g.Pype is a Python Software Development Kit (SDK) for building real-time neuroscience, high-resolution EEG, multimodal biosignal, and Brain-Computer Interface (BCI) applications with g.tec biosignal and EEG amplifiers.
The SDK provides a modern Python environment to acquire, process, visualize, stream, and analyze biosignal data in real time. It supports research workflows with g.tec’s biosignal ampfliers such as g.HIamp, g.USBamp, g.Nautilus RESEARCH, g.Nautilus PRO FLEXIBLE, Unicorn Hybrid Black, Unicorn BCI Core-8 and Unicorn BCI Core-4 Headband.
g.Pype is designed for researchers, engineers, and developers who need open Python workflows, documented APIs, real-time processing, multimodal integration, and flexible connection to existing lab infrastructure. It allows users to build custom pipelines for EEG, ECoG, EMG, ECG, EOG, fNIRS synchronization, TMS experiments, neurofeedback, closed-loop stimulation, and advanced BCI research.
The framework uses a modular node-based architecture. Acquisition, filtering, feature extraction, classification, visualization, storage, LSL streaming, UDP communication, and custom processing steps can be combined into real-time pipelines directly in Python.
g.Pype is open to the Python ecosystem and can be extended with scientific and machine learning libraries such as NumPy, SciPy, scikit-learn, PyTorch, TensorFlow, MNE-Python, Pandas, OpenCV, and other research tools.
| Build custom neuroscience applications entirely in Python |
| Create real-time BCI and closed-loop experiments |
| Integrate EEG, ECoG, EMG, ECG and multimodal biosignal streams |
| Connect machine learning and AI models to live biosignal data |
| Synchronize experiments with third-party hardware and software |
| Stream data to external applications and research platforms |
| Develop reusable workflows for collaborative research |
| Accelerate development with modular processing nodes |
| Scale from proof-of-concept studies to complex research systems |
| Integrate seamlessly into existing Python ecosystems |
| Python SDK distributed via pip |
| SDK Reference Documentation |
| Training Curriculum with Hands-On Examples |
| Acquisition Nodes for g.tec Amplifiers |
| Processing Nodes for Real-Time Signal Analysis |
| Visualization Nodes for Time-Series and Spectral Data |
| Trigger and Event Handling Framework |
| Lab Streaming Layer (LSL) Interface |
| UDP Communication Interface |
| Custom Node Development Framework |
| Custom Widget Development Framework |
| Example Projects and Templates |
| Windows Support |
| macOS Support |
REAL-TIME PYTHON FOR HIGH-RESOLUTION EEG
g.Pype enables real-time acquisition and processing of high-resolution EEG and multimodal biosignal data in Python.
Researchers can build pipelines for high-channel-count EEG, ECoG, EMG, ECG and EOG recordings, process incoming signals with low latency, and send results to visualization tools, classifiers, stimulation systems, VR environments, or external applications.
This makes g.Pype especially useful for laboratories that need flexible, programmable, and reproducible workflows instead of closed black-box software.
OPEN PYTHON ECOSYSTEM
g.Pype allows researchers to work directly in Python, one of the most widely used programming environments in neuroscience, machine learning, and data science.
Users can integrate established Python libraries for signal processing, statistics, machine learning, deep learning, visualization, and data management. This makes it possible to connect g.tec amplifiers with custom research code and modern open-source workflows.
Examples include:
- NumPy and SciPy for signal processing
- scikit-learn for classification
- PyTorch and TensorFlow for deep learning
- MNE-Python for EEG and MEG analysis workflows
- Pandas for structured data handling
- OpenCV for video and computer vision applications
- Custom Python packages for lab-specific research pipelines
MODULAR NODE-BASED ARCHITECTURE
g.Pype uses a modular architecture based on processing nodes.
Each node performs a defined task such as signal acquisition, filtering, feature extraction, classification, visualization, streaming, storage, or communication. Nodes can be connected to create complete real-time pipelines.
This structure makes experiments easier to develop, understand, debug, modify, and reuse across different studies and laboratories. Developers can also implement custom nodes to integrate new algorithms, machine learning models, third-party devices, external software, or specific experimental protocols.
LAB STREAMING LAYER AND UDP
g.Pype supports Lab Streaming Layer output for connecting g.tec biosignal data to LSL-enabled research environments.
LSL makes it possible to stream data into external tools and synchronize biosignals with additional modalities. UDP communication enables real-time data exchange with external software, distributed systems, VR applications, robotic devices, and custom laboratory setups.
These interfaces help laboratories integrate g.tec amplifiers into heterogeneous research environments instead of being limited to one closed software ecosystem.
REPRODUCIBLE AND OPEN-SCIENCE-READY WORKFLOWS
g.Pype supports transparent, scriptable and reproducible neuroscience workflows.
Experiments can be defined in Python code, versioned with Git, shared across laboratories, documented with examples, and adapted to specific research protocols. This is especially important for multi-site studies, grant-funded projects, academic collaborations, and open-science initiatives.
Python-based workflows also simplify integration with open analysis environments and data management pipelines, including MNE-Python-based analysis, BIDS-oriented data organization, and custom conversion workflows.
MULTIMODAL RESEARCH INTEGRATION
Modern neuroscience experiments often combine EEG with other modalities such as fNIRS, TMS, eye tracking, motion tracking, virtual reality, stimulation, robotics, or behavioral data.
g.Pype is designed to support these multimodal workflows by providing real-time communication interfaces and flexible Python integration.
The SDK can be used to synchronize biosignal processing with external systems, send triggers, stream data, receive events, and connect custom laboratory infrastructure through Python, LSL, UDP, or dedicated interface nodes.
Typical multimodal applications include:
- EEG and fNIRS experiments
- EEG and TMS experiments
- EEG, fNIRS and behavioral recordings
- Closed-loop neurofeedback
- Real-time BCI control
- VR and AR neuroscience experiments
- Eye-tracking and EEG studies
- Robotic and assistive device control
- Stimulation-based neuroscience protocols
REAL-TIME VISUALIZATION
g.Pype includes tools for real-time visualization of biosignal data and processing results.
Users can display raw data, filtered signals, event markers, triggers, spectra, classification outputs, and custom feedback in real time. This helps researchers monitor signal quality, validate experimental timing, inspect processing pipelines, and build interactive BCI applications.
Visualization tools can be adapted or extended with custom widgets for specific experiments.
BCI DEVELOPMENT
g.Pype provides a flexible environment for Brain-Computer Interface development.
Researchers can implement complete BCI pipelines in Python, including data acquisition, preprocessing, feature extraction, machine learning, classification, feedback, stimulation, and device control.
Applications include:
- P300 BCI
- SSVEP BCI
- Motor imagery BCI
- Hybrid BCI
- Neurofeedback
- Closed-loop stimulation
- Real-time rehabilitation systems
- Assistive technology
- Cognitive workload monitoring
- Multimodal BCI research
CLOSED-LOOP EXPERIMENTS
Closed-loop neuroscience requires fast acquisition, processing, decision-making, and feedback.
g.Pype enables users to build closed-loop experiments where biosignal features are extracted in real time and used to control feedback, stimulation, external software, or connected devices.
This is useful for EEG-TMS experiments, neurofeedback, rehabilitation research, adaptive stimulation, cognitive state monitoring, and real-time experimental control.
HIGH-CHANNEL-COUNT DATA PIPELINES
g.Pype is built for demanding biosignal workflows with g.tec amplifiers.
High-channel-count EEG and ECoG recordings can be processed in custom Python pipelines. Researchers can define how data is buffered, transformed, visualized, streamed, stored, or forwarded to other software.
This gives laboratories control over their own data flow and helps address demanding requirements such as long recordings, multimodal synchronization, real-time feature extraction, and integration with external analysis environments.
g.PYPE TRAINING
g.Pype includes structured training material and example applications to help users get started quickly.
The training covers environment setup, first scripts, signal generation, visualization, filtering, routing, spectral analysis, data storage, LSL communication, UDP communication, paradigm integration, and event-related experiments.
This allows new users to build working applications quickly and gives advanced users a foundation for custom development.
OPEN RESEARCH WORKFLOWS WITH g.tec AMPLIFIERS
g.Pype helps researchers use g.tec amplifiers in open, programmable and collaborative research environments.
Instead of limiting the workflow to one predefined software path, g.Pype allows laboratories to build their own Python-based research infrastructure around g.tec hardware. This is important for academic labs working with MNE-Python, machine learning pipelines, LSL-based synchronization, BIDS-oriented data organization, and multi-lab collaborations.
G.TEC SUITE 2024
g.Pype complements the g.tec software ecosystem and can be combined with g.NEEDaccess, g.Recorder, g.HIsys, and g.BSanalyze. The g.tec Suite 2024 provides software tools for data acquisition, real-time processing, offline analysis, APIs, stimulation control, montage planning, software updates, and compatibility checks. g.Pype extends this ecosystem with a modern Python SDK for custom real-time neuroscience development.
Together, g.tec hardware and software provide a powerful environment for high-resolution EEG, multimodal biosignal acquisition, real-time BCI development, open Python workflows, and advanced neuroscience research.
FREQUENTLY ASKED QUESTIONS
Yes. g.Pype provides access to biosignal data within Python, allowing researchers to build custom export pipelines, BIDS-oriented workflows, automated processing chains, and integration with modern open-science infrastructures.
Yes. g.Pype applications can be packaged and distributed as standalone executables. This simplifies deployment of custom neuroscience applications without requiring users to modify source code.
Yes. Python-based workflows, open interfaces, network communication, and integration with established neuroscience software make g.Pype suitable for multi-lab studies, collaborative research projects, and large-scale neuroscience initiatives.
Yes. Pipelines are written as Python code and can be version-controlled, documented, shared between laboratories, and integrated into reproducible research workflows. This simplifies collaboration, validation, and long-term maintenance of neuroscience experiments.
Yes. Many laboratories use Python and MATLAB together. Data generated with g.Pype can be exported or streamed to external environments, enabling integration with existing MATLAB-based analysis pipelines and research infrastructure.
Yes. Researchers and developers can create custom nodes for signal processing, machine learning, visualization, communication, hardware integration, and experimental control. This makes g.Pype highly adaptable to specialized research requirements.
Yes. g.Pype enables closed-loop applications where biosignals are acquired, processed, classified, and used to control stimulation, feedback systems, external software, robotic devices, or virtual environments in real time.
Yes. g.Pype was designed for multimodal neuroscience research. Multiple biosignal streams, external sensors, behavioral events, stimulation devices, and software applications can be synchronized within a common experimental framework.
Yes. g.Pype can communicate with third-party systems using Python libraries, UDP communication, and LSL streams. This enables integration with eye tracking systems, motion capture solutions, virtual reality environments, robotics, and custom laboratory equipment.
Yes. g.Pype includes LSL output functionality and can stream biosignal data to LSL-compatible applications. This enables integration with a large ecosystem of neuroscience tools, stimulation software, virtual reality environments, eye trackers, motion tracking systems, and multimodal research platforms.
Yes. TMS devices can be integrated through custom Python nodes, trigger interfaces, UDP communication, or Lab Streaming Layer synchronization. This allows researchers to build EEG-TMS experiments and closed-loop stimulation paradigms.
Yes. g.Pype supports multimodal workflows through Python interfaces, Lab Streaming Layer (LSL), triggers, and network communication. This enables synchronization of EEG recordings with fNIRS systems and other physiological monitoring devices.
Yes. Biosignal data acquired with g.Pype can be processed using MNE-Python workflows. Researchers can integrate MNE-Python into custom pipelines or export and process data within existing neuroscience analysis environments.
Absolutely. g.Pype is fully compatible with the Python ecosystem and allows direct integration of libraries such as NumPy, SciPy, scikit-learn, PyTorch, TensorFlow, Pandas, and OpenCV through custom processing nodes.
Yes. g.Pype was specifically developed for low-latency, real-time applications. Data acquisition, signal processing, machine learning, classification, visualization, and feedback generation can all be performed within a single real-time pipeline.
Yes. g.Pype is suitable for high-resolution EEG experiments and can be used together with g.tec acquisition systems that support high-channel-count recordings. This makes it suitable for advanced neuroscience applications such as source localization, high-density EEG, multimodal research, and Brain-Computer Interfaces.
g.Pype is designed as a Python SDK for real-time biosignal acquisition and processing with g.tec hardware. It supports g.Nautilus, Unicorn Hybrid Black, and is being extended for integration with additional g.tec amplifiers such as g.HIamp and g.USBamp. The architecture is designed to provide a common Python framework across the g.tec amplifier portfolio.
NEED MORE INFORMATION
ABOUT THIS PRODUCT?
Send us your email so we can contact you as soon as possible.
