geo-sleuth

About geo-sleuth

geo-sleuth is an open-source agent skill that helps estimate where a photograph was taken. It combines image metadata, OCR, reverse image search, OpenStreetMap features, terrain elevation, satellite imagery, and street-view comparisons to investigate candidate locations. Python scripts search and rank evidence, while a compatible agent interprets the results and explains its reasoning.

The workflow records candidate locations and links conclusions to the commands and files that produced them. Reports can include coordinates, an error radius, camera direction, an evidence image, and a confidence grade. It runs through agents such as Claude Code, Codex, and Cursor rather than a standalone hosted app. Results depend on the photograph, available data, and the agent's decisions.