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(tools): Add AgentDispatcherToolset for runtime agents
- agents: block all stdlib modules in agent-config code-refs (denylist bypass via cProfile.run/timeit)
- fix: StreamingResponseAggregator drops/duplicates function calls in streaming mode
- feat: add OpenAI Realtime support to live runs
- chat wrapper (run_llm_agent_as_node) extracts task-delegation FCs from partial=True progressive-SSE chunks and breaks — the FC event is never persisted, orphaning the synthesized task FR and permanently poisoning the session
- RemoteA2aAgent ends the invocation silently when the A2A stream stops before a terminal task state
- RemoteA2aAgent: a terminal A2A task carrying tool activity fails is_final_response(), so the turn cannot be detected as finished (non-streaming peer)
- docs: drop tracking parameters from the OpenAI gateway tip
- "Failed to detach context" (Token created in a different Context) logged as ERROR when caller stops runner.run_async() early
- StreamingResponseAggregator causes infinite tool-call loop with transfer_to_agent + streaming
- Docs
- Python not yet supported