OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Srai

Srai is an open-source Python library for geospatial machine learning with vector geometries. It provides tools to acquire and process geographic data, divide areas into micro-regions, and embed those regions into vector spaces for downstream tasks.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Srai — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Srai when a Python workflow needs to acquire or process geographic data, create smaller spatial units, or produce vector representations of regions for machine-learning tasks.

Who it is for

  • Python developers building geospatial machine-learning workflows.
  • Spatial analysts preparing geographic or transit data for downstream tasks.

Documented uses

  • Download OpenStreetMap or Overture Maps data for an area.
  • Process vector data to extract features such as roads, buildings and points of interest.
  • Extract features from GTFS data.
  • Partition geographic areas into smaller regions using methods such as H3 or Voronoi.
  • Create region embeddings from spatial features using supported algorithms and PyTorch models.
Before you choose

Requirements & limits

The public GitHub repository identifies the project as open source under the Apache-2.0 license.

  • The base installation covers most use cases, while additional capabilities require named optional dependency groups.
  • Available functionality includes OSM and Overture Maps acquisition, vector processing, GTFS feature extraction, regionalization and embedding.
  • The README describes the library as under heavy development and cautions that minor versions may introduce breaking changes.
  • Srai is a developer library for geospatial workflows, with examples and datasets for downstream tasks.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Srai and select workflow dependencies

Set up the Python package with optional dependency groups for the geospatial capabilities you need.

Before you start

  • Python environment capable of installing Python packages with pip.

Steps

  1. Install the base package with the command below.

    Documented command
    pip install srai

  2. Choose and install the documented optional dependencies for your workflow, such as srai[osm] for OpenStreetMap downloads, srai[gtfs] for GTFS processing, or srai[torch] for torch-based embedders.

Expected outcome

The Srai package and dependencies for most use cases are installed, with selected optional functionality enabled through extras.

Guide limitations

  • The base install covers dependencies required by most use cases, not every optional capability.
  • The project warns that minor versions may include breaking changes.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
7 October 2026
Original website title
kraina-ai/srai · Official homepage title · retained in its source language
How we review sourcesSuggest a correction