CrewAI
ActiveDescription
CrewAI is a multi-agent framework for orchestrating role-playing, autonomous AI agents that collaborate like a team to tackle complex tasks.
Key Features
- Role-playing agents — every agent has role, goal, backstory and a private toolset
- Task orchestration — express dependencies, parallelism and context handoff between tasks
- Autonomous collaboration loops — delegation, hierarchical and consensual processes built-in
- Tool ecosystem — 100+ pre-built tools plus LangChain, Composio and MCP server integrations
- Memory & knowledge — short-term, long-term, entity memory and knowledge base retrieval
- Training & evaluation — crewAI train command and evaluation harness for feedback-driven improvement
Use Cases
💡 Building market research, code review, content production multi-agent pipelines
💡 Decomposing complex business work into sub-tasks with auto-delegation and aggregation
💡 Standing up a research team with role division on top of an enterprise knowledge base
💡 Combining with LangChain / LlamaIndex for tool-using multi-agent workflows
💡 Continuously improving agent output quality via feedback-driven training
Categories
Quick Start
# Install the SDK
pip install crewai crewai-tools
# Define a researcher and a writer agent
from crewai import Agent, Task, Crew
researcher = Agent(role='Researcher', goal='Gather latest AI industry news',
backstory='Senior industry analyst', tools=[search_tool])
writer = Agent(role='Writer', goal='Turn research into a short article',
backstory='Tech columnist')
# Describe the tasks
research_task = Task(description='Survey 2026 Agent framework trends', agent=researcher)
write_task = Task(description='Write a 500-word article from the research', agent=writer)
# Kick off the crew
crew = Crew(agents=[researcher, writer], tasks=[research_task, write_task])
result = crew.kickoff()