# deepchecks/deepchecks

Deepchecks: Tests for Continuous Validation of ML Models & Data. Deepchecks is a holistic open-source solution for all of your AI & ML validation needs, enabling to thoroughly test your data and models from research to production.

Repository: https://github.com/deepchecks/deepchecks
Canonical: https://ross.abutalabs.com/products/deepchecks
Homepage: https://docs.deepchecks.com/stable
Language: Python
License: NOASSERTION
License Family: other
Topics: machine-learning, ml, model-validation, data-validation, mlops, data-science, python, jupyter-notebook, model-monitoring, data-drift, html-report, deep-learning, pytorch, pandas-dataframe
Last push: 2025-12-28T12:07:44+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 59, release rhythm 40, longevity 100
- inputs: {"age_days": 1787, "days_push": 248, "days_rel": 626, "gap_med": 10, "n_releases_24m": 2}
- 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 4047, forks 303 (observed 2026-08-28T04:08:33.724950+00:00)

## What it is
Deepchecks is an open-source Python library for continuous validation of machine learning models and data, covering testing, CI integration, and monitoring from research to production. It provides built-in checks for data integrity, data drift, and model performance with HTML report output.

## Use cases
- validate ml model quality before deployment
- detect data drift in production
- test training data for integrity issues
- add model validation to ci pipeline
- generate html reports of model evaluation
- monitor model performance over time

## When to choose
- you need structured, reusable checks for ML data and models across research and production
- you want drift detection and model monitoring in a Python workflow with pandas or PyTorch
- you need shareable HTML validation reports for stakeholders

## When to avoid
- you need a full hosted ML observability platform with dashboards and alerting out of the box
- your stack is not Python-based
- the AGPLv3 license is incompatible with your project's licensing

## Facets
- artifact type: library
- maturity: active
- function: testing, monitoring, machine-learning, data-science, benchmarking
- domain: machine-learning, data-science
- platform: python, cross-platform
- tags: model-validation, data-validation, data-drift, mlops, model-monitoring, html-report, pytorch, pandas, jupyter-notebook, agpl-license, data-engineering

## Member repositories
- deepchecks/deepchecks (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:33.724950+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 2026-08-29T18:23:42.273327+00:00, confidence not recorded.
  - readme: https://github.com/deepchecks/deepchecks (fetched 2026-08-28T04:08:33.724950+00:00, sha bce0bc7072a1)
  - homepage: https://docs.deepchecks.com/stable (fetched 2026-08-29T09:16:04.754962+00:00, sha fe75457f84e2)
  - registry_pypi: https://pypi.org/pypi/deepchecks/json (fetched 2026-08-29T09:16:04.757743+00:00, sha d51b706cf9a3)
- Data as of 2026-08-30T08:39:29.467469+00:00.