ModuleNotFoundError: No Module Named ‘crewai’ (2026)

CrewAI is a Python framework for orchestrating role-based AI agents that collaborate on tasks. It is one of the hottest multi-agent frameworks in 2026 alongside LangGraph. If you see ModuleNotFoundError: No module named ‘crewai’, install with one pip command.

Step 1: Install crewai

# Base install:
pip install crewai

# With tool integrations (RAG, file I/O, web search):
pip install 'crewai[tools]'

# Specific Python version (CrewAI needs 3.10+, 3.13 not yet stable):
python3.11 -m pip install crewai

Step 2: Minimal crew example

from crewai import Agent, Task, Crew, Process

researcher = Agent(
    role='Research Analyst',
    goal='Find recent AI breakthroughs',
    backstory='Expert at scanning technical papers and summarizing key findings.',
    verbose=True
)

writer = Agent(
    role='Tech Writer',
    goal='Turn research into clear blog posts',
    backstory='Award-winning explainer of complex tech.',
    verbose=True
)

research_task = Task(
    description='Find 3 recent advances in multimodal LLMs',
    agent=researcher,
    expected_output='3 bullet points with sources'
)

write_task = Task(
    description='Write a 500-word blog from the research',
    agent=writer,
    expected_output='Final blog post in markdown'
)

crew = Crew(
    agents=[researcher, writer],
    tasks=[research_task, write_task],
    process=Process.sequential,
    verbose=True
)

result = crew.kickoff()
print(result)

Step 3: Use a local Ollama model (no API cost)

from crewai import Agent, LLM

local_llm = LLM(
    model="ollama/llama3.1",
    base_url="http://localhost:11434"
)

agent = Agent(role='Analyst', goal='...', backstory='...', llm=local_llm)

Why this error happens

Debugging checklist for MNFE: crewai

• Confirm which Python is running: which python and python --version.
• CrewAI requires Python 3.10+. Older versions cannot install it.
• Confirm pip install worked: python -m pip show crewai.
• If Jupyter, install into the running kernel: %pip install crewai. Restart kernel after.

Correct install for common setups

# Standard venv
python -m pip install crewai

# With tools included
python -m pip install "crewai[tools]"

# uv (fastest 2026 workflow)
uv add crewai
uv add "crewai[tools]"

# Poetry
poetry add crewai

# Jupyter notebook (auto-picks correct kernel)
%pip install crewai

Verify install + smoke test

import crewai
print(crewai.__version__)

from crewai import Agent, Task, Crew
agent = Agent(role="Researcher", goal="Find facts", backstory="Analyst")
print(agent.role)

Real-world example: minimal CrewAI agent

from crewai import Agent, Task, Crew

researcher = Agent(
    role="Researcher",
    goal="Find current AI trends in 2026",
    backstory="AI industry analyst",
)

writer = Agent(
    role="Writer",
    goal="Summarize findings in 3 bullet points",
    backstory="Technical content editor",
)

research = Task(
    description="Research AI agent frameworks",
    expected_output="Comparison of top 3 frameworks",
    agent=researcher,
)

write = Task(
    description="Write 3-bullet summary",
    expected_output="3 bullet points",
    agent=writer,
    context=[research],
)

crew = Crew(agents=[researcher, writer], tasks=[research, write])
result = crew.kickoff()
print(result)

CrewAI vs LangChain agents: when to pick which

Both frameworks build agents. Different strengths:

• CrewAI: role-play framework. Best when your agents are distinct personas (Researcher + Writer + Editor) working sequentially or in parallel. Simpler mental model.
• LangGraph: state-machine framework. Best when your workflow has branches, loops, or human-in-the-loop steps. More powerful but steeper learning curve.
• Anthropic Claude Agent SDK: lowest-level. Best when you want fine control over tool calling, permissions, and streaming.

Common install issues on M1 Mac and Windows

• M1 Mac: some CrewAI tool dependencies need Rosetta. Use arch -x86_64 pip install crewai if you hit compilation errors.
• Windows: Long path names sometimes break pip install. Enable long paths in Registry or use uv add crewai which handles this automatically.
• Corporate proxy: set HTTPS_PROXY environment variable before running pip install.

Quick reference summary

ModuleNotFoundError: crewai almost always means the package installed into a different Python than the one running your script. The single most reliable fix is uv add crewai plus uv run python your_script.py. This forces both sides to use the same interpreter.

CrewAI in production

CrewAI works well for prototyping but needs guardrails in production. Set a max iteration cap on your Crew to prevent runaway loops. Add token-usage callbacks so you can bill correctly. Use LangSmith or Braintrust to trace agent decisions when things go wrong. For long-running crews, checkpoint state to Postgres so a crash does not lose hours of work.

Choosing between crewai[tools] and crewai plain

The base crewai package gives you agents, tasks, and crews. The crewai[tools] extras add file readers, web scrapers, code interpreters, and other pre-built tools. Install the base for maximum lightness, add extras when you know which tools you need. Never install extras you do not use because each one pulls in more dependencies and increases the surface for version conflicts.

Diagnostic checklist for “No module named ‘crewai'”

• Verify pip install target. Run pip show crewai — if not installed, run pip install crewai.
• Check the active Python interpreter. which python (mac/Linux) or where python (Windows). Both pip and python must point to the same environment.
• Check virtual environment activation. If you use venv/conda, activate before installing: source .venv/bin/activate.
• Rule out uppercase/lowercase. Python imports are case-sensitive: import PyPDF2 not import pypdf2.
• Rule out the pip-vs-package-name mismatch. Some packages install under a different name than you import (e.g. pip install beautifulsoup4 → import bs4).

Modern install for LLM frameworks

# 2026 recommended workflow — uv is fastest
pip install uv
uv pip install crewai

# Or classic pip
pip install crewai

# With extras for LLM providers
pip install "crewai[openai,anthropic]"

Common “No module named ‘crewai'” causes

• Version pinning conflict. LLM libraries update fast — pip install --upgrade crewai if you saw the module before.
• Multiple Python versions. LLM tutorials often use Python 3.11 or 3.12. Verify python --version matches.
• Notebook kernel. Jupyter picks a different kernel than pip installs to. Use %pip install crewai inside the notebook.
• WSL / Docker paths. Install in the same environment as your Python — not on the host if you run Python inside WSL.

Working code example

# Verify install
import crewai
print(crewai.__version__)

# Basic usage skeleton
# (adapt to your specific crewai version)

Best practices

• Use a virtual environment for every LLM project. Dependencies overlap and pin conflicts are common.
• Pin your versions in requirements.txt or pyproject.toml. LLM libraries move fast.
• Consider uv or Poetry. Modern package managers handle dep resolution far better than pip alone.

Adrian Mercurio

Full-Stack Developer at PIES IT Solution

Specializes in building complete capstone projects with full documentation. Strong background in PHP/MySQL development and database design. Has personally built and tested over 30 capstone-ready projects with ER diagrams, DFDs, and chapter-by-chapter thesis documentation.

Expertise: PHP · Laravel · Database Design · Capstone Projects · C# · C · C++ · Python · AI Projects
 · View all posts by Adrian Mercurio →