Logo
Deploy Now

SaaS Alternative

Google Photos

Categories

Self-Hosted Privacy AI Machine Learning Media Server Photo Management Face Recognition

Stars

8,044

Forks

384

Watchers

53

Developer links

Last Updated: 08-20-2026 11:21 AM (UTC)

LibrePhotos

With over 8,000 GitHub stars and continuous development since 2020, LibrePhotos delivers the core intelligence of Google Photos — face recognition, object detection, semantic search, and automatic album generation — entirely on your own hardware without sending a single photo to a third-party server. The Django 5 backend processes uploaded media through a machine learning pipeline that runs face detection via the face_recognition library, clusters identified faces using scikit-learn and HDBSCAN, generates image captions through BLIP and Moondream 2, and classifies scenes using Places365 or Google's SigLIP 2 vision-language model with zero-shot classification against 900+ real-world tags. Semantic search lets you find photos by natural language queries like "sunset at the beach" without manual tagging, while metadata search filters by person, camera, lens, file type, and filesystem path. The React 18 frontend built with Vite presents a timeline view, fullscreen lightbox with slideshow mode, photo detail sidebar showing location and people, and a folder navigation view with breadcrumb paths. RAW files from any camera are converted via ImageMagick, videos processed through FFmpeg, and Live Photos paired with their RAW+JPEG counterparts as unified entries. Public album sharing via link provides fine-grained privacy controls, and duplicate detection uses perceptual hashing to identify near-identical images. Deployment runs as a single unified Docker container or via Docker Compose with Kubernetes manifests also available. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

LibrePhotos
LibrePhotos
LibrePhotos
LibrePhotos
LibrePhotos

Benefits

  • AI Photo Search On-Premise
  • Semantic image search powered by BLIP captioning and SigLIP 2 vision-language models finds photos by natural language descriptions without manual tagging or cloud dependencies.
  • Automatic Face Recognition
  • Face detection and clustering via face_recognition, scikit-learn, and HDBSCAN automatically identifies and groups people across your entire photo library without manual sorting.
  • Complete Privacy by Design
  • Every photo, metadata record, and machine learning model runs entirely on your server with zero data transmitted to third parties, unlike Google Photos or iCloud alternatives.
  • Universal Format Support
  • Handles RAW files from any camera via ImageMagick, videos through FFmpeg, Live Photos as unified entries, and HEIC/HEIF formats with automatic thumbnail generation.

Features

  • Scene and Object Detection
  • Places365 and SigLIP 2 models classify scenes and objects in photos with 900+ tag vocabulary, enabling automatic categorization and search without manual organization.
  • Semantic Image Search
  • Natural language photo queries powered by BLIP and Moondream 2 captioning models find images by description like "dog in park" across your entire library.
  • Timeline and Album Views
  • Chronological timeline, automatic event-based albums like "Thursday in Berlin," folder navigation with breadcrumbs, and fullscreen lightbox with slideshow mode.
  • Reverse Geocoding Maps
  • Automatic location tagging via Nominatim, Mapbox, MapTiler, or OpenCage converts GPS coordinates from photo EXIF data into human-readable place names and map views.
  • Duplicate Detection
  • Perceptual hashing identifies near-identical images across your library, helping eliminate redundant copies while preserving the highest quality version of each photo.