Requirements
Before installing, ensure you have:- Python ≥ 3.11 (Python 3.11, 3.12, or 3.13)
- pip package manager
- 64-bit system (Linux, macOS, or Windows)
The Python SDK does not require an API key. All processing is local.
Install from PyPI
Install the latest stable version from PyPI:- NumPy ≥ 1.26
- scikit-learn ≥ 1.4
- SciPy ≥ 1.17.1
Optional Dependencies
Install optional features as needed:MNE-Python Integration
For EEG preprocessing and feature extraction:- MNE ≥ 1.6
Visualization
For plotting and diagnostics:- Matplotlib ≥ 3.8
Softmax Model
For the optional JAX-basedNimbusSoftmax model:
- JAX ≥ 0.4.25
Riemannian Feature Pipelines
For pyRiemann covariance and tangent-space feature extraction with Nimbus classifier heads:- pyRiemann ≥ 0.11
The
riemann extra enables nimbus_bci.riemann.make_riemann_nimbus_pipeline(...). This is a feature-extraction bridge from EEG epochs to Nimbus heads, not a separate Riemannian Bayesian model family.All Optional Dependencies
Install everything:Development Installation
For development or contributing:- pytest for testing
- Cython for building extensions
- build and twine for packaging
Verify Installation
Test your installation — product surface first, then classical heads:Platform-Specific Notes
macOS
Pre-built wheels for Intel (x86_64) and Apple Silicon (arm64):
Linux
Pre-built wheels for x86_64 use themanylinux_2_28 platform tag. Other architectures fall back to building from the sdist (requires a C compiler and Cython).
Windows
Pre-built wheels for 64-bit Windows:32-bit systems are not supported. Use 64-bit Python on a 64-bit OS.
Troubleshooting
JAX Installation Issues
JAX is only required forNimbusSoftmax. If JAX installation fails, install it separately first:
Import Errors
If you see import errors, verify dependencies:MNE-Python Conflicts
If you have an existing MNE installation, you may need to upgrade:Upgrading
Upgrade to the latest version:Uninstalling
Remove the package:License
The nimbus-bci Python SDK is proprietary, with two tracks under LICENSE.txt (v2.1):
Any use inside a for-profit company, in a paid product or service, or for sponsored / fee-for-service research requires a commercial license. Citation is requested as a community norm, not a license condition.
Request a commercial license
Email hello@nimbusbci.com with your use case.Non-commercial eligibility is self-executing — no license key or registration is required. Full terms ship with the package as
LICENSE.txt.What’s next
Quickstart
Build your first Personalizer in minutes
API Reference
Explore the complete API documentation
sklearn Integration
Use nimbus-bci with sklearn pipelines
MNE Integration
Preprocess EEG data with MNE-Python
Support
Need help with installation?- Email: hello@nimbusbci.com
- GitHub Issues: github.com/nimbusbci/nimbuspysdk/issues
Successfully installed? Continue with the Quickstart.