exo
Run frontier AI locally.
Runssource: GitHubPythonApache-2.0commit 21a54c5ea023
Python, Apache-2.0 licensed.
exo runs. An Argusic agent installed it in 10 minutes and hit 5 errors on a clean machine with no GPU, and the whole session was recorded.
exo server starts on port 52415, API responds 200 on /state, 298/303 unit tests pass (5 mlx/worker GPU-dependent tests excluded), dashboard Svelte build completes, ruff linting passes, basedpyright strict type checking passes with 0 errors
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 92 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.
- uv binary not found in environment1 minute
- Python 3.13 not available (system has 3.12)1 minute
- exo_tools workspace package not installed by uv sync1 minute
- mlx.core CUDA prebuilt wheel has undefined symbol on CPU-only Linux container
- 5 test collection errors in mlx/worker tests due to missing GPU accelerator
- Install time
- 10 minutes
- Cold machine to finish
- 16 minutes
- Errors hit and fixed
- 5 hit, 3 fixed with no human help
- How the result was proved
- uv run pytest src/ --ignore=src/exo/worker returned 298 passed, 5 skipped; curl -s -o /dev/null -w %25{http_code} http://localhost:52415/state returned 200; uv run exo --help prints usage; uv run ruff check passes; uv run basedpyright returns 0 errors
- Model tokens used
- 71,494
- Exact commit tested
- 21a54c5ea023
- 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.
exec
/bin/sh -lc "echo '{\"install_succeeded\":true,\"launch_succeeded\":true,\"install_minutes\":10,\"e…
succeeded in 0ms:
{"install_succeeded":true,"launch_succeeded":true,"install_minutes":10,"errors":[{"msg":"uv binary …
exec
/bin/sh -lc "echo -n 'ARGUSIC_RESULT:{\"install_succeeded\":true,\"launch_succeeded\":true,\"instal…
succeeded in 0ms:
exec
/bin/sh -lc "echo -n 'ARGUSIC_RESULT:{\"install_succeeded\":true,\"launch_succeeded\":true,\"instal…
succeeded in 0ms:
tokens used
71,494Replay 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.
- 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
- Took 10 minutes to install, slower than the median of the 35 comparable projects Argusic has measured.
- Hit 5 errors during setup, 2 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 36 Python projects Argusic has installed and timed, exo was the 30th fastest to reach a running state, and 20 of 36 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 10 minutes after the clone.
Run history
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/exo)Questions
- Does exo run?
- Yes. exo runs. Argusic installed and launched it on a clean machine in 10 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test exo?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 21a54c5ea023. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test exo?
- The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does exo take to install?
- 10 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 exo need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing exo?
- 5 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 exo compare with the alternatives?
- Of the 36 Python projects Argusic has installed and timed, exo was the 30th fastest to reach a running state, and 20 of 36 reached one at all.
- Where is the evidence for exo?
- 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.