mne

What it is and what it does

MNE-Python is a mature, open-source toolkit for working with human brain recordings. It handles data from multiple modalities—MEG, EEG, sEEG, ECoG, fNIRS—and provides a complete pipeline from raw data import and preprocessing to visualization and statistical analysis. The package bundles modules for source localization, spectral and time-frequency decomposition, functional connectivity, and machine learning on neural data.

The package is built on standard scientific Python dependencies including numpy, scipy, and matplotlib, and includes convenience functions for common neuroimaging workflows. It is widely used in neuroscience research and clinical settings. Installation is straightforward via pip, and the codebase is actively maintained with comprehensive documentation and a user forum for support.

Use it for:

• Load and preprocess raw MEG or EEG recordings, apply filters, and detect artifacts before analysis.
• Estimate the location of neural sources in the brain from surface recordings using inverse methods.
• Compute spectrograms, power spectral density, or cross-frequency coupling in neurophysiological data.
• Analyze functional connectivity between brain regions using correlation or coherence measures.
• Prepare neural data for machine learning pipelines for classification or regression on brain signals.
• Visualize brain activity on cortical surfaces or as time-series plots for exploratory analysis.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

MNE-Python provides tools for exploring, visualizing, and analyzing human neurophysiological data including MEG, EEG, sEEG, and ECoG recordings, with modules for preprocessing, source estimation, time-frequency analysis, connectivity, and machine learning.

Yes. MNE-Python is a well-established, actively maintained toolkit with no known vulnerabilities, permissive BSD-3-Clause licensing, and low install friction. It is the standard choice for neurophysiological data analysis in Python. Install it if you work with MEG, EEG, or related brain recordings.

Install

mne on PyPI

pip install mne

uv add mne

poetry add mne

Installing mne

Before you install

Low friction installation via pip with a stable, actively maintained codebase. Last release 116 days ago with active repository (3482 stars, last commit 2026-08-12). Requires Python ≥3.10 and nine well-established scientific dependencies.

License in practice

BSD-3-Clause permissive license allows use in commercial and private projects with minimal restrictions, requiring only preservation of copyright and license notices.

Quickstart

pip install mne

import mne
raw = mne.io.read_raw_fif('sample_data.fif')
raw.plot()

Requires Python ≥3.10. Typical use requires neurophysiological data files (MEG, EEG, etc.) in supported formats.

Verify before relying

• Whether optional dependencies for advanced visualization or specific file formats are available and their install friction.
• Performance characteristics for large datasets or real-time processing scenarios.
• Specific machine learning capabilities and their scope relative to dedicated ML libraries.

Package facts

Evidence: mne-1.12.1-py3-none-any.whl

Keywords: ECoG, EEG, MEG, brain, fNIRS, neuroimaging, neuroscience

Tags

More Software Development packages