GeoINT

GeoINT is an agent skill for finding the exact location of photos, screenshots, videos, or Street View images.

GeoInt is an agent skill designed to find where any photo, screenshot, video frame, or Street View image was taken. It functions like an OSINT investigation combined with a GeoGuessr player, evaluating the scene through an initial assessment and then verifying it with web research and local tools down to the street level. The system uses local models like StreetCLIP, GeoCLIP, OWLv2, and GeoCalib, alongside tools for optical character recognition, metadata extraction, and panoramic analysis. Every photo generates a timestamped archive containing a report, evidence images, and a scoreboard. The software is built for investigators, researchers, and technical users requiring automated geographic verification.

GeoINT at a glance

Best for: Researcher
Runs on: CLI, self-hosted, open source
Pricing: Free
Released: October 2026
Category: AI agent tool
Website: github.com/marouane53/geoint

Key features

Analyze scenes using local models and automated tools
Extract metadata, text, and objects from images
Run automated web and reverse image searches
Examine panoramic views and street-level imagery
Query open-data portals and OpenStreetMap data
Calculate camera calibration and sun positioning
Maintain timestamped archives with reports and scoreboards

Use it for

Find the location of unverified photos or video frames
Investigate screenshots and images for OSINT projects
Perform automated street-level geographic reconnaissance

Alternatives to GeoINT

Geo Sleuth — It uses geometry, elevation data, and open street maps to locate photos without metadata.
BrowserOS — Runs entirely locally and lets AI agents use real user logins to complete tasks.
Agent Reach — Provides zero API fees, multi-backend routing, and local credential storage.
OpenGCUA — Lets models decide how to observe, act, and organize work dynamically.
AgenticSeek — It runs entirely on a local machine without cloud dependency or API costs.
OWL — Ranks first among open-source frameworks on the GAIA benchmark with a score of 69.09.

All GeoINT alternatives