Recommendarr is a web application that generates personalized TV show and movie recommendations based on your Sonarr, Radarr, Plex, and Jellyfin libraries using AI.
- AI-Powered Recommendations: Get personalized TV show and movie suggestions based on your existing library.
- Sonarr & Radarr Integration: Connects directly to your media servers to analyze your TV and movie collections.
- Plex, Jellyfin, Tautulli & Trakt Integration: Analyzes your watch history for better recommendations.
- Flexible AI Support: Works with OpenAI, local models (Ollama/LM Studio), or any OpenAI-compatible API.
- Customization Options: Adjust recommendation count, model parameters, and more.
- Dark/Light Mode: Toggle between themes based on your preference.
- Poster Images: Displays media posters with fallback generation.
For a full list, see Features.
Before installing, ensure you have the necessary services and access. See the Prerequisites page on the wiki for details.
The simplest way to get started with Recommendarr:
# Pull and run with default port 3000
docker run -d \
--name recommendarr \
-p 3000:3000 \
-v recommendarr-data:/app/server/data \
tannermiddleton/recommendarr:latestThen visit http://localhost:3000 in your browser.
Default Login:
- Username:
admin - Password:
1234(Change immediately after first login!)
For other installation methods (Docker Compose, Build from Source, Manual), please see the Installation page on the wiki.
After installation, you'll need to connect your media services and set up an AI provider.
- Connecting Services: Connect Sonarr, Radarr, Plex, Jellyfin, Tautulli, Trakt.
- AI Service Setup: Configure OpenAI, Ollama, LM Studio, or other compatible services.
- Authentication Setup (Optional): Set up OAuth login with Google, GitHub, etc.
- Usage: Learn how to generate recommendations.
- Reverse Proxy Setup: Run Recommendarr securely behind Nginx, Traefik, etc.
- Environment Variables: Full list of configuration options.
Encountering issues? Check the Troubleshooting page on the wiki for common problems and solutions.
This project is licensed under the MIT License - see the LICENSE file for details.