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
- feat(memory): SQL-backed DatabaseMemoryService with scratchpad for durable agent memory
- 关于多agent中，子agent参数planner=PlanReActPlanner()的问题
- OpenAPIToolset / GoogleAPIToolset not picking up Gemini Enterprise Authorization
- fix: ensure call_llm spans are always ended in multi-agent scenarios
- fix: handle read-only .git files in deploy cleanup on Windows
- LongRunningFunctionTool: no way to skip LLM summarization when client sends back function_response
- adk deploy app-engine with --validate-agent-import parameter fails because .env files are not included.
- fix: filter thought parts from A2A client user-facing response
- Images that are included into instructions via {artifact.<name>} syntax should allow a underlying LLM for image processing/interpeting.
- feat: Add --dev flag to adk run for watchdog-based hot-reloading
- Docs
- Python not yet supported