NeuroTechX/moabb

Health v2 · maintenance only

Adoption not part of the score

1048 stars · 261 forks observed · 2026-09-01

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

MOABB (Mother of All BCI Benchmarks) is a Python library for reproducible benchmarking of machine-learning algorithms on EEG-based brain-computer interface tasks. It provides unified access to 160 open EEG datasets (3500+ subjects), standardized paradigms (motor imagery, P300, SSVEP, c-VEP), and evaluation schemes built on MNE-Python and scikit-learn.

Use cases

• benchmark my EEG decoding pipeline across multiple public datasets
• download and load BCI EEG datasets in a unified format
• run cross-session or cross-subject evaluation for motor imagery classification
• compare P300 or SSVEP classification algorithms fairly
• reproduce published BCI benchmark results
• add a custom EEG dataset in BIDS format for benchmarking
• visualize and statistically analyze BCI classification results

When to choose

• you need reproducible, standardized comparisons of BCI/EEG decoding algorithms
• you want unified access to many open EEG datasets without writing per-dataset loaders
• you work with scikit-learn or MNE-Python pipelines and want fair evaluation schemes
• you are doing open-science BCI research and need citable benchmark results

When to avoid

• you need real-time BCI signal acquisition or online closed-loop operation
• you work with non-EEG modalities like fMRI or MEG exclusively
• you want a GUI-based EEG analysis tool rather than a Python library
• you need clinical-grade or regulatory-compliant EEG processing

Facets

library · maturity active

machine-learning benchmarking data-science data-visualization machine-learning data-science healthcare python cross-platform eeg brain-computer-interface bci neuroscience benchmark motor-imagery p300 ssvep mne-python open-science signal-processing research

Member repositories

For agents

markdown · JSON · MCP: product_card(name="NeuroTechX/moabb")