neurokit2

Process and analyze ECG, EEG, EDA, RESP, EMG, EOG, and PPG biosignals.

21|1|Updated Mar 19, 2026
One-click install
npx skills add https://github.com/OwnLabAI/ownlab --skill neurokit2-ownlabai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: neurokit2
Source: https://github.com/OwnLabAI/ownlab/tree/main/mart/skills/scientific-skills/neurokit2
Command: npx skills add https://github.com/OwnLabAI/ownlab --skill neurokit2-ownlabai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

NeuroKit2 provides a comprehensive, Python-based toolkit for processing, analyzing, and integrating a wide range of physiological signals (biosignals) such as ECG, EEG, EDA, RESP, EMG, EOG, and PPG, enabling researchers to extract meaningful metrics with reproducible workflows.

Core Features & Use Cases

  • Multi-signal processing and analysis across cardiac, neural, autonomic, respiratory, and muscular domains.
  • HRV, RSA, brain microstates, and cross-signal coupling for holistic psychophysiology research.
  • Modular workflows (ecg_process, rsp_process, eda_process, bio_process, eeg_power, microstates_segment, etc.) with MNE and NeuroKit2 integration.
  • Extensive reference documentation in references/ supporting education and replication.

Quick Start

Install NeuroKit2 and run a simple ECG workflow to see cleaned signals and HRV metrics.

Frequently Asked Questions about neurokit2

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I process ECG and EEG biosignals together for multimodal analysis?

HRV analysis extracts heart rate variability metrics from ECG data using modular workflows like ecg_process. It cleans raw cardiac signals and computes HRV metrics, enabling reproducible psychophysiology and clinical research workflows.

Can I compute brain microstates and EEG power spectra using Python?

Yes, EEG power and microstate analysis compute spectral power and segment brain microstates from raw EEG data. Modular functions like eeg_power and microstates_segment integrate with MNE to support neuroscience research and clinical contexts.

Does this biosignal processing toolkit work with MNE?

Yes, multimodal biosignal processing integrates with MNE for EEG workflows. Modular pipelines like bio_process handle cardiac, neural, and autonomic signals, enabling cross-signal coupling and holistic psychophysiology research.

What is the best way to extract RSA and EDA metrics for psychophysiology research?

Extracting RSA and EDA metrics requires modular workflows like rsp_process and eda_process that clean raw respiratory and electrodermal signals. This computes autonomic metrics, enabling reproducible psychophysiology and human-computer interaction research.

Are there limitations when processing multimodal physiological signals for clinical research?

Biosignal processing for clinical research requires clean raw physiological data inputs for accurate HRV, RSA, and cross-signal coupling results. Signal artifacts and incomplete multimodal datasets limit accuracy, requiring careful preprocessing for reproducible workflows.