# Anagnorisis

> Self-hosted local recommendation system that learns from your ratings and searches images, music, text, and video — all processed on your hardware.

- **Category:** AI Assistant
- **Licence:** AGPL-3.0
- **Latest version:** v0.4.0
- **Open source:** oss
- **Languages:** JavaScript, Python
- **Platforms:** Docker Compose
- **Tags:** Privacy, Data Management, Local Ai, Semantic Search, Music Player, Docker, Self Hosted, Self Hosting, File Management, Note Taking, Image Search, Data archiving, Information management, Image manager, Data hoarding, Data Hoarder, Note Taker, Personal Data, Recommendation System, Recommendation Engine, Multimodal Embeddings, GPU Accelerated, Music Recommendation

## Description

Anagnorisis is a local-first recommendation platform that runs entirely on your own machine or home server. You rate files (images, music, text, videos) on a 0–10 scale, and the system trains a personal evaluator model from those ratings to predict scores for unrated content. Search works in three modes: filename fuzzy matching, content-based semantic search via embeddings, and metadata-based search using EXIF/ID3 tags and optional .meta sidecar files that enable distributed semantic indexing without a central protocol. The core engine (anagnorisis_core) is a standalone Python package with a CLI (anag) so the same models and memory can be shared between the web UI, command line, and a lightweight data server for file sharing. Built-in modules cover Images, Music, Text, Videos, and a Train UI; experimental external modules add web and YouTube indexing. Deployment is via Docker Compose with NVIDIA GPU support (CUDA), AMD ROCm, or CPU-only fallback. The project recommends a recent NVIDIA GPU with at least 8 GB VRAM and 32 GB RAM for best performance, plus ~20–25 GB disk space for models and caches. All processing stays local — no data leaves your machine unless you explicitly share .meta files.

## Links

- [Homepage](https://github.com/volotat/Anagnorisis)
- [GitHub Repository](https://github.com/volotat/Anagnorisis)
- [Article: Part 3 - Why Should You Go Local?](https://volotat.github.io/p/anagnorisis-part-3-why-should-you-go-local/)
- [Article: Part 1 - Vision for Better Information Management](https://volotat.github.io/p/anagnorisis-part-1-a-vision-for-better-information-management/)
- [Article: Part 2 - Music Recommendation Algorithm](https://volotat.github.io/p/anagnorisis-part-2-the-music-recommendation-algorithm/)
- [Article: Part 4 - File Sharing is All We Need](https://volotat.github.io/p/anagnorisis-part-4-file-sharing-is-all-we-need/)
- [YouTube: Search Your Data Effectively (v0.3.1)](https://www.youtube.com/watch?v=X1Go7yYgFlY)
- [YouTube: Music Module Preview (v0.1.6)](https://www.youtube.com/watch?v=vux7mDaRCeY)
- [YouTube: Images Module Preview (v0.1.0)](https://www.youtube.com/watch?v=S70Lp0oL7aQ)

---
Source: https://selfhost.directory/project/anagnorisis