Skip to main content

​
Watch: Building CrewAI Agents & Flows with Coding Agent Skills

Install our coding agent skills (Claude Code, Codex, …) to quickly get your coding agents up and running with CrewAI.

​
Video Tutorial

Watch this video tutorial for a step-by-step demonstration of the installation process:

​
Text Tutorial

Python Version RequirementsCrewAI requires Python >=3.10 and <3.14. Here’s how to check your version:
If you need to update Python, visit python.org/downloads
OpenAI SDK RequirementCrewAI 0.175.0 requires openai >= 1.13.3. If you manage dependencies yourself, ensure your environment satisfies this constraint to avoid import/runtime issues.
CrewAI uses the uv as its dependency management and package handling tool. It simplifies project setup and execution, offering a seamless experience. If you haven’t installed uv yet, follow step 1 to quickly get it set up on your system, else you can skip to step 2.
1

Install uv

  • On macOS/Linux: Use curl to download the script and execute it with sh:
    If your system doesn’t have curl, you can use wget:
  • On Windows: Use irm to download the script and iex to execute it:
    If you run into any issues, refer to UV’s installation guide for more information.
2

Install CrewAI 🚀

  • Run the following command to install crewai CLI:
    If you encounter a PATH warning, run this command to update your shell:
    If you encounter the chroma-hnswlib==0.7.6 build error (fatal error C1083: Cannot open include file: 'float.h') on Windows, install Visual Studio Build Tools with Desktop development with C++.
  • To verify that crewai is installed, run:
  • You should see something like:
  • If you need to update crewai, run:
This upgrades the global crewai CLI tool only. To upgrade the crewai version inside your project’s virtual environment, see Upgrading CrewAI in a project.
Installation successful! You’re ready to create your first crew! 🎉

​
Creating a CrewAI Project

crewai create crew now creates a JSON-first crew project. Agents live in agents/*.jsonc, tasks and crew-level settings live in crew.jsonc, and crewai run loads that JSON definition directly.
1

Generate Project Scaffolding

  • Run the crewai CLI command:
  • This creates a new project with the following structure:
  • If you need the older Python/YAML scaffold with crew.py, config/agents.yaml, and config/tasks.yaml, run:
2

Customize Your Project

  • Your project will contain these essential files:
  • Start by editing crew.jsonc and the files in agents/ to define your crew’s behavior.
  • Use {placeholder} values in agent and task text, then set defaults in crew.jsonc under inputs. When you run crewai run, the CLI prompts for any missing values.
  • Keep sensitive information like API keys in .env.
3

Run your Crew

  • Before you run your crew, make sure to run:
  • If you need to install additional packages, use:
    As a supply-chain security measure, CrewAI’s internal packages use exclude-newer = "3 days" in their pyproject.toml files. This means transitive dependencies pulled in by CrewAI won’t resolve packages released less than 3 days ago. Your own direct dependencies are not affected by this policy. If you notice a transitive dependency is behind, you can pin the version you want explicitly in your project’s dependencies.
  • To run your crew, execute the following command in the root of your project:

​
Enterprise Installation Options

For teams and organizations, CrewAI offers enterprise deployment options that eliminate setup complexity:

​
CrewAI AMP (SaaS)

  • Zero installation required - just sign up for free at app.crewai.com
  • Automatic updates and maintenance
  • Managed infrastructure and scaling
  • Build Crews with no Code

​
CrewAI Factory (Self-hosted)

  • Containerized deployment for your infrastructure
  • Supports any hyperscaler including on prem deployments
  • Integration with your existing security systems

Explore Enterprise Options

Learn about CrewAI’s enterprise offerings and schedule a demo

​
Next Steps

Quickstart: Flow + agent

Follow the quickstart to scaffold a Flow, run a one-agent crew, and produce a report.

Join the Community

Connect with other developers, get help, and share your CrewAI experiences.