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
- fix(a2a): close task-mode delegation when a plain A2A peer completes without finish_task
- fix(a2a): send long-running calls once from the legacy executor
- fix(integrations): run BigQuery forecast/analyze_contribution/detect_anomalies off the event loop
- fix(a2a): aggregate streamed text into a final non-partial event in RemoteA2aAgent
- Cache-stable progressive disclosure of tools (deferred tools + per-turn selection hook)
- fix: nested parallel agents can't see output from earlier parallel stages (#3470)
- `AgentTool` returns `""` when the wrapped agent's final event has only function parts (task-mode `finish_task`, `skip_summarization` tool response)
- A2A (default executor, streaming): RemoteA2aAgent receives the final reply and the `adk_request_confirmation` pause twice
- RemoteA2aAgent emits only partial events on the streaming path, never a final aggregated non-partial event, so the specialist's answer is never persisted
- gen_ai.response.model is never set on LLM spans -- only gen_ai.request.model
- Docs
- Python not yet supported