CrewAI — framework multi-Agent basé sur les rôles (guide 2026)

Quick Start — 3-Agent Research Crew

Les trois Agents s’exécutent séquentiellement — la sortie du chercheur alimente le rédacteur, qui alimente l’éditeur. Passez à process=Process.hierarchical pour ajouter un agent manager qui décide dynamiquement de l’attribution des tâches. allow_delegation=True permet à un Agent de déléguer des sous-tâches à un autre membre de l’équipe.

# pip install crewai crewai-tools
import os
from crewai import Agent, Task, Crew, Process
from crewai_tools import SerperDevTool

os.environ["OPENAI_API_KEY"] = "sk-..."
os.environ["SERPER_API_KEY"] = "..."

search = SerperDevTool()

researcher = Agent(
    role="Senior research analyst",
    goal="Find authoritative facts on a given topic",
    backstory="A 10-year industry analyst with an allergy to unsourced claims.",
    tools=[search],
    allow_delegation=False,
    verbose=True,
)
writer = Agent(
    role="Technical writer",
    goal="Turn research notes into a crisp 300-word brief",
    backstory="Writes for developers who hate fluff.",
    allow_delegation=False,
)
editor = Agent(
    role="Editor",
    goal="Enforce brevity and factual accuracy",
    backstory="Former tech-book editor. Cuts 30% of every draft.",
    allow_delegation=True,
)

research_task = Task(description="Research the state of multi-agent frameworks in 2026.",
                    agent=researcher, expected_output="A bullet list with citations.")
draft_task    = Task(description="Draft a 300-word brief from the research.",
                    agent=writer, expected_output="A short brief.")
edit_task     = Task(description="Edit and finalize the brief.",
                    agent=editor, expected_output="The final 300-word brief.")

crew = Crew(
    agents=[researcher, writer, editor],
    tasks=[research_task, draft_task, edit_task],
    process=Process.sequential,
    verbose=True,
)
print(crew.kickoff())

Fonctionnalités clés

Comparaison

Cas d'usage

Tarification et licence

Assets associés sur TokRepo

CrewAI Flows — Event-Driven Multi-Agent Orchestration

CrewAI Flows is the event-driven orchestration layer on top of Crews. Decorators @start, @listen, @router build a typed state machine for multi-agent.

CrewAI — Multi-Agent Orchestration in Python

Python framework for orchestrating role-playing AI agents that collaborate on complex tasks. Define agents with roles, goals, and tools, then let them work together autonomously. 25,000+ stars.

CrewAI — Multi-Agent Orchestration Framework

Build teams of autonomous AI agents that collaborate on complex tasks. Define roles, assign tasks, and let crews work together.

Phoenix Tracing Quickstart — OpenInference Tracer Setup

Phoenix instruments OpenAI, Anthropic, LangChain, LlamaIndex, CrewAI via OpenInference. Local UI or Arize cloud. No per-call code changes.

Questions fréquentes