Skip to content
The BCI Briefing

Machine learning · Decoding

pyRiemann

Machine learning on covariance matrices using Riemannian geometry.

  • Active
  • Mature
  • Specialized
github.com/pyRiemann/pyRiemann (opens in a new tab)Documentation (opens in a new tab)

What problem does it solve?

Covariance-based classifiers are robust and data-efficient for EEG; pyRiemann makes them scikit-learn compatible.

Who is it for?

BCI researchers needing strong baselines with little data

At a glance

Primary use
Machine learning
Licence
BSD-3-Clause · permissive
Language
Python
Current release
v0.12, published 1 Jul 2026
Development activity
Last commit 1 Oct 2026 · repository created 19 Apr 2015
Maintainers
pyRiemann developers
GitHub stars
778 as of 3 Oct 2026

Repository facts are a snapshot read from the GitHub API on 3 Oct 2026; they are reported as found, not scored.

Supported modalities and use

Modalities

Real-time capability

Designed for or usable in real-time loops

Common use cases

  • Motor-imagery classification
  • ERP detection
  • Transfer learning across sessions

How it fits into a BCI stack

  1. Hardware

    2 tools

  2. Acquisition

    3 tools

  3. Streaming

    3 tools

  4. Processing

    6 tools

  5. Decoding

    pyRiemann

  6. Applications

    2 tools

  7. Data & standards

    3 tools

Sources

  1. 01

    github.com/pyRiemann/pyRiemann (opens in a new tab)

    Open-source repositoryGitHubChecked against source 3 Oct 2026

    Repository metadata read from the GitHub API.