Saga Reader is an AI-powered, cross-platform internet reader designed for efficient information consumption and interactive discussion. It targets users seeking a lightweight, privacy-focused tool to discover, summarize, and engage with online content, offering a personalized and ad-free experience.

How It Works

The application leverages a Rust backend for efficient data retrieval via search and RSS, coupled with a SvelteKit frontend for a responsive UI. Its core innovation lies in the AI Immersive Reading Companion, enabling real-time discussions with AI about fetched content. It supports both cloud and local LLMs for summarization and interaction, with all user data stored locally for enhanced privacy.

Quick Start & Requirements

• Install: Clone the repository (git clone https://github.com/sopaco/saga-reader.git --recursive) and navigate into the directory.
• Dependencies: Requires Rust and Bun (recommended) or Node.js.
• Run: bun run dev (or pnpm run dev, npm run dev).
• Build: bun run build (or pnpm run build, npm run build).
• Documentation: Installation and LLM configuration details are available in the Help Document.

Highlighted Details

• Extremely lightweight with reported memory usage under 10MB.
• AI-driven content subscription based on user-defined keywords.
• Built with Rust, Tauri, and Svelte for cross-platform compatibility (Windows, Mac, Linux).
• Supports multilingual intelligent translation.

Maintenance & Community

The project is primarily maintained by a single developer with experience at Kuaishou. Contributions are welcomed via GitHub Issues for features like additional search providers or LLM integrations.

Licensing & Compatibility

Licensed under the MIT license, permitting commercial use and integration with closed-source projects.

Limitations & Caveats

The project is largely a solo effort, which may impact the pace of development and breadth of contributions. Specific LLM provider integrations beyond those initially supported would require community contributions.