SuggestArr
Effortlessly request recommended movies, TV shows and anime to Jellyseer/Overseer based on your recently watched content on Jellyfin, Plex or Emby—let SuggestAr
What is SuggestArr?
Effortlessly request recommended movies, TV shows and anime to Jellyseer/Overseer based on your recently watched content on Jellyfin, Plex or Emby—let SuggestArr handle it all automatically, keeping your library fresh with new and exciting content!
Overview of SuggestArr
What it is
SuggestArr is an open-source tool that automates media content recommendations and download requests based on user activity in media servers such as Jellyfin, Plex, and Emby. It retrieves recently watched content, searches for similar titles using the TMDb API, and sends automated download requests to Seer (Jellyseer/Overseer). The project is written in Python and can be run via Docker or directly.
Key features
- Supports Jellyfin, Plex, and Emby for retrieving media content.
- Integrates with TMDb to search for similar movies and TV shows.
- AI-powered recommendations (beta) using any OpenAI-compatible LLM (OpenAI, Ollama, Gemini, LiteLLM, etc.) to generate personalized suggestions based on watch history.
- AI Search (beta): describe in natural language what you want to watch and let the AI find matching titles.
- Trakt watch history integration: each user can link their own Trakt account to use recent watches as seeds and skip already-watched content.
- Automated requests to Seer, with per-job approval settings (always approve, always send automatically, or inherit global setting).
- Web interface for configuration, real-time logs, cron job management, and user selection.
- Content filtering to exclude requests for content already available on streaming platforms in your country.
- External database support (PostgreSQL, MySQL) in addition to SQLite.
Use cases
SuggestArr is designed for users who run a media server (Jellyfin, Plex, or Emby) and use Seer (Jellyseer/Overseer) for content requests. It automates the process of finding and requesting new content based on what users have recently watched, keeping the media library fresh without manual intervention. It is also useful for administrators who want to control request workflows, approve or reject suggestions, and manage per-user request visibility.
Getting started
See the repository README for detailed setup instructions. The project can be run using Docker Compose. An example configuration is provided in the README. Images are available from GitHub Container Registry as ghcr.io/giuseppe99barchetta/suggestarr:latest.
License and pricing
The project is licensed under MIT and is open source. No pricing information is stated.
Based on the project's public README and repository metadata.
