jev-ultrafast
Fastest and cheapest web agent
Runs with mockssource: GitHubhomepagePythonMITcommit 1231850a0bf1
Python, MIT licensed.
jev-ultrafast runs, with stand-ins for the services it depends on. An Argusic agent installed it in 9 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
uv sync installs cleanly, all 31 offline unit tests pass, all 21 browser guard checks pass against real Chromium 156, ruff lint is clean, JS syntax checks pass, uv build produces valid wheel/sdist, and the demo HTTP server starts and answers 200 on http://127.0.0.1:8766
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.
- browser-harness ensure_daemon() failed to detect running Chrome4 minutes
- No Chromium browser found in container3 minutes
- uv not found in PATH0.5 minutes
- Install time
- 9 minutes
- Cold machine to finish
- 8 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- uv run pytest exited 0, 31 passed; scripts/check_guards.py exited 0, 21 browser guard checks passed against real Chromium 156 headless; ruff check . passed; node --check app.js && node --check snapshot.js passed; uv build built wheel and sdist; uv run jev started demo server, curl returned HTTP 200
- Model tokens used
- 292,145
- Exact commit tested
- 1231850a0bf1
- 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
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
tokens used 292,145 Here's the final report: **Summary of what was done:** - Installed `uv` via `pip install --break-system-packages uv` - Ran `uv sync` — resolved and installed all 22 dependencies cleanly - Downloaded Chromium 156 snapshot (no system package available) so browser interaction could be te… - Started Chrome with `--headless=new --no-sandbox --remote-debugging-port=9222` and the browser-ha… - All 31 unit tests pass (offline, model APIs mocked) - All 21 browser guard checks (`check_guards.py`) pass against real Chromium — exercises DOM snapsh… - Demo server starts and returns HTTP 200 - Ruff lint, Node.js syntax checks, and `uv build` all pass
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
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Took 9 minutes to install, slower than the median of the 6 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 7 Python projects Argusic has installed and timed, jev-ultrafast was the 7th fastest to reach a running state, and 4 of 7 reached one at all.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.06 |
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/jev-ultrafast)Questions
- Does jev-ultrafast run?
- jev-ultrafast runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 9 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test jev-ultrafast?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 1231850a0bf1. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test jev-ultrafast?
- The run that produced this verdict cost $0.06: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does jev-ultrafast take to install?
- 9 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 jev-ultrafast need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing jev-ultrafast?
- 3 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 jev-ultrafast compare with the alternatives?
- Of the 7 Python projects Argusic has installed and timed, jev-ultrafast was the 7th fastest to reach a running state, and 4 of 7 reached one at all.
- Where is the evidence for jev-ultrafast?
- 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.