Skip to content
iamteksonPublic

About

Plugin for QGIS interaction using LLM. Enables geospatial analysis and data processing through natural language commands.

Topics

Resources

Stars

46 stars

Watchers

2 watching

Forks

Repository files navigation

GeoAgent

GeoAgent Logo

GeoAgent is a QGIS plugin for geospatial analysis in plain language. Ask it to load data, explore your layers, or run a chain of processing steps: it picks the QGIS algorithms, fills in their parameters, runs them, and adds the results to your map.

Documentation · Install from the QGIS Plugin Repository · Report an issue

GeoAgent Plugin Interface

Features

  • Explore and manage data (General mode) — add layers from files or URLs, list layers and columns, select features by attribute or geometry, create and save projects.
  • Geoprocessing in plain language (Processing mode) — any algorithm in the Processing Toolbox (native, GDAL, GRASS, ...), alone or as a multi-step chain where each result feeds the next.
  • Turn a run into a QGIS model — open it in the Model Designer, or save it as a .model3 file to re-run on other data.
  • Your choice of LLM — Ollama (local and free), OpenAI, Google Gemini, or Anthropic Claude.
  • See what happened — every step, the parameters used, and the tokens each request cost, in the Logs tab.

Quick start

  1. Install GeoAgent from Plugins ▸ Manage and Install Plugins.

  2. In the GeoAgent panel's Settings tab, click Check / Install Dependencies.

  3. Choose a provider: Ollama runs locally for free; OpenAI, Gemini and Anthropic need an API key. Click Save Settings. See LLM providers.

  4. Switch to Processing mode and describe your analysis:

    Buffer the rivers by 500 m, clip the DEM with the buffer and compute the slope of the clipped DEM
    

The quickstart walks through this example with the demo data.

Documentation

  • Getting started — installation, LLM providers, quickstart
  • User guide — General and Processing modes, model export, settings, logs and token usage, troubleshooting
  • Developer guide — architecture, tests, contributing

Contributing

Contributions are welcome — fork, create a feature branch, and open a pull request. The contributing guide covers the development setup, the tests, and building the docs. For bugs, open an issue with your QGIS version, plugin version, and steps to reproduce.

License & credits

MIT License — see LICENSE. GeoAgent's own code is MIT-licensed; when it runs inside QGIS (GPL v2+, with PyQt under GPL v3), the combined work is governed by those licenses' terms, as with any QGIS plugin.

Authors: Tek Kshetri, Rabin Ojha

Related projects that inspired this work: QChatGPT, GeoAI, QGIS MCP. Thanks to the QGIS, LangChain, and open-source GIS communities.

Citation

If you use GeoAgent in your research, please cite the preprint:

Kshetri, T. B., & Ojha, R. (2026). GeoAgent: An Agent-Based QGIS Plugin for Natural-Language-Driven Geospatial Analysis with Multi-Backend Large Language Model Support. EarthArXiv. https://doi.org/10.31223/X53803

@misc{kshetri2026geoagent,
  title     = {GeoAgent: An Agent-Based QGIS Plugin for Natural-Language-Driven
               Geospatial Analysis with Multi-Backend Large Language Model Support},
  author    = {Kshetri, Tek Bahadur and Ojha, Rabin},
  year      = {2026},
  publisher = {EarthArXiv},
  doi       = {10.31223/X53803},
  url       = {https://doi.org/10.31223/X53803}
}

About

Plugin for QGIS interaction using LLM. Enables geospatial analysis and data processing through natural language commands.

Topics

Resources

Stars

46 stars

Watchers

2 watching

Forks

Releases

Packages

Contributors

Languages