github Python analyzed 050c65a

cognis-digital/locateanything

github

Infer where a photo was taken using a local uncensored vision + reasoning model (OSINT/geoint, 100% local)

maintainer
cognis-digital
licence
NOASSERTION
first seen
2026-06-08
last seen
2026-06-30
releases · 30d
0
short id

Drift inferred · capture-to-capture

No drift recorded — single capability capture; advisories appear once its surface changes.

capabilities 0 tools
transport stdio counts 0 tools · 0 res · 0 prompts permission surface via code analysis

No tools enumerated yet for this server.

code evidence vHEAD · github-tarball
evidence-backed findings quoted directly from the published source artifact — not inferred

code files: 15

filesystem 3

  • fs cognis-digital-locateanything-050c65a/locateanything/connect.py :76 text = sys.stdin.read() if a.input == "-" else open(a.input, encoding="utf-8").read()
  • fs cognis-digital-locateanything-050c65a/locateanything/core.py :22 img = Image.open(path); exif = img._getexif() or {}
  • fs (weak) cognis-digital-locateanything-050c65a/scripts/make_demo_images.py :14 from pathlib import Path

network 3

  • net cognis-digital-locateanything-050c65a/integrations/webhook.py :8 import argparse, json, sys, urllib.request
  • net cognis-digital-locateanything-050c65a/livesearch.py :28 import urllib.parse
  • net cognis-digital-locateanything-050c65a/locateanything/core.py :7 import base64, json, os, urllib.request

declared dependencies 4

  • mcp@>=1.0
  • cognis-connect@@ git+https://github.com/cognis-digital/cognis-connect.git
  • Pillow@>=10
  • pytest@>=8.0