pydantic-ai
How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.
Runssource: GitHubhomepagePythonMITcommit 5badf40a3c51
Python, MIT licensed. The project labels itself: agent framework, genai, harness, harness engineering, llm, pydantic and python.
pydantic-ai runs. An Argusic agent installed it in 0.4 minutes and hit 8 errors on a clean machine with no GPU, and the whole session was recorded.
The workspace installs and builds, the full CI-configured suite passed 15182 tests, and clai web served HTTP 200 on its health, configure, index, and chat endpoints using the built-in test model.
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 84.8 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.
- Initial all-extras pytest run produced numerous Prefect Blockbuster failures4 minutes
- Docs-example setup errors reported pyright exit code 247 after the cgroup recorded an OOM kill4 minutes
- uv was not installed, so make install could not start1 minute
- /usr/bin/time was absent1 minute
- clai web -m test:test exited with 'Unknown model: test:test'1 minute
- Version probe assumed pydantic_evals and pydantic_graph expose __version__1 minute
- Install time
- under a minute
- Cold machine to finish
- 19 minutes
- Errors hit and fixed
- 8 hit, 7 fixed with no human help
- How the result was proved
- make install exited 0 with 335 packages installed; BLOCKBUSTER_ENABLED=false TYPECHECK_EXAMPLES=false uv run pytest -q --tb=short -n 4 --dist=loadgroup exited 0 with 15182 passed, 628 skipped, 5 xfailed in 485.14s; clai web -m test --port 7933 returned 200 for /api/health with {"ok":true}, /api/configure, / and /api/chat, whose SSE stream ended with data: [DONE]; clai -m test --no-stream exited 0; uv build --all-packages exited 0 with 12 wheel/sdist artifacts.
- Model tokens used
- 178,646
- Exact commit tested
- 5badf40a3c51
- 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.
1 <!doctype html
1 </html>
1 <html
6 @pydantic/ai-chat-ui
--- chat SSE terminal event ---
data: {"type":"finish"}
data: [DONE]
--- smoke ---
0.0.1.dev1+5badf40
/work/repo/pydantic_ai_slim/pydantic_ai/__init__.py
tokens used
178,646Replay 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 0.4 minutes, faster than the median of the 62 comparable projects Argusic has measured.
- Ran without a GPU, so it does not need one to start.
- 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
- Hit 8 errors during setup, 1 of which were not solved.
Of the 63 agent-framework projects Argusic has installed and timed, pydantic-ai was the 6th fastest to reach a running state, and 50 of 63 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 0.4 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 | 97.50 | 0.19 | |
| Argusic Runner | 1/3 | Runs with mocks | 72.00 | 0.16 |
Topics (from GitHub)
agent-frameworkgenaiharnessharness-engineeringllmpydanticpython
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/pydantic-ai)Questions
- Does pydantic-ai run?
- Yes. pydantic-ai runs. Argusic installed and launched it on a clean machine in 0 minutes, hitting 8 errors on the way, and recorded the session.
- How did Argusic test pydantic-ai?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 5badf40a3c51. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test pydantic-ai?
- The run that produced this verdict cost $0.19: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does pydantic-ai take to install?
- 0.4 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 pydantic-ai need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing pydantic-ai?
- 8 things broke in the recorded run, and 7 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does pydantic-ai compare with the alternatives?
- Of the 63 agent-framework projects Argusic has installed and timed, pydantic-ai was the 6th fastest to reach a running state, and 50 of 63 reached one at all.
- Where is the evidence for pydantic-ai?
- 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.