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 supported4 Subscribers
Add a CodeTriage badge to pydantic-ai
Help out
- Issues
- Render `RetryPromptPart` so the model can tell validation feedback from a user message
- Reduce overhead in Google streamed response handling
- Process `StopRun` outputs through the output pipeline
- Add `ToolOutput(buffered=True)` for incremental output tools
- Support `OnlineEvaluation` capability in `TemporalAgent` (durable execution)
- Optionally expose MCP resources to the model as tools on `MCPToolset`
- feat(instrumentation): classify tool-call argument validation failures on spans
- feat(profiles): `prompt_cache_retention` + `prompt_cache_outlook()` cold-window helper
- fix(cli): make command name consistent between entry point, `--help`, and docs
- Add `timestamp` to `ToolCallPart` or `FunctionToolCallEvent`
- Docs
- Python not yet supported