Alibi
github.com
- Free plan
- Linux
- API
- Self-hosted
6.7 Club score Visit github.com
Plans
Every plan and priceAlibi
Free
Pricing on request
What the maker publishes
- Confidence scores
- Trust Scores and Linearity Measure provide instance-specific measures of model confidence. source
- Global explainers
- Global methods include ALE, partial dependence, partial dependence variance, and permutation importance. source
- Install options
- The project documents installation through pip from PyPI or GitHub, and through conda/mamba. source
- Integration
- The usage API is modeled on scikit-learn's initialize, fit, and explain steps. source
- 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. source
- Local explainers
- Local methods include Anchors, counterfactuals, and Integrated Gradients. source
- Methods
- It includes black-box and white-box, local and global explanation methods. source
- Model compatibility
- The method table distinguishes black-box explainers needing a prediction function, differentiable black-box methods, and white-box methods requiring model access. source
- Optional dependencies
- Ray can be installed for distributed explanation computation and SHAP support is available as an install option. source
- Prototype method
- ProtoSelect provides a distilled dataset view to help construct a 1-nearest-neighbor interpretable classifier. source
- Purpose
- Alibi is a Python library for machine-learning model inspection and interpretation, with explanation methods for classification and regression. source
- Supported inputs
- Its listed explanation methods cover tabular, text, and image data. source
Checked against the maker's pages on 14 Nov 2026.