# SeldonIO/alibi

Algorithms for explaining machine learning models

Repository: https://github.com/SeldonIO/alibi
Canonical: https://ross.abutalabs.com/products/alibi
Homepage: https://docs.seldon.io/projects/alibi/en/stable/
Language: Python
License: NOASSERTION
License Family: other
Topics: machine-learning, explanations, interpretability, counterfactual, xai
Last push: 2025-10-17T13:23:21+00:00

## Health v2 (maintenance only)
Score: 44/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 47, release rhythm 8, longevity 100
- inputs: {"age_days": 2745, "days_push": 320, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2644, forks 266 (observed 2026-08-28T04:07:06.667422+00:00)

## What it is
Alibi is a Python library providing algorithms for explaining and interpreting machine learning models, including black-box, white-box, local, and global explanation methods for classification and regression. It supports techniques like anchor explanations, integrated gradients, and counterfactuals across tabular, image, and text data.

## Use cases
- explain predictions of a black-box ML model
- generate counterfactual explanations for classifier decisions
- compute feature attributions like integrated gradients for text models
- interpret image classification model predictions
- audit model decisions for regulatory compliance
- understand which features drive a regression model's output

## When to choose
- you need production-quality implementations of explanation algorithms in Python
- you want to explain models across tabular, image, and text modalities
- you need both local and global interpretability methods in one library

## When to avoid
- you need outlier or drift detection - use the sister project alibi-detect instead
- you need a no-code or GUI-based explainability tool
- your license requirements are incompatible with the Business Source License 1.1

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, nlp, computer-vision
- domain: machine-learning, data-science, artificial-intelligence
- platform: python, cross-platform
- tags: explainability, xai, interpretability, counterfactual-explanations, model-inspection, shap, anchor-explanations

## Member repositories
- SeldonIO/alibi (main) score 44

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:06.667422+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:19:00.277008+00:00, confidence not recorded.
  - readme: https://github.com/SeldonIO/alibi (fetched 2026-08-28T04:07:06.667422+00:00, sha cd307cb35449)
  - registry_pypi: https://pypi.org/pypi/alibi/json (fetched 2026-08-29T10:01:49.737274+00:00, sha db062dc6135f)
- Data as of 2026-08-30T08:39:29.467469+00:00.