Freedom251 › AI Model Explainability Software
Alibi
Plans
| Plan | Billed and limits | Price |
|---|---|---|
| Alibi | Source-available Python library · non-production use; limited production use for non-profit educational institutions subject to conditions | Free |
As github.com lists them, read 14 Nov 2026. The maker's own page has the final word.
Facts from Alibi's own pages
- Confidence scores
- Trust Scores and Linearity Measure provide instance-specific measures of model confidence. · github.com, 14 Nov 2026
- Global explainers
- Global methods include ALE, partial dependence, partial dependence variance, and permutation importance. · github.com, 14 Nov 2026
- Install options
- The project documents installation through pip from PyPI or GitHub, and through conda/mamba. · github.com, 14 Nov 2026
- Integration
- The usage API is modeled on scikit-learn's initialize, fit, and explain steps. · github.com, 14 Nov 2026
- License
- The repository license is Business Source License 1.1, with the stated change license of Apache License 2.0 four years after a version's release. · github.com, 14 Nov 2026
- Local explainers
- Local methods include Anchors, counterfactuals, and Integrated Gradients. · github.com, 14 Nov 2026
- Methods
- It includes black-box and white-box, local and global explanation methods. · github.com, 14 Nov 2026
- Model compatibility
- The method table distinguishes black-box explainers needing a prediction function, differentiable black-box methods, and white-box methods requiring model access. · github.com, 14 Nov 2026
- Optional dependencies
- Ray can be installed for distributed explanation computation and SHAP support is available as an install option. · github.com, 14 Nov 2026
- Prototype method
- ProtoSelect provides a distilled dataset view to help construct a 1-nearest-neighbor interpretable classifier. · github.com, 14 Nov 2026
- Purpose
- Alibi is a Python library for machine-learning model inspection and interpretation, with explanation methods for classification and regression. · github.com, 14 Nov 2026
- Supported inputs
- Its listed explanation methods cover tabular, text, and image data. · github.com, 14 Nov 2026
Where Alibi stands on Freedom251
- AI Model Explainability Software#27 of 29