564 projects tested, and "npm install failed" stopped 5: week of October 12, 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

698 at 0.1195 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

87.76 USD

Machines

93.06 USD

Per project measured

0.32 USD

Dearest project

markdowndb at 2.91 USD

Cheapest project

Stealth-Requests 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

2628

Of those, reached a working state

1852

Most measured languages

Python (662), TypeScript (595), Go (363), Rust (292), JavaScript (268)

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.

5 projects

npm install failed

4 projects

PHP not installed in container

4 projects

pnpm not installed

4 projects

Rust toolchain not installed

3 projects

composer install failed

The result most worth reading

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

All three services (mm_server on port 50110, mmrag_server on port 8001, qmedia_web on port 3000) are installed and respond to API calls; mmrag_server loads persisted index from db/ with embeddings for 14 assets and serves note search and detail APIs.

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

Real-service behavior for 158 of them

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

The report as written

Argusic installed and ran 564 projects on clean machines between 2026-10-12 and 2026-10-19, over 652 attempts, 92 fewer subjects than the week before.

363 were verified against the real thing, 158 only against stand-in services, and 131 could not be verified at all.

563 projects were tested here for the first time.

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

The result most worth reading was Qmedia, which scored 100 of 100 after hitting 11 errors that the agent fixed with no human help. In the agent's own words: All three services (mm_server on port 50110, mmrag_server on port 8001, qmedia_web on port 3000) are installed and respond to API calls; mmrag_server loads persisted index from db/ with embeddings for 14 assets and serves note search and detail APIs.

Running all of this cost 180.82 USD, of which 49% was model tokens rather than machines.

87.76 USD of that was model tokens and 93.06 USD was machines, which is 0.32 USD for each project measured.

The dearest project of the week was markdowndb at 2.91 USD, the cheapest Stealth-Requests 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: 698 attempts on CPU machines at 0.1195 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, 2628 projects have been installed and run here, and 1852 of them reached a working state. Most of them are written in Python (662), TypeScript (595), Go (363), Rust (292), JavaScript (268).

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