Skip to main content

GitHub Super-Linter GitHub Super-Linter SQAaaS source code DOI

itwinai-icon

itwinai is a Python toolkit designed to help scientists and researchers streamline AI and machine learning workflows, specifically for digital twin applications. It provides easy-to-use tools for distributed training, hyper-parameter optimization on HPC systems, and integrated ML logging, reducing engineering overhead and accelerating research. Developed primarily by CERN, in collaboration with Forschungszentrum Jülich (FZJ), itwinai supports modular and reusable ML workflows, with the flexibility to be extended through third-party plugins, empowering AI-driven scientific research in digital twins.

See the latest version of our docs here.

Installation

For instructions on how to install itwinai, please refer to the user installation guide or the developer installation guide, depending on whether you are a user or developer

For information about how to use containers or how to test with pytest, you can look at the following documents:

Using itwinai with Claude Code

If you use Claude Code, itwinai ships a skill that guides the integration of your existing training code into an itwinai plugin, covering distributed training, hyper-parameter optimization, logging, profiling and scalability reports.

This repository doubles as a Claude Code plugin marketplace, so the skill installs once and is then available in any directory, including the plugin repository you are creating:

/plugin marketplace add interTwin-eu/itwinai
/plugin install itwinai

Then start an integration with /itwinai:integrating-a-use-case.

For details see Integrating a Use Case with Claude Code and the worked tutorial.

How to contribute

Want to help improve itwinai? Here are a few good ways to get involved:

Citation

If you use itwinai in your research, please cite:

Bunino et al., (2026). itwinai: A Python Toolkit for Scalable Scientific Machine Learning on HPC Systems. Journal of Open Source Software, 11(117), 9409. https://doi.org/10.21105/joss.09409

BibTeX:

@article{Bunino2026,
  doi = {10.21105/joss.09409},
  url = {https://doi.org/10.21105/joss.09409},
  year = {2026},
  publisher = {The Open Journal},
  volume = {11},
  number = {117},
  pages = {9409},
  author = {Bunino, Matteo and Sæther, Jarl and Eickhoff, Linus and Lappe, Anna and Tsolaki, Kalliopi and
            Verder, Killian and Mutegeki, Henry and Machacek, Roman and Girone, Maria and Krochak, Oleksandr and
            Rüttgers, Mario and Sarma, Rakesh and Lintermann, Andreas},
  title = {itwinai: A Python Toolkit for Scalable Scientific Machine Learning on HPC Systems},
  journal = {Journal of Open Source Software}
}

Metadata

Release files for itwinai 0.5.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for itwinai 0.5.0
File Size Uploaded Provenance Actions
itwinai-0.5.0.tar.gz 136.3 kB With provenance Details for itwinai-0.5.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for itwinai 0.5.0
File Interpreter ABI Platform Actions
itwinai-0.5.0-py3-none-any.whl Python 3 none any Details for itwinai-0.5.0-py3-none-any.whl

Total release size: 281.1 kB

Release files / itwinai-0.5.0.tar.gz

Download URL itwinai-0.5.0.tar.gz
Size 136.3 kB
Tags Source
SHA-256 checksum
How to use checksums
cea1d4e6f7c95b11137e07194956d131595db2fcb387a0518acd6e8b33166a42
BLAKE2b-256 checksum
How to use checksums
ce0fb55771cf49a027d5c544dfbb683f0fd2a50bc8241bf39278876d66308d65
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 27, 2026.

Transparency log

Release files / itwinai-0.5.0-py3-none-any.whl

Download URL itwinai-0.5.0-py3-none-any.whl
Size 144.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
656b20e5f9443c3971d475f83d4883b7c8bb45634528a4a678d92d1eb4cb553a
BLAKE2b-256 checksum
How to use checksums
80aa1068ad266bb499de8e994147eb244fdeed152e2a0e98d7ed09c8c6d53fbf
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 27, 2026.

Transparency log

Security for itwinai 0.5.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for itwinai-0.5.0.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 27, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page