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 supported2 Subscribers
Add a CodeTriage badge to adk-python
Help out
- Issues
- Chat Agent inside Workflow loses conversation history across turns
- SequentialAgent deprecated but replacement (Workflow) cannot fill its role as sub_agent
- Ability to add prompt chips to custom adk agents will be very useful
- fix: use working-directory to resolve adk_pr_triaging_agent module path
- refactor: centralise JSON parsing via json_utils.safe_json_loads
- Make _live_api_client a public, documented override point (like api_client)
- Feature request: Auto-mount referenced artifacts into AgentEngineCodeExecutor / BuiltInCodeExecutor sandboxes (parity with OpenAI code_interpreter.file_ids)
- fix: retry when model returns empty response after tool execution
- fix(a2a): Promote RemoteA2aAgent response to workflow node output
- Follow-up: allow safe data:image/* schemes via url_filter in SVG sanitizer
- Docs
- Python not yet supported