Strata

Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.

Runs with mockssource: GitHubC++MITcommit 1678de333d0e

C++, MIT licensed.

Strata runs, with stand-ins for the services it depends on. An Argusic agent installed it in 5 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

All 24 Python test modules pass: 132 setup tests (golden config, choices, AMD, low-RAM, pins, prompts, risk, rope, unsloth, draft vocab), 34 conversation cache tests, 10 calibrate tests, 22 strata_mcp tests, and 88 server tests (API via MockEngine with correct max-tokens budgeting, streaming, error handling, model aliases, lifecycle, telemetry, MCP integration, chat template rendering, and structured output).

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

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.64 (measured)
recorded runs
2
last tested
stars
45,341
forks
5,025
open issues
1,616
watchers
213
size
111 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.

Time lost to each failure while testing Strata, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • Golden baseline stale after setup.py changes: 'log' field changed from 'strata-<model>.log' to '<EXE>-<model>.log' on Linux where EXE='strata' not 'strata.exe'1 minute
  • test_enter_for_every_question failed for Unsloth UD-Q4_K_XL on low-RAM profiles (32GB, 47GB): confirm_risk() asked 'Install it anyway?' and Enter defaulted to 'n' (fail)1 minute
  • test_prebuilt_hip_zip failed on Linux: zip only contained strata.exe but EXE='strata', so (tmp/EXE).exists() failed1 minute
Install time
5 minutes
Cold machine to finish
39 minutes
Errors hit and fixed
3 hit, 3 fixed with no human help
How the result was proved
python -m unittest <all 24 test modules> ran 344 tests in 92.9s, OK (skipped=9)
Model tokens used
262,219
Exact commit tested
1678de333d0e
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.

.....................ss............sssssss...
Ran 344 tests in 92.872s
OK (skipped=9)
exit=0
[strata] done: 50 tokens in 0 s (92385.6 tok/s) (stop, cancel=False)
[strata] done: 50 tokens in 0 s (94084.9 tok/s) (stop, cancel=False)
[strata] done: 7 tokens in 0 s (121322.8 tok/s) (stop, cancel=False)
All 344 tests pass (9 expected skips). Here's the final report:
2026-11-02T02:06:27.290604Z ERROR codex_core::session: failed to record rollout items: thread 01a19…
tokens used
262,219
All 344 tests pass (9 expected skips). Here's the final report:

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

  • Installed in 5 minutes, faster than the median of the 4 comparable projects Argusic has measured.
  • 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.
  • Measured 2 times, so the result is not a one-off.

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.

Of the 5 C++ projects Argusic has installed and timed, Strata was the 2nd fastest to reach a running state, and 2 of 5 reached one at all.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs with mocks92.000.64
Argusic Runner1/3Runs with mocks92.000.19

Embed the badge

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

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

Questions

Does Strata run?
Strata runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 5 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test Strata?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 1678de333d0e. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test Strata?
The run that produced this verdict cost $0.64: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does Strata take to install?
5 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 Strata need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing Strata?
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 Strata compare with the alternatives?
Of the 5 C++ projects Argusic has installed and timed, Strata was the 2nd fastest to reach a running state, and 2 of 5 reached one at all.
Where is the evidence for Strata?
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