# 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.

## Install

Save as a script file and run:

## Quick Use

```bash
uv pip install crewai
crewai create crew my-research-team
cd my-research-team
crewai run
```

---

## Intro

CrewAI is a Python framework for orchestrating teams of autonomous AI agents. Define agent roles (researcher, analyst, writer), assign tasks, and let them collaborate — each agent brings specialized expertise to solve complex problems. Built from scratch without LangChain dependencies, optimized for speed. 47,000+ stars, 100,000+ certified developers.

**Works with**: GitHub Copilot
---

## Core Concepts

### Crews — Autonomous agent teams
Agents with defined roles collaborate naturally, delegating tasks and sharing context.

### Flows — Event-driven workflows
Fine-grained execution control with state management, conditional branching, and error handling.

## Quick Start

### 1. Define agents (agents.yaml)
```yaml
researcher:
  role: Senior Data Researcher
  goal: Uncover cutting-edge developments in {topic}
  backstory: >
    Seasoned researcher with a knack for uncovering the latest
    developments and presenting information clearly.

reporting_analyst:
  role: Reporting Analyst
  goal: Create detailed reports based on data analysis
  backstory: >
    Meticulous analyst known for turning complex data
    into clear, actionable reports.
```

### 2. Define tasks (tasks.yaml)
```yaml
research_task:
  description: Conduct thorough research about {topic}
  expected_output: 10 bullet points of relevant information
  agent: researcher

reporting_task:
  description: Expand research into a comprehensive report
  expected_output: Detailed markdown report with full sections
  agent: reporting_analyst
  output_file: report.md
```

### 3. Build the crew (crew.py)
```python
from crewai import Agent, Crew, Process, Task
from crewai.project import CrewBase, agent, crew, task
from crewai_tools import SerperDevTool

@CrewBase
class ResearchCrew():
    @agent
    def researcher(self) -> Agent:
        return Agent(config=self.agents_config['researcher'],
                     tools=[SerperDevTool()])

    @agent
    def reporting_analyst(self) -> Agent:
        return Agent(config=self.agents_config['reporting_analyst'])

    @task
    def research_task(self) -> Task:
        return Task(config=self.tasks_config['research_task'])

    @task
    def reporting_task(self) -> Task:
        return Task(config=self.tasks_config['reporting_task'],
                    output_file='report.md')

    @crew
    def crew(self) -> Crew:
        return Crew(agents=self.agents, tasks=self.tasks,
                    process=Process.sequential, verbose=True)
```

### 4. Run
```bash
crewai run
```

---



### FAQ

**Q: What is CrewAI?**
A: Build teams of autonomous AI agents that collaborate on complex tasks. Define roles, assign tasks, and let crews work together.

**Q: How do I install CrewAI?**
A: Check the Quick Use section above for step-by-step installation instructions. Most assets can be set up in under 2 minutes.

## Source & Thanks

> Created by [crewAIInc](https://github.com/crewAIInc). Licensed under MIT.
> [crewAI](https://github.com/crewAIInc/crewAI) — ⭐ 47,400+
> Docs: [docs.crewai.com](https://docs.crewai.com)

Thanks to the CrewAI team for building the leading multi-agent orchestration framework.

---
Source: https://tokrepo.com/en/workflows/129bde64-660b-48dc-a2e0-7eeaaedf48fe
Author: Script Depot