adk-python
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Runssource: GitHubhomepagePythonApache-2.0commit 9625b06c9a1b
Python, Apache-2.0 licensed. The project labels itself: agent, agentic, agentic ai, agents, agents sdk, ai, ai agents and aiagentframework.
adk-python runs. An Argusic agent installed it in 0.5 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
uv virtual environment installed with all extras, google-adk 2.9.2 builds and imports, full unit test suite passes at 16167/16167 (0 failures, 83 skipped, 26 expected failures, 2 unexpected passes), CLICK-based CLI entry point is functional.
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 60 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.
- test_entry_point_loads_only_allowlisted_packages failed: sitecustomize (system apport hook) loaded at interpreter startup not in allowlist2 minutes
- Install time
- under a minute
- Cold machine to finish
- 14 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- python -m pytest tests/unittests -n auto exited 0, 16167 passed, 83 skipped, 26 xfailed, 2 xpassed in 263s
- Model tokens used
- 142,119
- Exact commit tested
- 9625b06c9a1b
- 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.
= 16167 passed, 83 skipped, 26 xfailed, 2 xpassed, 2179 warnings in 263.04s (0:04:23) = All 16,167 tests passed. Let me compile the final result. Here's the summary of what was done: - **Install**: `uv venv` + `uv sync --all-extras` — resolved 402 packages, installed 347 in ~30s. P… - **Error found & fixed**: `test_entry_point_loads_only_allowlisted_packages` failed because the sy… - **Full test suite**: `python -m pytest tests/unittests -n auto` — **16167 passed, 83 skipped, 26 … exec /bin/sh -lc 'export PATH="$HOME/.local/bin:$PATH" && cd /work/repo && . .venv/bin/activate && pytho… succeeded in 0ms: 2.9.2 tokens used 142,119
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 0.5 minutes, faster than the median of the 37 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 38 agent projects Argusic has installed and timed, adk-python was the 3rd fastest to reach a running state, and 29 of 38 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 0.5 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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs | 100.00 | 0.05 | |
| Argusic Runner | 1/3 | Did not run | 20.00 | 0.26 |
Topics (from GitHub)
agentagenticagentic-aiagentsagents-sdkaiai-agentsaiagentframeworkgenaigenai-chatbotllmllmsmulti-agentmulti-agent-systemsmulti-agentsmulti-agents-collaboration
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/adk-python)Questions
- Does adk-python run?
- Yes. adk-python runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test adk-python?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 9625b06c9a1b. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test adk-python?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does adk-python take to install?
- 0.5 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 adk-python need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing adk-python?
- 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 adk-python compare with the alternatives?
- Of the 38 agent projects Argusic has installed and timed, adk-python was the 3rd fastest to reach a running state, and 29 of 38 reached one at all.
- Where is the evidence for adk-python?
- 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.