Environment:CrewAIInc CrewAI Python Runtime Environment

Knowledge Sources	CrewAI pyproject.toml
Domains	Infrastructure, AI_Agents
Last Updated	2026-02-11 17:00 GMT

Overview

Python 3.10-3.13 runtime environment with 23+ core dependencies for orchestrating autonomous AI agents using CrewAI.

Description

This environment defines the base Python runtime and core package dependencies required to run any CrewAI workflow. It is built on Python 3.10+ (up to 3.13) and includes Pydantic for data modeling, OpenAI SDK for default LLM communication, ChromaDB for vector storage, and OpenTelemetry for observability. The environment uses uv as its package manager and includes special PyTorch index configuration for Python 3.13 compatibility.

Usage

Use this environment for all CrewAI workflows. It is the mandatory base prerequisite for running any Agent, Task, Crew, Flow, or Knowledge operation. Every Implementation page in this wiki requires this environment.

System Requirements

Category	Requirement	Notes
OS	Linux, macOS, or Windows	Cross-platform Python support
Python	>=3.10, <3.14	Python 3.13 uses PyTorch nightly builds due to torch 2.5.0 incompatibility
Disk	2GB+	For core dependencies and ChromaDB vector storage
Network	Internet access	Required for LLM API calls and telemetry

Dependencies

System Packages

Python 3.10, 3.11, 3.12, or 3.13
`uv` package manager (bundled as dependency)

Core Python Packages

`pydantic` ~=2.11.9
`openai` >=1.83.0,<3
`instructor` >=1.3.3
`pdfplumber` ~=0.11.4
`regex` ~=2026.1.15
`opentelemetry-api` ~=1.34.0
`opentelemetry-sdk` ~=1.34.0
`opentelemetry-exporter-otlp-proto-http` ~=1.34.0
`chromadb` ~=1.1.0
`tokenizers` ~=0.20.3
`openpyxl` ~=3.1.5
`python-dotenv` ~=1.1.1
`pyjwt` >=2.9.0,<3
`click` ~=8.1.7
`appdirs` ~=1.4.4
`jsonref` ~=1.1.0
`json-repair` ~=0.25.2
`tomli-w` ~=1.1.0
`tomli` ~=2.0.2
`json5` ~=0.10.0
`portalocker` ~=2.7.0
`pydantic-settings` ~=2.10.1
`mcp` ~=1.26.0
`aiosqlite` ~=0.21.0

Credentials

The following environment variables may be set (at minimum one LLM provider key is required):

`OPENAI_API_KEY`: OpenAI API key (default LLM provider)
`CREWAI_DISABLE_TELEMETRY`: Set to `"true"` to disable anonymous telemetry
`CREWAI_DISABLE_TRACKING`: Alternative flag to disable telemetry
`CREWAI_STORAGE_DIR`: Override default storage directory (defaults to current working directory name)
`CREWAI_DISABLE_VERSION_CHECK`: Set to `"true"` to skip version check on startup
`TOKENIZERS_PARALLELISM`: Automatically set to `"false"` by CrewAI to suppress fastembed logging

Quick Install

# Install CrewAI with core dependencies
pip install crewai

# Or with uv (recommended)
uv add crewai

Code Evidence

Python version requirement from `lib/crewai/pyproject.toml:9`:

requires-python = ">=3.10, <3.14"

Python 3.11+ conditional import from `lib/crewai/src/crewai/cli/utils.py:20`:

if sys.version_info >= (3, 11):
    import tomllib  # Python 3.11+ standard library

PyTorch compatibility workaround from `lib/crewai/pyproject.toml:110-125`:

# PyTorch index configuration, since torch 2.5.0 is not compatible with python 3.13
[[tool.uv.index]]
name = "pytorch-nightly"
url = "https://download.pytorch.org/whl/nightly/cpu"
explicit = true

[tool.uv.sources]
torch = [
  { index = "pytorch-nightly", marker = "python_version >= '3.13'" },
  { index = "pytorch", marker = "python_version < '3.13'" },
]

Telemetry disabling from `lib/crewai/src/crewai/telemetry/telemetry.py:149-151`:

os.getenv("OTEL_SDK_DISABLED", "false").lower() == "true"
or os.getenv("CREWAI_DISABLE_TELEMETRY", "false").lower() == "true"
or os.getenv("CREWAI_DISABLE_TRACKING", "false").lower() == "true"

Common Errors

Error Message	Cause	Solution
`requires-python ">=3.10, <3.14"`	Python version out of range	Install Python 3.10, 3.11, 3.12, or 3.13
`ModuleNotFoundError: No module named 'tomllib'`	Python 3.10 missing tomllib	The framework auto-falls back to `tomli`; ensure `tomli` is installed
`torch 2.5.0 is not compatible with python 3.13`	PyTorch incompatibility	Use `uv` with configured PyTorch nightly index, or use Python 3.12

Compatibility Notes

Python 3.10: `tomllib` standard library module not available; uses `tomli` package as fallback
Python 3.13: PyTorch requires nightly builds via special `uv` index configuration
Windows: Supported but some CLI features may behave differently; uses `LOCALAPPDATA` for token storage
CI Environments: Auto-detected via `CI` environment variable; adjusts console formatting accordingly

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.

Principle

Implementation

Heuristic

Environment