Argusic could not verify that atlas runs. Argusic installed and launched it on a clean machine, hitting 0 errors on the way, and recorded the session.

How did Argusic test atlas?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7abe155908f6. 2 attempts are recorded, and the full method is on the methodology page.

What did it cost to test atlas?

The run that produced this verdict cost $0.15: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

Does atlas need a GPU?

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

What goes wrong when installing atlas?

Nothing did, in the recorded run: zero errors between clone and running.

Where is the evidence for atlas?

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.

atlas

Source control for agents. Use multiple coding agents, track their changes and query them in one place

Could not verifysource: GitHub homepageTypeScriptApache-2.0commit 7abe155908f6

TypeScript, Apache-2.0 licensed. The project labels itself: ai, ai coding assistant, claude code, codex, coding agents, git, gitops and kilo code.

Argusic could not get atlas running. An Argusic agent hit no errors on a clean machine with no GPU, and the whole session was recorded.

Measured by Argusic on a fresh machine every time. Every number links to its evidence.

At a glance

verdict: Could not verify
Argusic Score: not scored yet
cost of the verifying run: $0.15 (measured)
recorded runs: 2
last tested: 2026-09-08
stars: 6,042
forks: 303
open issues: 27
watchers: 33
size: 30 MB
created: 2026-05-14
last push: 2026-09-23

Subject data from GitHub, linked at the top of this page, refreshed 2026-09-23. 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.

Exact commit tested: 7abe155908f6
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.

Install time: the run did not report one
Cold machine to finish: the attempt was stopped at the time limit after 87 minutes, so it never finished
Errors hit and fixed: the attempt was cut off at the time limit before it reported what it had hit
How the result was proved: runs before 2026-09-07 did not record the command used to check the result
Peak GPU memory: this ran on a CPU machine, so there was no GPU to sample
Model tokens used: not recorded for this run
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
Whether it works at all: the attempt did not get far enough to verify anything before the time limit

The end of the recording

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

ls /work/repo/target/debug/.fingerprint/ 2>/dev/null | wc -l" in /work/repo
 succeeded in 721ms:
467
1853
It's making good progress - 467 crates compiled so far. Let me let it continue. Let me wait more pa…
Let me check progress again.
exec
/bin/sh -lc 'ls /work/repo/target/debug/deps/*.d 2>/dev/null | wc -l
ls /work/repo/target/debug/.fingerprint/ 2>/dev/null | wc -l' in /work/repo
 succeeded in 908ms:
521
1853

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

Nothing broke on the way: zero errors between clone and running.
Licensed Apache-2.0, as reported by its host.
Measured 2 times, so the result is not a one-off.

What did not, or is not known

An agent with no time limit did not get it running.

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	Ran out of time	0.00	0.15	2026-09-08 11:19 UTC
Argusic Runner	1/3	Ran out of time	0.00	0.28	2026-09-07 17:23 UTC

Topics (from GitHub)

ai ai-coding-assistant claude-code codex coding-agents git gitops kilo-code mcp mcp-client opencode opencode-ai opencode-skills self-hosted skills

Embed the badge

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

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

Questions

Does atlas run?: Argusic could not verify that atlas runs. Argusic installed and launched it on a clean machine, hitting 0 errors on the way, and recorded the session.
How did Argusic test atlas?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7abe155908f6. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test atlas?: The run that produced this verdict cost $0.15: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
Does atlas need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing atlas?: Nothing did, in the recorded run: zero errors between clone and running.
Where is the evidence for atlas?: 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.