GeoAgent: A QGIS Plugin for Natural Language-Driven Geospatial Analysis
2026-09-02 , Phoenix Hall

GeoAgent is a QGIS plugin that integrates large language models to enable natural language interaction with geospatial data. It allows users to explore layers, perform spatial analysis, and automate geoprocessing workflows through conversational commands, improving accessibility and efficiency in GIS tasks.


GeoAgent is an open-source QGIS plugin that enables users to perform geospatial analysis through natural language commands, powered by large language models (LLMs). The plugin supports multiple LLM backends (Ollama for local inference, OpenAI, and Google Gemini for cloud services) and operates in two modes: General mode for data exploration and querying attributes, and Processing mode for automated geoprocessing workflows. By abstracting traditional GIS complexity through conversational interaction, GeoAgent lowers barriers to advanced geospatial analysis for non-specialist users while maintaining transparency through detailed chat transcripts and automatic result visualization in QGIS.


Level of technical complexity: 2 - intermediate Give indication of resources (video, web pages, papers, etc.) to read in advance, that will help get up to speed on advanced topics.:
  1. Code and Documentation: https://github.com/iamtekson/GeoAgent
  2. GeoAgent Basic (Youtube Video Tutorial): https://youtu.be/sJ_Lgbia4CM?si=WDmUFEEcKEt_BOFn
Indicate what is (are) the open source project(s) essential in your talk:
  1. QGIS
  2. GeoAgent Plugin
I make my conference contribution available under the CC BY 4.0 license. The conference contribution comprises the abstract, the text contribution for the conference proceedings, the presentation materials as well as the video recording and live transmission of the presentation:

Tek Kshetri is a passionate Geospatial expert with over six years of hands-on experience in the field. He is a strong advocate for open source, open standards, and open solutions.

His primary research interests lie in Artificial Intelligence and the Geospatial domain intersection, including natural disaster modelling, Web GIS, and satellite imagery analysis using Machine Learning and Deep Learning. Tek has developed several open-source packages such as GeoAgent, geoserver-rest, GeoTile, pySLD, leaflet-geoserver-request, etc. He also shares his knowledge and insights through his YouTube channel, GeoDev.

Geomatics Engineer and Cartographer by degree
Open source GIS enthusiast and Member, OSGeo Nepal
OpenStreetMap contributor since 2016