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
- Are node-level callbacks / plugin hooks planned for graph Workflow?
- docs: VertexAiSessionService Session ID Constraints During Evaluation
- feat(integrations): Add OpenSandboxEnvironment for remote sandbox workspaces
- fix(evaluation): honor each metric's own eval_status in AgentEvaluator.evaluate()
- fix(cli): adk eval process exit code now reflects PASSED/FAILED
- feat(evaluation): add tool parameter matching
- feat(cli): expose session rewind on Agent Engine and api_server
- Follow-up to #4309: fix for failed A2A tasks needs both _handle_a2a_response/_v2, _compat.TS_FAILED, and error_code — still reproducible in 2.6.2
- fix(a2a): mark failed A2A tasks as error events
- fix(skills): validate skill_id path segments before GCS blob lookup
- Docs
- Python not yet supported