Edit Mind lets you index your videos including transcription, frame analysis, and multi-model embedding, and you can search your videos or specific video scenes using natural language. The project is designed to help you transcribe, analyze and index your personal video library to help you search for the exact part of the video you're looking for.

The core features include video indexing and processing through a background service that watches for new video files and queues them for AI-powered analysis. It provides AI-powered video analysis that extracts metadata like face recognition, transcription, object & text detection, scene analysis, and more. The system offers vector-based semantic search capabilities on video content using ChromaDB and provides dual interfaces accessible through a web app.

Edit Mind runs fully locally using local ML models and a local vector database, ensuring your videos never leave your computer or server with Docker support. The system uses AI for rich metadata extraction and semantic search, allowing users to search videos by spoken words, objects, faces, and other criteria.

The primary benefit is the ability to search through personal video libraries efficiently using natural language queries while maintaining complete privacy since everything runs locally. Use cases include finding specific moments in personal video collections, analyzing video content for specific objects or faces, and exporting relevant scenes based on semantic search results.

Edit Mind targets users who need to manage and search through personal video libraries while maintaining privacy. It integrates with Docker for containerization and supports multiple AI backends including Ollama, local models, and Google Gemini API. The technical stack includes pnpm workspaces, Docker, React Router V7, TypeScript, Vite, Node.js, Express.js, BullMQ, Python, OpenCV, PyTorch, OpenAI Whisper, ChromaDB, and PostgreSQL with Prisma ORM.