---
id: odc-stac
version: "0.5.3"
license: unclear
license_treatment: unclear
maintenance: active
---

# odc-stac — Tooling for converting STAC metadata to ODC data model

License: unclear · Maintenance: active · Downloads: 114.5K/mo

## What it is and what it does

odc-stac bridges STAC metadata catalogs and xarray, the standard data model for multidimensional geospatial arrays in Python. It takes STAC items (which describe collections of raster imagery and other spatial data) and loads them into xarray Datasets, making them ready for analysis, visualization, and computation. The package integrates with Dask to parallelize data loading and processing across multiple machines or cores, which is essential for working with large satellite or climate datasets that don't fit in memory.

The library is built on a foundation of mature geospatial tools: rasterio for raster I/O, affine for coordinate transformations, odc-geo for geospatial utilities, and xarray for the data model itself. It's actively maintained and supports modern Python versions (3.10–3.13). The package is designed for researchers, data engineers, and analysts working with cloud-hosted or distributed geospatial datasets.

Use it for:

- Load satellite imagery from a STAC catalog into xarray for time-series analysis or change detection.
- Query a STAC source, retrieve matching scenes, and parallelize their loading across a Dask cluster.
- Convert STAC metadata into a standardized xarray format for ingestion into geospatial processing pipelines.
- Visualize multispectral raster data (e.g., red, green, blue bands) retrieved from STAC items using xarray's plotting methods.
- Build reproducible workflows that fetch and process geospatial data from STAC catalogs without manual download steps.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Converts STAC (SpatialTemporal Asset Catalog) metadata into xarray Datasets, with optional Dask support for distributed data loading and computation.

Yes, if you work with STAC catalogs or cloud-hosted geospatial data. The package is actively maintained, has low install friction, and fills a clear gap between STAC metadata and xarray workflows. However, verify the license terms before use in proprietary projects, and confirm your workflow's actual dependency requirements.

## Install

pip install odc-stac
uv add odc-stac
poetry add odc-stac

## Installing odc-stac

Before you install: Low friction: pure Python wheel with no compiled dependencies. Active maintenance (last release 15 days ago, last commit 2026-07-29). Requires Python 3.10+. Eleven runtime dependencies are all established geospatial and data-processing libraries.

License in practice: License status is unclear—no SPDX identifier or raw license text is recorded in the package metadata. Verify the actual license before use in proprietary or restricted contexts.

Quickstart:

pip install odc-stac

import odc.stac
from pystac import Item

xx = odc.stac.load(
    items=[],
    bands=["red", "green", "blue"],
)

Requires Python 3.10 or later. Requires a STAC item source; pystac is a runtime dependency but the full workflow typically requires external catalog access.

Verify before relying:

- Whether pystac_client (not listed as a dependency) is required for typical STAC catalog workflows.
- Actual license text and terms—metadata shows no SPDX or raw license field.
- Whether the optional botocore extra is needed for typical AWS S3 workflows.

## Package facts

- License: not declared (unclear)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 114.5K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

load STAC items into xarray, STAC to xarray conversion, spatial temporal asset catalog loader, distributed geospatial data loading, STAC metadata processing, raster data from STAC catalogs, dask-enabled geospatial loading, geospatial, stac, dask-distributed

[View on SkillFed](https://skillfed.io/packages/odc-stac) · [View on PyPI](https://pypi.org/project/odc-stac/)