pystac-ext-mlm

What it is and what it does

pystac-ext-mlm is a PySTAC extension package that implements the Machine Learning Model extension specification for STAC (SpatioTemporal Asset Catalog). It allows you to attach standardized ML model metadata to STAC items and collections, describing model architecture, the framework used, input and output specifications, training configuration, and runtime requirements. This is useful when cataloging machine learning models alongside the geospatial or scientific data they operate on.

The package is tightly integrated with the PySTAC ecosystem and depends on pystac-core, pystac-ext-classification, and pystac-ext-raster. It supports multiple versions of the MLM specification (v1.0.0 through v1.4.0) and follows semantic versioning aligned to the extension spec version. The package is actively maintained, marked Production/Stable, and requires Python 3.10 or later.

Use it for:

• Catalog machine learning models used in geospatial analysis alongside the satellite or raster imagery they process.
• Document model architecture, training datasets, and performance metrics within a STAC collection for reproducibility.
• Track ML model lineage and versioning when models are retrained or updated in a data pipeline.
• Integrate ML model metadata with classification and raster extensions to describe end-to-end geospatial ML workflows.
• Enable discovery of trained models by framework, input/output format, or training approach in a searchable STAC catalog.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Adds Machine Learning Model extension support to PySTAC, enabling description of ML model architecture, framework, inputs, outputs, training details, and runtime information within STAC catalogs.

Yes. Active maintenance (released 4 days ago), Production/Stable status, permissive Apache-2.0 license, no known vulnerabilities, and low install friction make this a safe choice. Install it if you are already using PySTAC and need to catalog machine learning models with standardized metadata. The tight coupling to pystac-core and related extensions means it integrates seamlessly into existing PySTAC workflows.

Install

pystac-ext-mlm on PyPI

pip install pystac-ext-mlm

uv add pystac-ext-mlm

poetry add pystac-ext-mlm

Installing pystac-ext-mlm

Before you install

Low friction install with active maintenance. Released 4 days ago, last commit 2026-08-10, and marked Production/Stable. Requires Python >=3.10 and depends on three pystac packages (pystac-core, pystac-ext-classification, pystac-ext-raster), all of which are part of the same ecosystem.

License in practice

Apache-2.0 permissive license allows commercial and private use with minimal restrictions—you can use, modify, and distribute this code freely provided you include the license notice.

Quickstart

pip install pystac-ext-mlm

from pystac_ext_mlm import MLM

# Use MLM extension to add ML model metadata to a STAC item
mlm = MLM.from_item(item)

Requires Python >=3.10; pystac-core and related extensions must be installed as runtime dependencies.

Verify before relying

• Whether the extension supports all major ML frameworks (TensorFlow, PyTorch, scikit-learn, etc.) or a specific subset.
• Whether model versioning and lineage tracking are supported beyond the core architecture/framework fields.
• Performance characteristics when working with large STAC catalogs containing many ML model items.

Package facts

Evidence: pystac_ext_mlm-1.4.1-py3-none-any.whl

Keywords: STAC, catalog, imagery, mlm, pystac, raster

Tags

More Artificial Intelligence packages