sagify

LLMs and Machine Learning done easily

Runs with mockssource: GitHubhomepagePythonMITcommit 054a6a2edc21

Python, MIT licensed. The project labels itself: ai gateway, anthropic, cohere, generative ai, langchain, langchain python, large language model and large language models.

sagify runs, with stand-ins for the services it depends on. An Argusic agent installed it in 30 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

sagify 0.25.4 installed in a Python 3.12 virtual environment. CLI responds to --help with 7 command groups (build, cloud, configure, init, llm, local, push) and all 63 existing pytest unit tests pass.

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
$0.20 (measured)
recorded runs
1
last tested
stars
442
forks
68
open issues
18
watchers
16
size
37 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 sagify, 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.

  • LLM gateway dependencies (structlog, anthropic, uvicorn, fastapi, openai, Pillow) not listed in setup.py install_requires4 minutes
  • future 0.18.3 references removed `imp` module on Python 3.123 minutes
  • pkg_resources missing with setuptools 84.x3 minutes
Install time
30 minutes
Cold machine to finish
14 minutes
Errors hit and fixed
3 hit, 3 fixed with no human help
How the result was proved
/tmp/venv/bin/python -m pytest tests/ -q exited 0: 63 passed, 3 warnings in 12.74s
Model tokens used
97,587
Exact commit tested
054a6a2edc21
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.

-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
63 passed, 3 warnings in 12.74s
All verification is complete. Here is the summary:
exec
/bin/sh -lc "cd /work/repo && echo '{\"install_succeeded\":true,\"launch_succeeded\":true,\"install…
 succeeded in 0ms:
{"install_succeeded":true,"launch_succeeded":true,"install_minutes":30,"errors":[{"msg":"future 0.1…
exec
/bin/sh -lc "cd /work/repo && ARGUSIC_RESULT='{\"install_succeeded\":true,\"launch_succeeded\":true…
 succeeded in 0ms:
tokens used
97,587

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 30 minutes to install, slower than the median of the 23 comparable projects Argusic has measured.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 24 ai-gateway projects Argusic has installed and timed, sagify was the 23rd fastest to reach a running state, and 18 of 24 reached one at all.

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.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs with mocks92.000.20

Topics (from GitHub)

ai-gatewayanthropiccoheregenerative-ailangchainlangchain-pythonlarge-language-modellarge-language-modelsllmllm-inferencellmopsopen-source-llmopenaisagemaker

Embed the badge

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

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

Questions

Does sagify run?
sagify runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 30 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test sagify?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 054a6a2edc21. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test sagify?
The run that produced this verdict cost $0.20: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does sagify take to install?
30 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 sagify need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing sagify?
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 sagify compare with the alternatives?
Of the 24 ai-gateway projects Argusic has installed and timed, sagify was the 23rd fastest to reach a running state, and 18 of 24 reached one at all.
Where is the evidence for sagify?
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.

Discussion