Installation
Get started with CrewAI - Install, configure, and build your first AI crew
Python Version Requirements
CrewAI requires Python >=3.10 and <3.13
. Hereβs how to check your version:
If you need to update Python, visit python.org/downloads
Setting Up Your Environment
Before installing CrewAI, itβs recommended to set up a virtual environment. This helps isolate your project dependencies and avoid conflicts.
Create a Virtual Environment
Choose your preferred method to create a virtual environment:
Using venv (Pythonβs built-in tool):
Using conda:
Activate the Virtual Environment
Activate your virtual environment based on your platform:
On macOS/Linux (venv):
On Windows (venv):
Using conda (all platforms):
Installing CrewAI
Now letβs get you set up! π
Install CrewAI
Install CrewAI with all recommended tools using either method:
or
Both methods install the core package and additional tools needed for most use cases.
Upgrade CrewAI (Existing Installations Only)
If you have an older version of CrewAI installed, you can upgrade it:
If you see a Poetry-related warning, youβll need to migrate to our new dependency manager:
This will update your project to use UV, our new faster dependency manager.
Skip this step if youβre doing a fresh installation.
Verify Installation
Check your installed versions:
You should see something like:
Creating a New Project
We recommend using the YAML Template scaffolding for a structured approach to defining agents and tasks.
Generate Project Structure
Run the CrewAI CLI command:
This creates a new project with the following structure:
Install Additional Tools
You can install additional tools using UV:
UV is our preferred package manager as itβs significantly faster than pip and provides better dependency resolution.
Customize Your Project
Your project will contain these essential files:
File | Purpose |
---|---|
agents.yaml | Define your AI agents and their roles |
tasks.yaml | Set up agent tasks and workflows |
.env | Store API keys and environment variables |
main.py | Project entry point and execution flow |
crew.py | Crew orchestration and coordination |
tools/ | Directory for custom agent tools |
Start by editing agents.yaml
and tasks.yaml
to define your crewβs behavior.
Keep sensitive information like API keys in .env
.
Next Steps
Was this page helpful?