATH

3 projects

Go not found in container

3 projects

Go not installed in container

The result most worth reading

shopper scored 100 of 100, after hitting 9 errors that the agent fixed with no human help.

Shopper monorepo dependencies installed, 630+ Pest tests pass on SQLite with 0 failures. The npm CSS/JS build cannot complete because the @tailwindcss/cli package requires Node >=20.19 (only Node 18.19 is available).

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

Real-service behavior for 153 of them

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

The report as written

Argusic installed and ran 656 projects on clean machines between 2026-10-05 and 2026-10-12, over 748 attempts, 1 fewer subjects than the week before.

458 were verified against the real thing, 153 only against stand-in services, and 137 could not be verified at all.

656 projects were tested here for the first time.

The same problems keep appearing across unrelated projects. The most common this week was "Go compiler not found in container", which stopped 8 projects. Also recurring: "Rust toolchain not installed" (8), "pnpm not found in PATH" (6), "Go not found in container" (3), "Go not installed in container" (3).

The result most worth reading was shopper, which scored 100 of 100 after hitting 9 errors that the agent fixed with no human help. In the agent's own words: Shopper monorepo dependencies installed, 630+ Pest tests pass on SQLite with 0 failures. The npm CSS/JS build cannot complete because the @tailwindcss/cli package requires Node >=20.19 (only Node 18.19 is available).

Running all of this cost 285.38 USD, of which 30% was model tokens rather than machines.

85.48 USD of that was model tokens and 199.90 USD was machines, which is 0.44 USD for each project measured.

The dearest project of the week was ShahanPanel at 3.15 USD, the cheapest duckle 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: 755 attempts on CPU machines at 0.1192 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-MO-2, US-NC-1, US-NE-1.

Across everything measured so far, 2065 projects have been installed and run here, and 1489 of them reached a working state. Most of them are written in Python (535), TypeScript (456), Go (290), Rust (230), JavaScript (199).

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