Installation and setup

CrewAI installs with pip as one package. A hosted model needs a key, and some providers need one more package; the model you write needs neither.

crewai 1.15.22

The crewai package brings the agent, task, crew and flow classes, and OpenAI's SDK, which CrewAI also uses to reach OpenRouter. Other providers, such as Anthropic and Gemini, need one more package.

pip install "crewai==1.15.22"

Check which version Python finds:

from importlib.metadata import version

print(version("crewai"))

CrewAI also ships a crewai command that generates a project folder of YAML files and classes. Plain Python files are used below, so every lesson is one script you can run; the generated layout is the same pieces in a different shape.

What CrewAI sends by default

CrewAI collects anonymous usage data, such as agent roles and tool names, and sends it to its own servers. Setting CREWAI_DISABLE_TELEMETRY to true turns that off. Two more variables keep a run offline: CREWAI_TRACING_ENABLED=false declines the trace upload a first run offers, and CREWAI_DISABLE_VERSION_CHECK=true stops the check against PyPI that a verbose run makes. The model you write in lesson 3 sets all three.

A hosted model from a free providerOptional

Every lesson runs on the stand-in model from lesson 3. To use a hosted model instead, set its key as an environment variable and, for some providers, install one more package. Lesson 27 makes the switch with LLM.

export OPENROUTER_API_KEY=sk-or-...