π οΈ A modern, cross-platform application built on top of Rust, Tauri & Svelte.
πͺπ» Blazing-Fast and Extremely-Lightweight Internet Reader Client driven by AI.
π Help me develop this software better by sponsoring on GitHub
Saga Reader is an AI-driven think tank-style reader that automatically retrieves information from the internet based on user-specified topics and preferences. It uses cloud or local large models to summarize and provide guidance, and it includes an AI-driven interactive companion reading function, allowing you to discuss and exchange ideas with AI about the content you've read.
Saga Reader is completely free and open-source, meaning all data is securely stored on your own computer and is not controlled by third-party service providers. Additionally, you can manage your subscription keywords based on your interests and preferences without being disturbed by advertisements and commercialized content.
Download it from website!
The installation is straight forward, just follow the steps below:
Clone the repository.
git clone https://github.com/sopaco/saga-reader.git --recursive
Step into the cloned project folder.
cd saga-reader
Install Dependencies.
*Recommend bun, this is blazing fast.*
# **recommend, this is blazing fast**
bun install
# or use pnpm
# pnpm install
# or use npm
# npm install
Run
# **recommend, this is blazing fast**
bun run dev
# or use pnpm
# pnpm run dev
# or use npm
# npm run dev
Or build it directly
By default, it will build for the version of the system used by the machine you are compiling on. If you need to cross-compile, you can run the
build:macos
orbuild:windows
scripts in thepackage.json
. ```sh # recommend, this is blazing fast bun run build
# or use pnpm
# pnpm run build
# or use npm
# npm run build
```
We use a combination of Rust, Svelte (SvelteKit), Tauri, SeaORM, SqlLite, TailwindCSS throughout this monorepo.
intelligent
: Article optimization workflow module, providing abstractions for article optimization processes and prompt engineering optimizations.scrap
: Provides data scraping functionality, fetching internet information by calling mainstream search engines. This module is by default fully localized and does not rely on any third-party services.recorder
: Provides local storage functionality, where user interest prompts, raw articles, and post-processed optimized articles are saved on the user's personal computer storage.llm
: Provides internal LLM Provider abstractions and adapts to various cloud and local large model service implementations.ollama
: Operates local ollama, including running basic instances, model updates, and management functions.feed_api_rs
: The core capability API and implementation, based on the classic facade pattern.tauri-plugin-feed-api
: Core capability API for frontend calls via tauri commands.types
: Shared basic types module.+---------------------+ +---------------------+
| Frontend | | Backend |
| (Svelte/SvelteKit) |<--->| (Rust Modules) |
+---------------------+ +---------------------+
^ ^ ^ | | |
| | | | | |
+------+---+---+-------+ +------+---+---+-------+
| UI/UX Components | | tauri-plugin-feed-api|
| State Management | | feed_api_rs |
| Internationalization| | llm |
| Styling (Tailwind) | | ollama |
| Build Tools (Vite) | | recorder |
| | | scrap |
| | | types |
| | | intelligent |
+----------------------+ +-----------------------+
Help improve Saga Reader by reporting bugs or submitting feature requests through GitHub Issues.
Similarly, there are some features in wunderlist that need to be improved.
For Example
If you enjoy using this app, consider supporting its development by donating through GitHub Sponsors, Paypal, or Alipay.
MIT, A copy of the license is provided in the LICENSE file.
π Help me develop this software better by sponsoring on GitHub
An experienced internet veteran, having navigated through the waves of PC internet, mobile internet, and AI applications. Starting from an individual mobile application developer to a professional in the corporate world, I possess rich experience in product design and research and development. Currently, I am employed at Kuaishou, focusing on the R&D of universal front-end systems and AI exploration.
WeChat: dokhell
Email: dokhell@hotmail.com