Evidently evaluates, tests, and monitors machine learning systems and data pipelines.
Open source
24 alternativesNannyML
NannyML provides Python tools for post-deployment data science and monitoring model performance under data drift.
About NannyML
NannyML is an open-source Python library for post-deployment data science and machine learning model monitoring. It estimates model performance without access to post-deployment target labels, detects data drift, and links drift alerts to corresponding changes in model performance. It is model-agnostic and designed for data scientists working with deployed models. The library supports tabular classification and regression use cases, using confidence-based performance estimation (CBPE) for classification, direct loss estimation (DLE) for regression, PCA-based data reconstruction for multivariate drift detection, and statistical tests for univariate drift detection. It includes interactive visualizations for analysis.
Key features
- Estimates model performance without post-deployment target labels
- Detects multivariate data drift via PCA-based reconstruction
- Detects univariate feature drift with statistical tests
- Links data drift alerts to model performance changes
- Supports tabular classification and regression use cases
- Provides interactive visualizations for monitoring analysis
Best for: Data scientists monitoring deployed tabular classification and regression machine learning models.
Good for
- Open-source and model-agnostic, compatible with any deployed model
- Estimates model performance without requiring post-deployment target labels
- Links drift alerts to performance changes to reduce alert fatigue
Watch out for
- Limited to tabular classification and regression use cases as of the latest release
NannyML at a glance
- Website
- github.com/NannyML/nannyml
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
NannyML alternatives
Tools and sites you could use instead, ranked by how closely they match.
Deepchecks tests and validates machine learning models and data, covering workflows from research through production.
Open source
24 alternatives
Eurybia tracks model drift and validates data during machine learning model deployment.
Open source
24 alternatives
Pachyderm provides data-focused pipelines and version control for datasets and related workflows.
Open source
24 alternatives
igel lets users train, test, and use machine learning models without writing code.
Open source
24 alternatives
Adaptive Reliability Layer decides when to retrain a model based on drift signals and delayed labels.
Popular in AI Infrastructure & MLOps
Well-known listings from the same topic.
Guild AIguild.aiFlow AIflow-ai.comsystemprompt.iosystemprompt.ioCoreWeavecoreweave.comKili Technologykili-technology.comAPI docsdocs.x.ai
NannyML FAQ
Does NannyML need post-deployment target labels to estimate model performance?
No, it uses CBPE for classification and DLE for regression to estimate performance without targets.
How does NannyML detect multivariate data drift?
It uses PCA-based data reconstruction and monitors reconstruction error over time.
What model types is NannyML compatible with?
It is completely model-agnostic and works with any deployed model.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.