pydantic-ai

How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.

Runs with mockssource: GitHubPythonMITcommit 5badf40a3c51

Python, MIT licensed. The project labels itself: agent framework, genai, harness, harness engineering, llm, pydantic and python.

pydantic-ai runs, with stand-ins for the services it depends on. An Argusic agent installed it in 1 minute and hit 3 errors on a clean machine with no GPU, and the whole session was recorded.

Full install succeeds, agent runs end-to-end with the test model, CLI boots and displays help, and the vast majority of tests pass without any API keys.

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

At a glance

verdict
Runs with mocks
Argusic Score
72 / 100
cost of the verifying run
$0.16 (measured)
recorded runs
1
last tested
stars
20,182
forks
0
open issues
0
watchers
0
created
-
last push
-

Subject data from GitHub, linked at the top of this page. 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_docs_examples fails with blockbuster BlockingError on os.path.samestat
  • test_cli banner width assertion fails when version string is long
  • 2 realtime test_supports tests fail with blockbuster BlockingError
Install time
1 minutes
Cold machine to finish
51 minutes
Errors hit and fixed
3 hit, 0 fixed with no human help
How the result was proved
uv run python -c "from pydantic_ai import Agent; print(Agent('test').run_sync('Hello').output)" returned 'success (no tool calls)'; uv run python -m pytest on 7k+ tests returned ~7121 passed
Model tokens used
616,163
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
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.

- CLI: `python -m clai --help` displayed the help text with all subcommands
**Test results (batched, no API keys needed — all VCR cassettes used):**
- Batch 1 (core): 4454 passed, 5 skipped, 3 xfailed
- Batch 2 (graph, UI, more): 643 passed, 2 skipped
- Batch 3 (capabilities, MCP, examples minus docs): 1483 passed, 2 skipped
- Batch 4 (realtime): 541 passed, 2 pre-existing failures (blockbuster `BlockingError` on `test_sup…
- Total: **~7121 passed, 9 skipped, 3 xfailed, 2 pre-existing failures**
**Pre-existing test failures (not caused by our setup):**
1. `test_docs_examples` in `test_examples.py` — `BlockingError` from `os.path.samestat` (blockbuste…
2. `test_run_chat_lays_the_banner_out_for_the_terminal_it_has` in `test_cli.py` — banner line lengt…
3. 2 realtime `test_supports_*` tests — `BlockingError` from blockbuster
No errors were introduced or fixed — everything worked out of the box.

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 1 minute, faster than the median of the 6 comparable projects Argusic has measured.
  • 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.
  • Hit 3 errors during setup, 3 of which were not solved.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 7 agent-framework projects Argusic has installed and timed, pydantic-ai was the 3rd fastest to reach a running state, and 4 of 7 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 mocks72.000.16

Topics (from GitHub)

agent-frameworkgenaiharnessharness-engineeringllmpydanticpython

Embed the badge

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

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

Questions

Does pydantic-ai run?
pydantic-ai runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 1 minutes, hitting 3 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. One attempt is 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 $0.16: 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?
1 minute 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?
3 things broke in the recorded run. Each one, and the time it cost, is listed on this page.
How does pydantic-ai compare with the alternatives?
Of the 7 agent-framework projects Argusic has installed and timed, pydantic-ai was the 3rd fastest to reach a running state, and 4 of 7 reached one at all.
Where is the evidence for pydantic-ai?
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