GitHub topic

interpretability GitHub repositories

Explore 10 tracked GitHub repositories tagged interpretability. Compare their recorded star activity and implementation languages, then follow related topics to find other projects.

Snapshot: 2026-10-28. The collection gained 3 stars since the previous daily snapshot.

Tracked repositories: 10
Total stars: 63,877
Stars gained · 7 days: +58
Stars gained · 30 days: +216

Compare star activity

Up to five projects on this page, ordered by daily star growth. Open a project for its description and recorded star history.

Swipe to compare all star periods →

Star activity for interpretability repositories on this page
Repository	Total stars	Today	7 days	30 days
shap/shap	25.8K	+2	+12	+52
EthicalML/awesome-production-machine-learning	21.0K	+1	+23	+86
ndif-team/nnsight	1.1K	+0	+8	+18
interpretml/interpret	7.0K	+0	+6	+20
MAIF/shapash	3.3K	+0	+3	+11

Explore repositories

Showing 1–10 of 10 tracked repositories.

shap/shap

A game theoretic approach to explain the output of any machine learning model.

★ 25.8K+2 todayJupyter Notebook

machine-learning deep-learning

View ↗

EthicalML/awesome-production-machine-learning

A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

ndif-team/nnsight

The nnsight package enables interpreting and manipulating the internals of deep learned models.

★ 1.1K+0 todayPython

machine-learning pytorch

View ↗

interpretml/interpret

Fit interpretable models. Explain blackbox machine learning.

MAIF/shapash

🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

★ 3.3K+0 todayJupyter Notebook

machine-learning python

View ↗

understandable-machine-intelligence-lab/Quantus

[JMLR 2023] Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations

★ 678+0 todayJupyter Notebook

machine-learning deep-learning

View ↗

microsoft/responsible-ai-toolbox

Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libraries empower developers and stakeholders of AI systems to develop and monitor AI more responsibly, and take better data-driven actions.