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
- AgentTool runs the wrapped agent without the parent App's events_compaction_config, so agent-as-tool history grows unbounded
- fix(a2a): serialize event actions in JSON mode for A2A metadata
- fix(plugins): return None, not the input, when a built-in plugin leaves a value unchanged
- Add a focused installed-reader report publication sample
- A task-mode root agent loses its task input once it asks the user a question
- A2aAgentExecutor sends the raw exception text to the A2A caller when the run fails
- Allow LLM-as-judge evaluation metrics to use configured LiteLLM proxy credentials
- Feature request: Semaprax policy-plugin example for before_tool_callback
- rubric_based_final_response_quality_v1 errors when the agent replies from a before_agent_callback
- fix: evaluate callback responses without captured agent details
- Docs
- Python not yet supported