Yes. phantom runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 3 errors on the way, and recorded the session.

How did Argusic test phantom?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit f8c7ab42d885. 2 attempts are recorded, and the full method is on the methodology page.

What did it cost to test phantom?

The run that produced this verdict cost $0.31: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does phantom 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 phantom need a GPU?

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

What goes wrong when installing phantom?

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.

Where is the evidence for phantom?

All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

phantom

An AI co-worker with its own computer. Self-evolving, persistent memory, MCP server, secure credential collection, email identity. Built on the Claude Agent SDK.

Runssource: GitHub homepageTypeScriptApache-2.0commit f8c7ab42d885

TypeScript, Apache-2.0 licensed. The project labels itself: ai agents, ai coworker, anthropic, autonomous agents, bun, claude, docker and llm.

phantom runs. An Argusic agent installed it in 1 minute and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

2639 tests pass, the HTTP server starts on port 3100 and returns 302 on GET /, and the CLI phantom doctor command reports the project configuration is valid.
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 60 of 100 (the mean of this project's run scores).

At a glance

verdict: Runs
Argusic Score: 60 / 100
cost of the verifying run: $0.31 (measured)
recorded runs: 2
last tested: 2026-10-07
stars: 1,480
forks: 194
open issues: 65
watchers: 13
size: 21 MB
created: 2026-03-26
last push: 2026-06-16

Subject data from GitHub, linked at the top of this page, refreshed 2026-10-07. 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 phantom, 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.

Bun treats `process.env.VAR = undefined` as string "undefined" (9 chars) instead of removing the variable8 minutes
Container has /.dockerenv file, causing false Docker detection in prompt-assembler test2 minutes
afterEach env restore leaked undefined across test files2 minutes

Install time: 1 minutes
Cold machine to finish: 34 minutes
Errors hit and fixed: 3 hit, 3 fixed with no human help
How the result was proved: npx bun test exited 0: 2639 passed, 0 failed
Model tokens used: 180,607
Exact commit tested: f8c7ab42d885
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

The end of the recording

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

# Summary
**Install**: `npm install --legacy-peer-deps` (since `bun` is not in PATH, `npx bun` is used instea…
**Test suite**: All 2639 tests pass (0 failures). 10 skipped (pre-existing integration tests requir…
**App launch**: The HTTP server starts and listens on port 3100, returning 302 redirect on `/`.
**9 bugs fixed** (all related to `process.env.X = undefined` string coercion in Bun + `/.dockerenv`…
All fixes were in test files — the production code is correct.
exec
/bin/sh -lc "cd /work/repo && echo '{\"install_succeeded\": true, \"launch_succeeded\": true, \"ins…
 succeeded in 0ms:
{"install_succeeded": true, "launch_succeeded": true, "install_minutes": 1, "errors": [{"msg": "Bun…
tokens used
180,607

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.
Installed in 1 minute, faster than the median of the 47 comparable projects Argusic has measured.
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 Apache-2.0, as reported by its host.
Measured 2 times, so the result is not a one-off.

Of the 48 ai-agents projects Argusic has installed and timed, phantom was the 7th fastest to reach a running state, and 36 of 48 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.
A quick evaluation: it was running 1 minutes after the clone.

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	2/3	Runs	100.00	0.31	2026-10-07 16:52 UTC
Argusic Runner	1/3	Did not run	20.00	0.01	2026-10-07 16:18 UTC

Topics (from GitHub)

ai-agents ai-coworker anthropic autonomous-agents bun claude docker llm mcp self-evolution slack typescript

Embed the badge

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

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

Questions

Does phantom run?: Yes. phantom runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test phantom?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit f8c7ab42d885. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test phantom?: The run that produced this verdict cost $0.31: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does phantom 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 phantom need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing phantom?: 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 phantom compare with the alternatives?: Of the 48 ai-agents projects Argusic has installed and timed, phantom was the 7th fastest to reach a running state, and 36 of 48 reached one at all.
Where is the evidence for phantom?: All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.