PaperStream Intelligence is an AI-powered academic paper discovery and management platform. It helps researchers find relevant papers from ArXiv, organize them into folders and reading lists, and discover curated lists from the community.
- Smart Discovery: Search for papers from ArXiv with AI-enhanced relevance scoring.
- Library Management: Save papers to your personal library and organize them into custom folders.
- Reading Lists: Create public or private reading lists to curate collections of papers.
- Community: Discover public reading lists created by other researchers.
- Sharing: Share your public reading lists with a simple link.
- Beautiful UI: A modern, dark-mode interface built with Tailwind CSS and Framer Motion.
- Framework: Next.js 15 (App Router)
- Language: TypeScript
- Styling: Tailwind CSS v4
- Animations: Framer Motion
- Database & Auth: Supabase
- Icons: Lucide React
- Node.js 18+ installed.
- A Supabase project.
Create a .env.local file in the root directory and add your Supabase credentials:
NEXT_PUBLIC_SUPABASE_URL=your_supabase_project_url
NEXT_PUBLIC_SUPABASE_ANON_KEY=your_supabase_anon_key-
Clone the repository:
git clone https://github.com/yourusername/paperstream.git cd paperstream -
Install dependencies:
npm install
-
Run the development server:
npm run dev
-
Open http://localhost:3000 with your browser to see the result.
The project uses Supabase Postgres. The core tables are:
user_profiles: Stores user information.papers: Caches paper metadata to avoid redundant ArXiv fetches.folders: For organizing saved papers.saved_papers: Links users, papers, and folders.reading_lists: Stores user-created lists (public/private).reading_list_papers: Links papers to reading lists.
Row Level Security (RLS) policies are used to ensure data privacy and secure sharing.
This project is licensed under the MIT License.