ecwilsonaz

ecwilsonaz / plexsage

Public

Unofficial AI-powered Plex playlist generator with library awareness. Every track it suggests, you actually own.

claude gemini llm music openai
54
7
100% credibility
Found Feb 05, 2026 at 20 stars 3x -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

MediaSage is a self-hosted web app that generates personalized music playlists exclusively from a user's Plex library using AI models.

How It Works

1
🔍 Discover MediaSage

You find this handy tool that creates perfect music playlists using only the songs you own in Plex.

2
🚀 Set it up quickly

Run a simple command to get your personal playlist maker running on your computer or server.

3
🎵 Connect your music collection

Link it to your Plex server so it sees all your favorite albums and tracks.

4
🤖 Add a smart helper

Choose an AI service to understand your tastes and pick the best matches.

5
Describe your vibe or pick a song
💭
Mood description

Type what you're feeling and let it suggest matching eras and styles.

🎶
Favorite song

Choose a song and pick qualities like mood or energy to find more like it.

6
🎉 Generate your playlist

Watch as it filters your library, thinks creatively, and builds a full list of playable songs ready to enjoy.

✅ Save and play anywhere

Name your new playlist, save it to Plex, and listen instantly in your favorite app.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 20 to 54 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is plexsage?

PlexSage is a self-hosted Python web app that generates AI-powered music playlists from your Plex library, ensuring every suggested track is one you actually own. It solves the post-Tidal death of Plexamp's Sonic Sage by using a filter-first approach: you set genres, decades, ratings, or exclude live versions from your library cache, then LLMs like Gemini, Claude, GPT, or local Ollama pick from that pool only. Deploy via Docker in minutes, access at localhost:5765 with prompt or seed-track flows.

Why is it gaining traction?

Unlike generic AI tools or broken streaming integrations that suggest unowned tracks, PlexSage's local SQLite cache delivers instant filtering and full playlists every time, even for 50k+ libraries. Multi-LLM support with cost estimates and experimental local inference appeals to privacy-focused devs, while real-time previews show track counts and expenses before generating. Its Docker Compose setup for NAS like Synology/Unraid hooks self-hosters tired of cloud-only playlist generators.

Who should use this?

Plex users with ripped CD/vinyl collections needing smart discovery without Spotify/Tidal subs. Home lab enthusiasts running Ollama who want offline AI curation. Music nerds curating "90s alt for rainy days" moods or seed-track explorations like "more of this Radiohead vibe."

Verdict

Solid for Plex loyalists—excellent docs, one-command Docker, and thoughtful UX—but at 33 stars and 1.0% credibility, it's early alpha; test on non-prod libraries first. Worth starring if you match the use case.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.