Google ADK Python 2.14 makes execution environments, A2A, and evaluation stable
Tagged Nov 7 (changelog dated Nov 4), Google's Agent Development Kit Python 2.14.0 graduates execution environments, A2A, evaluation, and core runtime modules from experimental, and adds adk generate_agent_card plus multi-run eval via adk eval --num_runs. It also adds a Microsoft Teams runner and an OpenAI Decisions classifier, and reports long multi-turn workflows running about 23% faster with 9% lower peak memory.