CrewAI at a glance

A Python framework for crews of role-playing agents that delegate tasks to each other, orchestrated by event-driven Flows. Flows add persistence and human feedback, and the CLI deploys straight to the managed CrewAI AMP service.

Best for: Role-based multi-agent setups with a short path to a managed deployment.

Key facts

Maintainer

CrewAI Inc.

Languages

Python

Licence

MIT

Latest version

1.15.23 · September 28, 2026

Repository

crewAIInc/crewAI · 59,255 stars

Hosted option

CrewAI AMP

Deploy from the CLI with crewai deploy create and crewai deploy push.

Quickstart

Install the package, set the credentials, then run the smallest agent from the official docs. Model IDs are the ones the docs use and may not be enabled on your account.

pip install crewai crewai-tools  (not copied verbatim; docs recommend CrewAI CLI per installation guide; SerperDevTool needs SERPER_API_KEY)

Needs Provider API key + SERPER_API_KEY

from crewai import Agent
from crewai_tools import SerperDevTool

# Create an agent
researcher = Agent(
    role="AI Technology Researcher",
    goal="Research the latest AI developments",
    tools=[SerperDevTool()],
    verbose=True
)

# Use kickoff() to interact directly with the agent
result = researcher.kickoff("What are the latest developments in language models?")

# Access the raw response
print(result.raw)

Quickstart source

Features

Recent changes

• The quickstart is now Flow-first, with JSONC agent and crew configs loaded by load_crew.
• Since v1.14.5, restore_from_state_id resumes or forks a Flow; inputs.id hydration is deprecated.

Alternatives in the same language