The source code and related artefacts of the tools developed in MLEvol are maintained in a dedicated GitHub organisation. This includes prototypes, reference implementations, and integration scripts that support the project’s experiments and case studies.

Visit the MLEvol GitHub organisation 

MLAssetSelection is a web application that helps software engineering (SE) researchers and practitioners find and select pre-trained models and datasets for SE tasks. It continuously extracts assets from multiple AI registries and catalogs them against a taxonomy of SE tasks that covers the whole software development life cycle.

By combining structured metadata with domain knowledge, the tool supports:

• Search and filtering of ML assets using multiple criteria (e.g., task, domain, quality attributes).
• Comparison of alternative assets in terms of suitability for a given MLS context.
• Informed selection decisions aligned with the evolution goals of the target system.

Team: Alexandra González, Oscar Cerezo, Xavier Franch, Silverio Martínez-Fernández

Access to Tool

MLSToolbox aims to provide a set of tools to support the development of Machine Learning Systems (MLS).

Tools: MLS Code Generator, MLS Code Assessment

Team: Claudia Ayala, Cristina Gómez, Lidia López

Links of interest:

• Access to the MLSToobox in the following link
• The source code is publicly available at GitHub 
• Documentation is available at GitHub Wiki 
• Some videos for the MLS Code Generator are available at a dedicated page on the GitHub Wiki 

You can contact the MLSToobox team at the following email address: mlstoolbox-request@mylist.upc.edu