mirage

The World's First Virtual Terminal for AI Agents

Could not verifysource: GitHubhomepageTypeScriptApache-2.0commit edf559fe79a9

TypeScript, Apache-2.0 licensed. The project labels itself: agent sandbox, agent tools, ai agents, bash, claude code, dsh, dsh plugin and fuse.

Argusic could not get mirage 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. Argusic Score 20 of 100 (the mean of this project's run scores).

At a glance

verdict
Could not verify
Argusic Score
20 / 100
cost of the verifying run
$0.05 (measured)
recorded runs
2
last tested
stars
3,675
forks
272
open issues
86
watchers
9
size
81 MB
created
last push

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.

Cold machine to finish
31 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
Exact commit tested
edf559fe79a9
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
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
this run verified nothing, so this page makes no claim either way

The end of the recording

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

exec
/bin/sh -lc 'cd /work/repo/python && .venv/bin/python -m pytest -q -x tests/vfs/disk/test_ram.py te…
 succeeded in 5244ms:
........................................................................ [ 41%]
........................................................................ [ 82%]
...............................                                          [100%]
Now let me run the core tests that don't need daemons or external services. Let me try a larger bat…
exec
/bin/sh -lc 'cd /work/repo/python && .venv/bin/python -m pytest -q -x tests/test_types.py tests/tes…
/work/run-agent.sh: line 4:  1030 Exit 101                codex exec --skip-git-repo-check --danger…
      1031 Broken pipe             | tee /work/agent-output.txt
      1032 Killed                  | python3 -u /work/brand-codex.py

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.

  • deepseek-harness verified to run · TypeScript · 3 shared topics
  • dsh-routing-suite verified to run · JavaScript · 3 shared topics
  • loopx verified to run · Python · 3 shared topics
  • tuios verified to run · Go · 3 shared topics
  • Vibe-Skills verified to run · Python · 3 shared topics
  • distilly tested, not verified · Python · 3 shared topics

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Did not run20.000.05
Argusic Runner1/3Did not run20.000.24

Topics (from GitHub)

agent-sandboxagent-toolsai-agentsbashclaude-codedshdsh-pluginfusellm-agentsopenai-agentspythonsshtypescriptvfsvirtual-filesystemvirtual-terminal

Embed the badge

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

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

Questions

Does mirage run?
Argusic could not verify that mirage runs. Argusic installed and launched it on a clean machine, hitting 0 errors on the way, and recorded the session.
How did Argusic test mirage?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit edf559fe79a9. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test mirage?
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.
Does mirage need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing mirage?
Nothing did, in the recorded run: zero errors between clone and running.
Where is the evidence for mirage?
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.

Discussion