PlexMind
ghcr.io/finechainesium/plexmind:latest
https://github.com/FineChAInesium/PlexMind/pkgs/container/plexmind
bridge
bash
false
https://github.com/FineChAInesium/PlexMind/issues
https://github.com/FineChAInesium/PlexMind
AI-powered Plex recommendations using a fully local LLM (Ollama). Analyzes each user's watch history and generates personalized movie/TV picks — no cloud, no API costs, no data leaving your server.
Also includes: Whisper ASR subtitle generation, Ollama-powered subtitle translation, and library maintenance tools.
Requires: Ollama container running with a model pulled (recommended: qwen3.5:9b for 12GB VRAM, gemma3:4b for 8GB).
Web dashboard at http://[IP]:[PORT:8000]/
MediaApp:Other Tools:
http://[IP]:[PORT:8000]/
https://raw.githubusercontent.com/nwithan8/unraid_templates/main/templates/plexmind.xml
https://raw.githubusercontent.com/FineChAInesium/PlexMind/main/templates/icon.png
--gpus all --group-add 281
PlexMind generates personalized Plex recommendations using a local LLM. See the full README at https://github.com/FineChAInesium/PlexMind for setup instructions and configuration options.
bridge
8000
8000
tcp
/mnt/user/appdata/plexmind/data
/app/data
rw
/var/run/docker.sock
/var/run/docker.sock
rw
http://192.168.1.10:32400
PLEX_URL
Your Plex Media Server URL (use LAN IP)
PLEX_TOKEN
Your Plex authentication token — find it at plex.tv/claim or in Plex web app preferences URL
http://192.168.1.10:11434
OLLAMA_URL
Ollama API URL — use LAN IP of the host running Ollama, not localhost
qwen3.5:9b
OLLAMA_MODEL
Ollama model name (must be pulled first: docker exec ollama ollama pull qwen3.5:9b)
TMDB_API_KEY
Optional — enriches recommendations with ratings and posters. Free at themoviedb.org/settings/api
PLEXMIND_API_KEY
STRONGLY RECOMMENDED — Protects all API endpoints. Generate a key with: openssl rand -hex 32 and paste it here. If left blank, all endpoints are open to anyone on your network (a WARNING is logged at every startup). If set, add ?api_key=YOUR_KEY to your Plex webhook URL.
10
MAX_RECOMMENDATIONS
Number of recommendations to generate per user
60
SUPPRESSION_DAYS
Days before a recommendation can reappear
America/New_York
TZ
Timezone for the scheduled monthly batch run
plexmind-whisper
WHISPER_CONTAINER_NAME
Docker container to start before transcription and stop when transcription exits
plexmind-ollama
OLLAMA_CONTAINER_NAME
Docker container to start before translation and stop when translation exits
1
START_SIDECAR_CONTAINERS
Set to 1 to start Whisper/Ollama sidecars before script jobs
1
STOP_SIDECAR_CONTAINERS
Set to 1 to stop Whisper/Ollama sidecars when script jobs exit