Shapash
Shapash: An open-source Python toolkit for exploring, documenting, and serving model explanations. Ranked #12 of 29 in AI Model Explainability Software by our editors (7.1/10); pricing: Free plan; best for teams sharing explainability dashboards and reports.
At a glance
- Editor score7.1 / 10
- PricingFree plan
- Best forTeams sharing explainability dashboards and reports
- Free planYes
- Paid fromNone
- Feature attributionYes
- Facts checked28 Sep 2026
Where it wins
- Interactive global and local explanation views with subset filtering
- Exports local explanations and standalone HTML audit reports
- Serves predictions and local explanations through API or batch workflows
Where it doesn't
- Requires a self-hosted Python environment rather than offering a hosted service
- Does not provide built-in counterfactual or fairness analysis
- Support is through documentation and community channels
Our verdict on Shapash
Shapash is an open-source Python library for data scientists who need to interpret machine-learning models and share explanations with others. Its web app presents global and local views, including feature contributions to predictions, while its tools can summarize and export local explanations. The library supports regression, binary classification, and multiclass problems, with documented compatibility for scikit-learn ensembles, linear models, SVM, LightGBM, CatBoost, and XGBoost. It is a fit for teams that want explainability within Python workflows, not buyers seeking a hosted commercial service.
The strongest case for Shapash is its reporting and exploration workflow. Users can filter subsets of data for closer analysis, evaluate explainability quality with metrics, and generate standalone HTML project reports for audit documentation. That combination supports both investigation and sharing: local explanations can be distilled for review, while the interactive app helps navigate explanations across a model. Shapash also integrates with SHAP and LIME, alongside common tree-model libraries, making it relevant where those approaches already feature in the modeling stack. Its focus is explanation and documentation rather than a broader governance suite; counterfactual and fairness analysis are not built-in capabilities.
Deployment and serving are suited to teams comfortable managing their own environment. Shapash is self-hosted, and its SmartPredictor can serve predictions and local explanations through API or batch workflows, extending it beyond retrospective analysis. The open-source model means there are no paid tiers to compare, while support channels are documentation and community. Choose Shapash when a Python-based, self-managed tool for explainability views, reports, and serving fits the workflow. Teams that need hosted operation, built-in fairness analysis, or dedicated counterfactual tooling should look at alternatives.
Your product? Our editors can test Shapash in depth and publish a review, labelled as paid · from $99/mo →
Shapash pricing
Shapash fact sheet
| Free plan | Yes |
|---|---|
| Paid from | None |
| Feature attribution | Yes |
| Counterfactual explanations | No |
| Fairness analysis | No |
| Audit reports | Yes |
| Deployment options | Self_hosted |
| Supported model types | CatBoost, XGBoost, LightGBM, scikit-learn ensembles, linear models, SVM; regression, binary classification, multiclass |
| Deployment | Self-hosted |
| Platforms | Web |
| Support | Docs, Community |
| Built for | Solo, Small business, Mid-market, Enterprise (editorial estimate) |
| Integrations | 6 integrations: SHAP, LIME, scikit-learn, LightGBM, CatBoost, XGBoost |
| Pricing | Free plan |
| Website | shapash.readthedocs.io |
| Facts checked | 28 Sep 2026 |
Shapash integrations
Shapash lists 6 integrations on its own site.
- SHAP
- LIME
- scikit-learn
- LightGBM
- CatBoost
- XGBoost
Alternatives to Shapash
- AIX360A broad, self-hosted Python toolkit for local, global, and time-series model explanations.9.1
- Arize AIProduction-focused explainability pairs feature attribution with fairness monitoring and model comparisons.8.5
- Fiddler AIA tracing and evaluation platform for teams debugging LLM and agent workflows.7.4
See all Shapash alternatives →
Used Shapash? Be the first to review it
The editor score above is our own research. What this page doesn't have yet is a reader's view — what you used Shapash for, what worked and what didn't. No stars are seeded and no review is paid for; an editor reads every one before it appears.
Write a reviewTwo minutes · verified accounts only · read by an editor before it appears
Featured on iTechGuides
Shapash is listed in our AI Model Explainability Software directory. Add the badge to your site — it links back to this page.
<a href="https://www.itechguides.com/products/shapash/"><img src="https://www.itechguides.com/best/badge/shapash.svg" alt="Featured on iTechGuides" width="230" height="46"></a>
Reviewed by iTechGuides Editors · Editorial team · Updated Oct 2026
Advertiser disclosure: iTechGuides is reader-supported. Vendors can pay for top positions in our rankings and for a place on other products' pages, and we may earn a commission when you click some links. How we rank.
Last updated · How we research and update