Neuropype 2026: new pipeline format, more ML algorithms
It's time for our next major release (2026) of the NeuroPype signal processing suite! (We skipped a 2025 release, so this one packs in a lot.) Headlining the release is a brand-new pipeline file format, a major expansion of our Bayesian machine learning toolkit, and a wave of new real-time visualization and notification capabilities.
The biggest change is a new, human-readable YAML-based pipeline file format. Unlike the legacy format (based on XML), YAML pipelines are plain text throughout, embed each node's properties right in the node definition, and are diff- and merge-friendly, making them ideal for version control and collaboration. You can easily edit a pipeline's settings with your favorite text editor if needed. The NeuroPype API reads and writes both the new and legacy formats and auto-detects them by content, so your existing pipelines keep loading exactly as before.
This release also brings a large Bayesian machine learning expansion: a new family of sparse Bayesian logistic-regression classifiers, including R2-D2, regularized horseshoe, several spike-and-slab variants, empirical-Bayes, and Skinny Gibbs methods, giving you powerful new tools for high-dimensional state decoding.
We've added a suite of new real-time visualization nodes, including a new PlotDashboard node that tiles live plots from other visualization nodes into a single window, a new stacked-lines mode for the TimeSeriesPlot, live image (heatmap) and table plots, and more. A new Notification node can send alerts via Email, Slack, Teams, Discord, or Pushover, and the Resample node now performs resampling in real time on streaming data.
There are also new connectivity, spectral, and diagnostics nodes — cross-spectral density, phase slope index, ridge/ARD MVAR models, automated channel-quality scoring, and signal-quality classification, among others.
The REST API gains new /inputs and /outputs endpoints that report the files an offline pipeline received and generated, along with richer error reporting and new configuration options. Plus, as always, plenty of minor improvements, node documentation clarifications, and bug fixes throughout.
Check out the Release Notes for full details, and grab the latest release today by logging into your NeuroPype account, or if you're not yet a NeuroPype user, sign up today. We greatly appreciate any feedback you may have, especially those of you using the Academic Edition.
