devbox runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 1 minutes, hitting 1 error on the way, and recorded the session.

How did Argusic test devbox?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit fc2b4270eb80. One attempt is recorded, and the full method is on the methodology page.

What did it cost to test devbox?

The run that produced this verdict cost $0.04: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does devbox take to install?

1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.

Does devbox need a GPU?

Not to start. Argusic reached a running state on a machine with no GPU.

What goes wrong when installing devbox?

1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.

Where is the evidence for devbox?

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.

devbox

Open source autonomous engineering harness in your cloud. One sandbox per task, no real secrets inside.

Runs with mockssource: GitHub homepageTypeScriptMITcommit fc2b4270eb80

TypeScript, MIT licensed. The project labels itself: agent harness, agent sandbox, agent security, agentic coding, autonomous agents, background agents, coding agents and harness engineering.

devbox runs, with stand-ins for the services it depends on. An Argusic agent installed it in 1 minute and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

All three component test suites (CLI 293/293, harness 1101/1101, helm chart 126/126) pass. Control-plane 1597/1608 pass; the 8 failures all require PostgreSQL 18 which is not available in this container. The CLI binary responds to its help command listing 10 commands.
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 92 of 100 (the mean of this project's run scores).

At a glance

verdict: Runs with mocks
Argusic Score: 92 / 100
cost of the verifying run: $0.04 (measured)
recorded runs: 1
last tested: 2026-11-01
stars: 267
forks: 16
open issues: 11
watchers: 0
size: 7 MB
created: 2026-10-27
last push: 2026-10-31

Subject data from GitHub, linked at the top of this page, refreshed 2026-11-02. 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 devbox, 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.

8 control-plane tests fail: no PostgreSQL 18 database available in container1 minute

Install time: 1 minutes
Cold machine to finish: 8 minutes
Errors hit and fixed: 1 hit, 1 fixed with no human help
How the result was proved: bun test (cli): 293/293 pass; bun test (control-plane): 1597/1608 pass, 8 DB-dependent fail; python3 -m unittest (harness): 1101/1101 pass; bun test (helm chart): 126/126 pass
Model tokens used: 177,450
Exact commit tested: fc2b4270eb80
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
Behaviour against real services: this run was verified against stand-in services only

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

**Chart tests (Helm):** 126 pass, 0 fail across 7 test files ✅
The `scripts.test.ts` file hangs in this sandbox due to subprocess spawning — not a repo defect.
Total install time: installing Bun (8s + download), uv/Python deps (3s), control-plane deps (1s), C…
tokens used
177,450
Now I have the full picture. Here's the summary of everything observed:
**CLI:** 293 pass, 0 fail ✅
**Harness (Python):** 1101 pass, 0 fail (7 skipped) ✅
**Control-plane (Bun):** 1597 pass, 3 skip, 8 fail — all 8 failures are from missing PostgreSQL (no…
**Chart tests (Helm):** 126 pass, 0 fail across 7 test files ✅
The `scripts.test.ts` file hangs in this sandbox due to subprocess spawning — not a repo defect.
Total install time: installing Bun (8s + download), uv/Python deps (3s), control-plane deps (1s), C…

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

Installed in 1 minute, faster than the median of the 8 comparable projects Argusic has measured.
Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
Licensed MIT, as reported by its host.

What did not, or is not known

Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 9 agent-harness projects Argusic has installed and timed, devbox was the 1st fastest to reach a running state, and 6 of 9 reached one at all.

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 by	attempt	outcome	score	cost USD	when
Argusic Runner	1/3	Runs with mocks	92.00	0.04	2026-11-01 10:24 UTC

Topics (from GitHub)

agent-harness agent-sandbox agent-security agentic-coding autonomous-agents background-agents coding-agents harness-engineering

Embed the badge

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

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

Questions

Does devbox run?: devbox runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 1 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test devbox?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit fc2b4270eb80. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test devbox?: The run that produced this verdict cost $0.04: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does devbox take to install?: 1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does devbox need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing devbox?: 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does devbox compare with the alternatives?: Of the 9 agent-harness projects Argusic has installed and timed, devbox was the 1st fastest to reach a running state, and 6 of 9 reached one at all.
Where is the evidence for devbox?: 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.