# Trusted-AI/AIX360

Interpretability and explainability of data and machine learning models

Repository: https://github.com/Trusted-AI/AIX360
Canonical: https://ross.abutalabs.com/products/aix360
Homepage: https://aix360.res.ibm.com/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: explainable-ai, explainable-ml, trusted-ai, trusted-ml, machine-learning, deep-learning, codait, artificial-intelligence, explainabil, xai, ibm-research, ibm-research-ai
Last push: 2026-08-08T16:30:28+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 96, release rhythm 8, longevity 100
- inputs: {"age_days": 2610, "days_push": 25, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1796, forks 325 (observed 2026-08-28T04:05:37.611294+00:00)

## What it is
AI Explainability 360 is an open-source Python library from IBM Research offering a comprehensive set of algorithms for interpreting and explaining datasets and machine learning models. It supports tabular, text, image, and time series data, covering data explanations, local and global post-hoc explanations, and directly interpretable models with proxy explainability metrics.

## Use cases
- explain predictions of a machine learning model
- get local post-hoc explanations for individual predictions
- find prototypical examples explaining a dataset
- explain image classifier decisions
- compute explainability metrics for models
- build interpretable models instead of black boxes
- explain time series model predictions

## When to choose
- you need a broad toolkit of established XAI algorithms in Python
- you work with tabular, text, image, or time series data and need explanations
- you want both data explanations and model explanations from one library
- you need Apache-2.0 licensed explainability tooling from a reputable research lab

## When to avoid
- you need explainability for LLMs - use IBM's ICX360 instead
- you want a actively evolving library - development has slowed and it is in maintenance mode
- you need a GUI or interactive-only tool rather than a Python API
- you need explanations for non-Python ML stacks

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, nlp, image-processing, data-science
- domain: machine-learning, artificial-intelligence, data-science
- platform: python
- tags: explainable-ai, xai, interpretability, explainability-metrics, ibm-research, trusted-ai

## Member repositories
- Trusted-AI/AIX360 (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:37.611294+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 2026-08-30T03:22:48.310129+00:00, confidence not recorded.
  - readme: https://github.com/Trusted-AI/AIX360 (fetched 2026-08-28T04:05:37.611294+00:00, sha 09808310eff5)
  - registry_pypi: https://pypi.org/pypi/aix360/json (fetched 2026-08-29T11:01:34.246606+00:00, sha c40df66753b6)
- Data as of 2026-08-30T08:39:29.467469+00:00.