crewai-multi-agent

Define Agent objects with role, goal, and backstory, create Task objects assigned to those agents, then combine them in a Crew with Process.sequential or Process.hierarchical. Call crew.kickoff with your inputs to execute the workflow.

CrewAI uses role-based agents with a lower learning curve and built-in memory, suited for multi-agent teams. LangGraph uses graph-based state machines, better for complex stateful workflows with cycles. CrewAI has no LangChain dependencies.

Set the context parameter on the downstream Task with a list of previous Task objects, for example context=[research_task]. The receiving agent then gets the earlier task output as input for its own execution.

Yes, CrewAI supports multiple providers through its LLM class, including Anthropic Claude, Azure OpenAI, and local models via Ollama such as ollama/llama3.1. Pass the configured LLM object to the agent's llm parameter.

Agents loop when tasks are ambiguous or iterations are unlimited. Set max_iter on the agent to cap reasoning iterations, add max_rpm for rate limiting, and write more specific task descriptions with explicit expected_output formats.

Use Flows when you need conditional branching, complex state management, or event-driven execution with routers and listeners. Crews are better for straightforward sequential or hierarchical multi-agent collaboration without custom control logic.