mne-rt 1.2.0

MNE-RT — Real-time M/EEG Signal Processing
From amplifier to 3-D brain display in a single, researcher-friendly API

MNE-RT is an open-source Python library for real-time M/EEG signal processing, built on MNE-Python and MNE-LSL. It covers the full closed-loop pipeline — from amplifier to 3-D brain display — in a single API designed for neurofeedback, BCI, and clinical or basic-science monitoring.

Ecosystem

Several MNE-affiliated packages address real-time M/EEG at different levels of abstraction. Here is how they relate:

mne-realtime was the original real-time extension for MNE-Python. It offered TCP/IP client classes for a handful of acquisition systems (FieldTrip buffer, RtClient, StimServer) and a basic RtEpochs object for online epoching and classification. The package is no longer maintained and should not be used for new projects.

mne-lsl is an actively maintained, low-to-mid-level streaming library. It provides modern Python bindings for the Lab Streaming Layer (LSL) C++ library (replacement for the older pylsl) — together with high-level objects: StreamInlet and StreamOutlet for reading and writing LSL streams, StreamPlayer for replaying recorded files without hardware, StreamRecorder for saving streams to disk, and EpochStream for real-time epoching with online filtering. MNE-RT uses MNE-LSL as its data-acquisition backbone.

MNE-RT (this package) is an actively maintained, high-level neurofeedback and BCI application framework built on top of MNE-Python and MNE-LSL. It adds the full closed-loop pipeline that neither of the above provides: neural feature extraction modalities spanning sensor and source space; adaptive feedback protocols; online artifact correction methods; and live visualisation windows. It also handles feature combining, external feedback output via OSC and LSL outlets, BIDS-compatible session saving, and a full CLI.

Highlights

Installation

pip install mne-rt                 # core package
pip install "mne-rt[full]"         # + 3-D viz, dev tools, docs

mamba install -c conda-forge mne-rt
# or, with plain conda:
conda install -c conda-forge mne-rt

uv pip install mne-rt
uv pip install "mne-rt[full]"

git clone https://github.com/mne-rt-org/mne-rt.git
cd mne-rt
pip install -e ".[dev]"

Verify:

mne-rt info     # prints MNE-RT and dependency versions
mne-rt demo     # runs a 60-second mock neurofeedback session

Quick start

from mne_rt import RTStream
from mne_rt.protocols import ZScoreProtocol

# 1 — Create a session object
nf = RTStream(
    subject_id="sub01",
    session="01",
    subjects_dir="/data/subjects",
    montage="easycap-M1",
)

# 2 — Connect to a live LSL stream (or replay a file without hardware)
nf.connect_to_lsl(mock_lsl=True)

# 3 — Record a resting-state baseline (bad channels, ICA, noise cov)
nf.record_baseline(duration=120)

# 4 — Run a closed-loop NF session
nf.record_main(
    duration=300,
    modality=["sensor_power", "erd_ers"],
    protocol=ZScoreProtocol(direction="up", zscore_threshold=0.5),
    show_nf_signal=True,
    show_topo=True,
)

# 5 — Save results (BIDS-compatible JSON + TSV)
nf.save()

CLI

# Print version and all dependency versions
mne-rt info

# Quick demo — no amplifier needed
mne-rt demo --duration 60 --modality sensor_power erd_ers

# Record a resting-state baseline
mne-rt baseline --subject sub01 --subjects-dir /data --session 01

# Run a full session with artifact correction and live displays
mne-rt run --subject sub01 --subjects-dir /data --duration 600 \
           --modality sensor_power erd_ers \
           --artifact-correction asr \
           --topo --brain

Documentation

Full documentation (API reference, tutorials, visualization gallery) is available at mne-rt-org.github.io/mne-rt.

Getting help

• Documentation — mne-rt-org.github.io/mne-rt
• Questions — GitHub Discussions
• Bugs — GitHub Issues; see SUPPORT.md for what to include
• Contributing — see CONTRIBUTING.md and our Code of Conduct

Cite

If you use MNE-RT in your research, please cite:

@inproceedings{shabestari2025advances,
  title        = {Advances on Real Time {M/EEG} Neural Feature Extraction},
  author       = {Shabestari, Payam S. and Ribes, Delphine and D{\'e}fayes, Lara
                  and Cai, Danpeng and Groves, Emily and Behjat, Harry H.
                  and Van de Ville, Dimitri and Kleinjung, Tobias
                  and Naas, Adrian and Henchoz, Nicolas
                  and Sonderegger, Andreas and Neff, Patrick},
  booktitle    = {2025 IEEE 38th International Symposium on Computer-Based
                  Medical Systems (CBMS)},
  publisher    = {IEEE},
  year         = {2025},
  pages        = {337--338},
  doi          = {10.1109/CBMS65348.2025.00074}
}

Acknowledgements

Development was supported by the Swiss National Science Foundation (grant 208164 — Advancing Neurofeedback in Tinnitus).

License

BSD 3-Clause License — © 2024–2026 Payam S. Shabestari