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(cli): handle agent engine deploy imports
- feat: Add LLM resource cleanup lifecycle with aclose() method
- feat(memory): add SQLite memory service
- after_agent_callback is not replacing the agent output but add the callback output to the original agent output
- feat(runner): add metadata parameter to Runner.run_async()
- Tool Call has been called multiple times by ADK
- feat: add a2a agent card generation with the CLI
- feat(mcp): Add session state-based JWT token propagation for MCP tools
- ADK import overhead (8-20s) causes slow cold starts
- Native Ollama LLM Integration + Example Project + Full Unit Tests
- Docs
- Python not yet supported