agent-starter-pack

Ship AI Agents to Google Cloud in minutes, not months. Production-ready templates with built-in CI/CD, evaluation, and observability.

Runssource: GitHubhomepagePythonApache-2.0commit 659f04774245

Python, Apache-2.0 licensed. The project labels itself: agents, gcp, gemini, genai agents, generative ai, llmops, mlops and observability.

agent-starter-pack runs. An Argusic agent installed it in 5 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

The agent-starter-pack v0.41.3 CLI installs, builds, and passes all 498 unit tests with the agent-starter-pack list, --help, and --version commands working correctly; uv is available at /home/runner/.local/bin/uv.

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 90 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
90 / 100
cost of the verifying run
$0.03 (measured)
recorded runs
2
last tested
stars
6,560
forks
1,501
open issues
50
watchers
64
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 agent-starter-pack, 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.

  • test_smart_merge_preserves_user_dependencies failed because uv was not in PATH, causing _write_dependencies_to_pyproject to log 'uv not found' and return False2 minutes
Install time
5 minutes
Cold machine to finish
8 minutes
Errors hit and fixed
1 hit, 1 fixed with no human help
How the result was proved
uv run pytest tests --ignore=tests/integration -q exited 0, 498 passed, 3 skipped; agent-starter-pack --version returned 'GCP Agent Starter Pack CLI version: 0.41.3'; agent-starter-pack --help listed all 7 commands; agent-starter-pack list showed 8 built-in templates.
Model tokens used
177,110
Exact commit tested
659f04774245
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.

Checked 101 packages in 1ms
=== CLI version ===
GCP Agent Starter Pack CLI version: 0.41.3
=== Test suite ===
tests/unit/test_makefile_template.py::TestJavaMakefileGeneration::test_java_makefile_uses_maven PAS…
======================= 498 passed, 3 skipped in 16.04s ========================
=== Elapsed seconds ===
0
All verified. Here's the final report:
tokens used
177,110
All verified. 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

  • Reached a running state on a clean machine, with the session recorded.
  • Installed in 5 minutes, faster than the median of the 17 comparable projects Argusic has measured.
  • Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
  • Ran without a GPU, so it does not need one to start.
  • Licensed Apache-2.0, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

Of the 18 agents projects Argusic has installed and timed, agent-starter-pack was the 9th fastest to reach a running state, and 11 of 18 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 5 minutes after the clone.

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 Runner2/3Runs100.000.03
Argusic Runner1/3Unverified80.000.04

Topics (from GitHub)

agentsgcpgeminigenai-agentsgenerative-aillmopsmlopsobservability

Embed the badge

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

[![Tested by Argusic](https://argusic.com/badge/agent-starter-pack.svg)](https://argusic.com/subject/agent-starter-pack)

Questions

Does agent-starter-pack run?
Yes. agent-starter-pack runs. Argusic installed and launched it on a clean machine in 5 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test agent-starter-pack?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 659f04774245. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test agent-starter-pack?
The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does agent-starter-pack 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 agent-starter-pack need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing agent-starter-pack?
1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does agent-starter-pack compare with the alternatives?
Of the 18 agents projects Argusic has installed and timed, agent-starter-pack was the 9th fastest to reach a running state, and 11 of 18 reached one at all.
Where is the evidence for agent-starter-pack?
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