AgentENV
AgentENV (AENV) is a distributed platform for running agent environments at scale.
Runssource: GitHubRustMITcommit 5843159b1eaf
Rust, MIT licensed.
AgentENV runs. An Argusic agent installed it in 36 minutes and hit 5 errors on a clean machine with no GPU, and the whole session was recorded.
Both server and aenv CLI binaries compile from source in debug profile; 947 agentenv unit tests, 110 CLI tests, 7 object-store-operator tests, 18 ublk tests pass; overlaybd lib tests pass with 6 expected direct-I/O failures on tmpfs; cargo fmt --check and cargo clippy --all-targets both clean
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 96 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page. 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.
- libclang not found (bindgen dependency)3 minutes
- Rust toolchain not installed2 minutes
- stdbool.h not found (rocksdb-sys dependency)2 minutes
- protoc not found (prost-build dependency)1 minute
- 6 overlaybd direct-I/O tests fail in container (O_DIRECT unsupported on tmpfs)
- Install time
- 36 minutes
- Cold machine to finish
- 42 minutes
- Errors hit and fixed
- 5 hit, 4 fixed with no human help
- How the result was proved
- cargo test --lib -p agentenv: 947/947 passed; cargo test -p aenv: 110/110 passed; cargo test --lib -p object-store-operator: 7/7 passed; cargo test --lib -p uvm-ublk: 18/18 passed; cargo clippy --all-targets: clean; cargo fmt --check: clean; aenv --version: aenv 0.2.3; server --help: prints usage
- Model tokens used
- 309,117
- Exact commit tested
- 5843159b1eaf
- 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.
- `cargo test --lib -p agentenv` — **947 passed, 0 failed, 4 ignored**
- `cargo test -p aenv` — **110 passed, 0 failed**
- `cargo test --lib -p object-store-operator` — **7 passed, 0 failed**
- `cargo test --lib -p uvm-ublk` — **18 passed, 0 failed**
- `cargo test --lib -p overlaybd` — **377 passed, 6 failed** (all 6 failures are direct-I/O tests t…
- Integration tests (`cargo test -p agentenv --test integration`): 21 tests skipped — all require `…
exec
/bin/sh -lc "echo '{\"install_succeeded\": true, \"launch_succeeded\": true, \"install_minutes\": 3…
succeeded in 0ms:
{"install_succeeded": true, "launch_succeeded": true, "install_minutes": 36, "errors": [{"msg": "Ru…
tokens used
309,117Replay 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 MIT, as reported by its host.
What did not, or is not known
- Took 36 minutes to install, slower than the median of the 9 comparable projects Argusic has measured.
- Hit 5 errors 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 10 Rust projects Argusic has installed and timed, AgentENV was the 8th fastest to reach a running state, and 9 of 10 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.
Run history
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/agentenv)Questions
- Does AgentENV run?
- Yes. AgentENV runs. Argusic installed and launched it on a clean machine in 36 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test AgentENV?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 5843159b1eaf. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test AgentENV?
- 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.
- How long does AgentENV take to install?
- 36 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 AgentENV need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing AgentENV?
- 5 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does AgentENV compare with the alternatives?
- Of the 10 Rust projects Argusic has installed and timed, AgentENV was the 8th fastest to reach a running state, and 9 of 10 reached one at all.
- Where is the evidence for AgentENV?
- 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.