crewAI

🤖 crewAI: Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Homepage | Documentation | Chat with Docs | Examples | Discord

Table of contents

• Why CrewAI?
• Getting Started
• Key Features
• CLI Commands
• Examples
• Connecting Your Crew to a Model
• How CrewAI Compares
• Contribution
• Telemetry
• License

Why CrewAI?

The power of AI collaboration has too much to offer. CrewAI is designed to enable AI agents to assume roles, share goals, and operate in a cohesive unit - much like a well-oiled crew. Whether you're building a smart assistant platform, an automated customer service ensemble, or a multi-agent research team, CrewAI provides the backbone for sophisticated multi-agent interactions.

Getting Started

To get started with CrewAI, follow these simple steps:

1. Installation

npm install crewai

2. Basic Usage

Here's a simple example of how to use CrewAI:

import { Crew, Agent, Task } from 'crewai';

// Create agents
const researcher = new Agent('Researcher', {...});
const writer = new Agent('Writer', {...});

// Create tasks
const researchTask = new Task('Research the topic', {...});
const writeTask = new Task('Write the article', {...});

// Create a crew
const crew = new Crew({
  agents: [researcher, writer],
  tasks: [researchTask, writeTask],
});

// Run the crew
const result = crew.run();
console.log(result);

CLI Commands

CrewAI comes with a set of CLI commands to help you manage your crew:

1. Create a new crew or pipeline:

   crewai create <type> <name> [--router]

2. Train the crew:

   crewai train [-n <iterations>] [-f <filename>]

3. Reset memories:

   crewai reset-memories [-l] [-s] [-e] [-k] [-a]

4. Run the crew:

   crewai run

5. Replay a task:

   crewai replay <task_id>

For more details on each command, use crewai <command> --help.