Skip to content
The BCI Briefing

Neural decoding · Decoding

Braindecode

Deep-learning models and training utilities for EEG, ECoG and MEG decoding in PyTorch.

  • Active
  • Widely used
  • Research-focused

What problem does it solve?

Provides tested reference architectures and data loaders so that deep models for neural signals are comparable across studies.

Who is it for?

Machine-learning practitioners working on neural time series

At a glance

Primary use
Neural decoding
Licence
BSD-3-Clause · permissive
Language
Python
Current release
v1.8.1, published 31 Aug 2026
Development activity
Last commit 3 Oct 2026 · repository created 7 Jan 2020
Maintainers
Braindecode developers
GitHub stars
1,319 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

Primarily for offline analysis

Common use cases

  • Convolutional and transformer decoders
  • Self-supervised pretraining
  • Benchmarking with MOABB

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

    Braindecode

  6. Applications

    2 tools

  7. Data & standards

    3 tools

Sources

  1. 01

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

    Open-source repositoryGitHubChecked against source 3 Oct 2026

    Repository metadata read from the GitHub API.