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(evaluation): NOT_EVALUATED metric no longer masked by a passing one
- fix(eval): generate Agent Engine-compliant eval session IDs
- fix(a2a): send append=True for the final chunk of a streamed artifact
- fix(skills): validate skill_id path segments before GCS blob lookup
- Context Compaction breaks Session with Workflow + DatabaseSessionService When Compaction is not on Last Agent
- ApiServer.get_fast_api_app() registers unbounded in-memory span exporters (memory leak on long-lived servers)
- fix(runners): skip duplicate user event append on invocation retry
- A2A message:stream against a deployed Agent Engine (reasoningEngines) target truncates after TASK_STATE_WORKING, or fails with 'append=True for nonexistent artifact_id'
- Evals fail with VertexAiSessionService because generated session IDs violate Agent Engine constraints
- fix(litellm): avoid duplicate streamed tool-call content
- Docs
- Python not yet supported