NeuroMANCER
Project record
Maintained by Pacific Northwest National Laboratory12
NeuroMANCER (Neural Modules with Adaptive Nonlinear Constraints and Efficient Regularizations) is an open-source differentiable programming library written in PyTorch and published by Pacific Northwest National Laboratory. It is built for learning to solve parametric constrained optimization problems, physics-informed system identification, and model-based optimal control, and it provides a symbolic interface for adding physics equations, domain knowledge, and constraints to learned models.1
- Repository: Repository (pnnl/neuromancer) (external site: github.com)
- Documentation: Documentation (external site: pnnl.github.io)
- License: LICENSE (external site: github.com)
- Release notes: Releases (external site: github.com)
Availability and license
Overall availability
Source code is public on GitHub, and the README documents installation with "pip install neuromancer".1
Availability is separate from permission: read the license before using or redistributing.
The license permits redistribution and use in source and binary forms, with or without modification, provided the copyright notice and disclaimers are retained. It also states that the Battelle name may not be used without Battelle's written consent. The README describes it as a BSD license; this catalog records no SPDX identifier because the text is Battelle's own wording.21
Component reuse rights
- weights
- Unknown — no complete fact-level rights review
- code
- Unknown — no complete fact-level rights review
- data
- Unknown — no complete fact-level rights review
- documentation
- Unknown — no complete fact-level rights review
No complete system-rights review is recorded for this release.
Public materials checklist
| Item | Status | Notes and evidence |
|---|---|---|
| Source codeIs the source code publicly readable? | Public | Public repository in PNNL's GitHub organization.1 |
| DocumentationIs user documentation published? | Public | Online documentation, a user and developer guide, release notes, and many tutorial notebooks (most runnable on Google Colab) are linked from the README. The online documentation site is labeled for version 1.3.3, older than the v1.5.6 code release.13 |
| InstallationAre installation instructions or packages publicly available? | Public | The README gives "pip install neuromancer" and links manual installation instructions; the documentation describes conda environment files for Ubuntu, Windows, and macOS on Apple M1.13 |
| Supported platformsAre supported operating systems or hardware documented? | Partial | The documentation provides environment files for Ubuntu, Windows, and macOS (Apple M1) and recommends conda for GPU acceleration; the README notes PyTorch Lightning integration for GPU and multi-GPU training. No complete support matrix was found.31 |
| Release statusAre versioned releases published? | Public | Versioned GitHub releases are published; the most recent listed is v1.5.6, released September 26, 2025.4 |
What it is useful for
The README lists learning to optimize, learning to model dynamical systems (for example with neural ODEs, Koopman operators, or SINDy), and learning to control with differentiable predictive control. Its tutorials include examples for building control, HVAC load forecasting, and grid-responsive building energy systems.1
Organization context
U.S. eligibility
Eligible · basis: U.S.-governed project
NeuroMANCER is published in PNNL's GitHub organization, and its license file names Battelle Memorial Institute as copyright holder. The README states that PNNL is a multi-program national laboratory operated for the U.S. Department of Energy by Battelle Memorial Institute, and PNNL states that Battelle manages and operates it for DOE.125
Sources
This listing is not an endorsement, a safety assessment, or a federal approval.