Trusted-AI/AIX360

Health v2 · maintenance only

Adoption not part of the score

1796 stars · 325 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity maintenance

machine-learning nlp image-processing data-science machine-learning artificial-intelligence data-science python explainable-ai xai interpretability explainability-metrics ibm-research trusted-ai

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Trusted-AI/AIX360")