adk-python
https://github.com/google/adk-python
Python
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
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 supported1 Subscribers
Add a CodeTriage badge to adk-python
Help out
- Issues
- Running eval through pytest is not saving evalset_result.json file
- Interrupt Handling
- Drop the `.env`, it's cleaner (ADK should pick up project and location from GCP metadata server)
- feat: Add progressive streaming for run_async via ProgressiveTool (partial progress + final result)
- feat: Allow for use of default anthropic client via `anthropic_llm`
- SQLite-based memory service implementation
- ADK MCP Toolset Session Management Issues
- RemoteA2aAgent must support Optional list of A2A Interceptors to support AuthN/AuthZ
- Include reasoning tokens and token streaming for anthropic LLMs
- Eval fails for non-English languages
- Docs
- Python not yet supported