agentbox
Run multiple agents in parallel sandboxed VMs, with a single command, on your PC or in the cloud
Runssource: GitHubhomepageTypeScriptMITcommit 605ee75d6331
TypeScript, MIT licensed. The project labels itself: claude, claude code, cli, cmux, codex, codex cli, coding agents and developer tools.
agentbox runs. An Argusic agent installed it in 11 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The AgentBox monorepo builds and all 46 package test suites pass (0 failures, 0 cached failures), the agentbox CLI binary responds with correct version/help output, and rsync is available at /home/runner/.npm-global/bin/rsync for the sync-layer tests
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
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.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- rsync binary not found, causing 9 test failures in sandbox-core3 minutes
- Node.js v18.19.1 does not satisfy engines.node >=20.101 minute
- pnpm binary not found on PATH1 minute
- Install time
- 11 minutes
- Cold machine to finish
- 19 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- pnpm test exited 0,46/46turbo tasks successful, all test files passed (25+ config, 183+ CLI, 55+ sandbox-core, etc.)
- Model tokens used
- 276,725
- Exact commit tested
- 605ee75d6331
- 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.
=== Final test count ===
Test Files 25 passed (25)
Tests 237 passed (237)
Start at 16:35:19
Duration 4.24s (transform 657ms, setup 318ms, collect 2.52s, tests 1.19s, environment 9ms, prep…
=== rsync available ===
/home/runner/.npm-global/bin/rsync
rsync version 3.4.4 protocol version 32
All tests pass after fixing three environment issues. Here's my final report:
tokens used
276,725
All tests pass after fixing three environment issues. Here's my final report: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 3 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 11 minutes to install, slower than the median of the 8 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 9 claude projects Argusic has installed and timed, agentbox was the 8th fastest to reach a running state, and 5 of 9 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
Topics (from GitHub)
claudeclaude-codeclicmuxcodexcodex-clicoding-agentsdeveloper-toolsdockergrok-buildharnessherdr-pluginiterm2opencodesandboxtmux
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/agentbox)Questions
- Does agentbox run?
- Yes. agentbox runs. Argusic installed and launched it on a clean machine in 11 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test agentbox?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 605ee75d6331. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test agentbox?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does agentbox take to install?
- 11 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 agentbox need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing agentbox?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does agentbox compare with the alternatives?
- Of the 9 claude projects Argusic has installed and timed, agentbox was the 8th fastest to reach a running state, and 5 of 9 reached one at all.
- Where is the evidence for agentbox?
- 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.