Windows
AvailableNative build for Windows 10 and 11. The installer is not code-signed yet, so Windows shows a warning on first launch.
Download .msiWindows 10 + · 8 GB RAM recommended
Wire filters, decomposition and models on a canvas, inspect every intermediate result, and hand the whole pipeline to a colleague as one file. Built on the same methods as MNE and EEGLAB.
Each card is a function you can open. Change one knob and every result downstream updates while you watch.
Every card keeps its output. Click a wire and the spectrum before and after appears, with the passband drawn on it. No print statements, no re-running a script to check one step.
How execution works
Cards that claim to reproduce a reference are run against it on public recordings. The agreement is published next to the card, so a reviewer can check it without trusting us.
Read the validation reportA pipeline saves to a single file with every card and parameter. A colleague opens it and gets the same result on their machine, with no environment to rebuild.
Sharing a workflowThe canvas, the gears and the plots, as they look on your screen.



Decorate a function and it becomes a block with typed inputs, outputs and controls. No build system, no YAML.
# Drop this in ~/.signal-studio/nodes/. It shows up in the palette. from signal_studio import node, Signal from scipy.signal import butter, filtfilt @node(category="filter", color="#0f62fe") def bandpass( x: Signal, low: float = 1.0, high: float = 40.0, order: int = 4, ) -> Signal: b, a = butter(order, [low, high], fs=x.sfreq, btype="band") return x.with_data(filtfilt(b, a, x.data))
{
"app_version": "0.9.2",
"cards": [
{ "id": "signalstudio.notch", "params": { "freq": 60 } },
{ "id": "signalstudio.band_pass", "params": { "l_freq": 1.0, "h_freq": 40.0 } },
{ "id": "signalstudio.epoch" },
{ "id": "signalstudio.n1n2" }
]
}
Free, local, no account and no telemetry. Signal Studio is in public beta: usable, but still moving.
Native build for Windows 10 and 11. The installer is not code-signed yet, so Windows shows a warning on first launch.
Download .msiWindows 10 + · 8 GB RAM recommended
Universal build for Apple Silicon and Intel. The code compiles; packaging and notarisation are in progress.
See the roadmapmacOS 12 + · 8 GB RAM recommended
Compiles on Linux, but is not packaged or tested across distributions yet.
Packages and Dockerglibc 2.31 + · 8 GB RAM recommended
Real software you can run on real recordings today. Expect bugs, and record the version you ran next to your data.
Join the betaReport what breaks on GitHub or Discord
Cards, workflows and models: published by labs, opened in one click, credited to their authors.
Filters, references, epoching, time-frequency and statistics. Each one documented and versioned.
Whole pipelines you can open, run on your own data, fork and share back.
Models, importers and skins published by the community, installed from the palette.
Acquisition systems and file formats Signal Studio reads, and how they map to MNE.
Concepts, the card reference, recipes and the full list of error codes.
Share a card or a workflow under your name or your lab's, with an API token for scripts.