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
- ApplicationIntegrationToolset silently builds no tools when a Connectors schema operation fails, and waits forever on one that never finishes
- fix: scope tool confirmation replay claims by session
- feat: gate human-in-the-loop tool confirmation on the caller principal
- RemoteA2aAgent enforces HTTPS for agent cards, blocking plaintext A2A inside a service mesh (mTLS)
- feat(skills): let SkillToolset pin registry skills to appear in the catalog
- A before_agent_callback which changes the state results in an empty Event being returned
- adk web GET/DELETE test endpoints skip the create_test path sanitiser
- [legacy path] Nested pydantic model tool parameter fails under VERTEX_AI when the function also has a fallback-parsed parameter — only with JSON_SCHEMA_FOR_FUNC_DECL disabled
- A custom BaseLlm has no documented mapping from LlmRequest.config to a Vertex request body, and getting it wrong drops your tools with no error
- to_openeval()/from_openeval(): interop between EvalSet and the EvalPort portable format
- Docs
- Python not yet supported