A modern, AI-driven Markdown note-taking application, Lumina Note aims to be a "second brain" for users seeking to build a personal knowledge management system. It targets individuals who value local-first data, advanced features like bidirectional linking and knowledge graphs, and AI assistance for tasks such as summarization and semantic search. The primary benefit is a powerful, integrated environment for knowledge creation and organization.

How It Works

Lumina Note employs a robust Rust backend bridged to a React frontend via Tauri v2, enabling a performant, native desktop application experience. Its architecture prioritizes local data storage, ensuring user privacy and control. A key differentiator is its deep integration of AI capabilities, including an agent system that can automate complex tasks, RAG-based semantic search over local notes, and AI-powered PDF analysis, all designed to enhance the knowledge discovery and production workflow.

Quick Start & Requirements

• Installation: Clone the repository, install dependencies using npm install or pnpm install, and run in development with npm run tauri dev or build for production with npm run tauri build.
• Prerequisites: Node.js (18.0+), Rust (1.70+), npm or pnpm. For PDF element recognition, Python 3 with flask, flask-cors, and pymupdf is required. Advanced PDF analysis may need additional Python dependencies.
• Links: Official English README: ./README.en.md, Japanese README: ./README.ja.md, PP-Structure Setup: docs/PP_STRUCTURE_SETUP.md.

Highlighted Details

• AI Agent System: Features an AI assistant with intent recognition, task automation (read, edit, search), a floating ball interface, voice input, Diff previews, and RAG semantic search leveraging a local SQLite vector database.
• Knowledge Graph: A high-performance, canvas-based visualization engine displays bidirectional links, with folders as nodes and physics-based layout adjustments.
• PDF Smart Reader: Offers interactive element recognition (text, images, tables), annotation tools (highlighting, notes), AI summarization/translation of selected content, and bidirectional navigation between notes and PDF pages.
• Bilibili Video Notes: Allows in-app video playback, syncing notes with video timestamps via danmaku, and direct time-based navigation within the video.
• Dataview-style Databases: Supports creating and editing databases directly within note YAML frontmatter, with table and Kanban board views.

Maintenance & Community

The project was developed rapidly with AI assistance, suggesting a lean development team. Specific details on maintainers, community channels (like Discord/Slack), or formal contribution guidelines are not explicitly detailed in the provided README.

Licensing & Compatibility

The project is licensed under the Apache License 2.0. This license is generally permissive, allowing for commercial use and integration into closed-source projects.

Limitations & Caveats

The advanced PDF parsing and element recognition features rely on an external Python backend service, which requires separate installation and setup, adding complexity. Initial RAG indexing for semantic search may be slow, and performance is sensitive to the size of the user's note vault. The project roadmap indicates ongoing development with several features still planned or in progress.