pydantic-ai
https://github.com/pydantic/pydantic-ai
Python
GenAI Agent Framework, the Pydantic way
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported6 Subscribers
Add a CodeTriage badge to pydantic-ai
Help out
- Issues
- Decision score validation rejects valid full-precision probabilities due to floating-point rounding
- Feature request: Evaluate native CIGE agentic test cases with Pydantic Evals
- API reference: overloaded signatures render back to back with no separator
- TrustedRouter provider (OpenAI-compatible)
- Document Smol Machines as a Pydantic AI workspace provider
- test: fixed some places where Is() was required (wip pull request for me to work on inline-snapshot)
- `cli_agent` keeps the `--model` from an earlier `cli()` call in `tests/test_cli.py`
- Restore `cli_agent.model` after each test in `tests/test_cli.py`
- docs: add LoopGrid third-party capability
- Default `run_id` swaps between concurrent branches on a Prefect flow retry
- Docs
- Python not yet supported