ScriptsMar 29, 2026·1 min read

CrewAI — Multi-Agent AI Framework

Build teams of AI agents that collaborate to solve complex tasks. Define roles, goals, and tools for each agent, then let them work together autonomously.

TO
TokRepo精选 · Community
Quick Use

Use it first, then decide how deep to go

This block should tell both the user and the agent what to copy, install, and apply first.

pip install crewai crewai-tools

Intro

CrewAI lets you create teams of specialized AI agents that collaborate like a real team. Each agent has a role, goal, and set of tools. They delegate tasks, share results, and work together to accomplish complex objectives.

Best for: Research pipelines, content creation, code review, data analysis, automated workflows Works with: OpenAI, Anthropic, Google, Ollama, local models


How It Works

from crewai import Agent, Task, Crew

researcher = Agent(
    role="Senior Researcher",
    goal="Find the latest AI trends",
    tools=[search_tool, web_scraper],
)

writer = Agent(
    role="Content Writer",
    goal="Write engaging articles based on research",
)

research_task = Task(description="Research AI trends for 2025", agent=researcher)
write_task = Task(description="Write a blog post from the research", agent=writer)

crew = Crew(agents=[researcher, writer], tasks=[research_task, write_task])
result = crew.kickoff()

Key Features

  • Role-based agents with distinct personalities and tools
  • Sequential & parallel task execution
  • Human-in-the-loop for critical decisions
  • Memory for cross-task context retention
  • 30+ built-in tools (search, scrape, file I/O, etc.)

🙏

Source & Thanks

Created by CrewAI. Licensed under MIT. crewAIInc/crewAI — 25K+ GitHub stars

Related Assets