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

How did Argusic test agentplay?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit 3851f5b05bc8. One attempt is recorded, and the full method is on the methodology page.

What did it cost to test agentplay?

The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does agentplay take to install?

3 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 agentplay need a GPU?

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

What goes wrong when installing agentplay?

1 thing broke in the recorded run. Each one, and the time it cost, is listed on this page.

Where is the evidence for agentplay?

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.

agentplay

Replay your coding agent sessions as a map and a timeline

Runssource: GitHub homepagePythonApache-2.0commit 3851f5b05bc8

Python, Apache-2.0 licensed. The project labels itself: agent observability, ai agents, claude, claude code, codex, coding agents, cursor and developer tools.

agentplay runs. An Argusic agent installed it in 3 minutes and hit 1 error on a clean machine with no GPU, and the whole session was recorded.

Python package agentplay 0.2.2 installed from source, 991 tests pass, CLI builds sessions from Codex history and serves a functional web viewer with API returning available=true.
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 80 of 100 (the mean of this project's run scores).

At a glance

verdict: Runs
Argusic Score: 80 / 100
cost of the verifying run: $0.03 (measured)
recorded runs: 1
last tested: 2026-10-25
stars: 307
forks: 27
open issues: 24
watchers: 0
size: 2 MB
created: 2026-10-14
last push: 2026-10-24

Subject data from GitHub, linked at the top of this page, refreshed 2026-10-25. 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 agentplay, 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.

Viewer vitest tests fail: 'File is not defined' (Node 18 vs 22+ global File API) and 'ERR_REQUIRE_ESM' in jsdom/html-encoding-sniffer. Root cause: Node.js v18.19.1 < required >=22. The viewer itself builds and serves correctly; only the test runner is affected.5 minutes

Install time: 3 minutes
Cold machine to finish: 5 minutes
Errors hit and fixed: 1 hit, 0 fixed with no human help
How the result was proved: cd /work/repo && python/.venv/bin/pytest python/tests -q => 991 passed; curl -s http://127.0.0.1:7317/api/status => {"success":true,"available":true,"mapCount":1}
Model tokens used: 43,434
Exact commit tested: 3851f5b05bc8
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.

43,434
Here is the complete report:
**Summary of work done:**
- Created a Python virtual environment, installed the package (editable) with dev dependencies.
- Built the web viewer (pnpm install + build), copied the viewer dist into the Python package.
- All 991 Python tests pass.
- `agentplay --version` prints `agentplay 0.2.2`.
- `agentplay build` built 1 Argusic Agent session from the existing Argusic Agent history.
- `agentplay view --no-build --no-open` serves the viewer on `http://127.0.0.1:7317/`.
- `curl http://127.0.0.1:7317/api/status` returns `{"success":true,"available":true,"mapCount":1}`.
- The viewer's HTML page is served correctly.
- Viewer's vitest tests fail because Node.js 18 (not 22+) does not support `File` globally and cann…

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 3 minutes.
Ran without a GPU, so it does not need one to start.
Licensed Apache-2.0, as reported by its host.

What did not, or is not known

Hit 1 error during setup, 1 of which were not solved.
Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 17 claude-code projects Argusic has installed and timed, agentplay was the 9th fastest to reach a running state, and 16 of 17 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 3 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	1/3	Runs	80.00	0.03	2026-10-25 13:21 UTC

Topics (from GitHub)

agent-observability ai-agents claude claude-code codex coding-agents cursor developer-tools devtools github-copilot kiro llm observability opencode privacy python session-replay typescript visualization

Embed the badge

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

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

Questions

Does agentplay run?: Yes. agentplay runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test agentplay?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit 3851f5b05bc8. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test agentplay?: The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does agentplay take to install?: 3 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 agentplay need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing agentplay?: 1 thing broke in the recorded run. Each one, and the time it cost, is listed on this page.
How does agentplay compare with the alternatives?: Of the 17 claude-code projects Argusic has installed and timed, agentplay was the 9th fastest to reach a running state, and 16 of 17 reached one at all.
Where is the evidence for agentplay?: 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.