Crewai

If you're building systems where multiple AI agents need to work together, this gives Claude the patterns for CrewAI's role-based framework. It covers the full stack: defining agents with specific roles and backstories, breaking work into tasks with dependencies, and orchestrating them in sequential or hierarchical processes. The YAML config approach keeps things clean, and the hierarchical mode with a manager agent is solid for complex delegation. Planning mode generates execution plans upfront, which helps with consistency. Memory configuration lets agents maintain context across runs. Flows handle event-driven workflows with state management. It's verbose compared to just chaining LLM calls, but that structure pays off when you need actual collaboration between specialized agents.