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: 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
- `RemoteA2aAgent(mode="task")`: delegation to a non-ADK A2A agent never closes when the task ends in `TASK_STATE_COMPLETED`; the coordinator never gets its turn back
- fix(cli): reject multi-line project/region before they reach the GKE manifest
- feat(eval): let AgentEvaluator evaluate an agent built at runtime
- fix: render Jinja2 instructions in an immutable sandbox
- fix(memory): isolate stored memories from caller mutations
- Docs
- Python not yet supported