A lightweight, self-hosted EPUB reader designed for reading with AI
Read books one chapter at a time, copy-paste to your favorite LLM, and deepen your understanding
I'm starting to get into a habit of reading everything (blogs, articles, book chapters,…) with LLMs. Usually pass 1 is manual, then pass 2 "explain/summarize", pass 3 Q&A. I usually end up with a better/deeper understanding than if I moved on.
This project illustrates how you can easily read books together with LLMs. Get EPUB books (e.g. from Project Gutenberg), open them in this reader, copy-paste text to your favorite LLM, and read together.
Supported formats: EPUB and PDF
|
Organize your books with tags, track reading progress, and pick up where you left off.
|
|
|
Clean, distraction-free reading with powerful navigation.
|
|
Select text to highlight, add notes, and export everything.
|
|
|
Full-featured reading experience on any device.
|
|
The project uses uv.
# Process a book
uv run reader3.py your-book.epub
# Start the server
uv run server.pyVisit localhost:8123 to see your library.
| Command | Description |
|---|---|
make start |
Run the server (auto-installs deps if needed) |
make stop |
Stop the server |
make add_book BOOK=/path/to/book.epub |
Process a book locally |
Open the Library page and drag & drop your .epub or .pdf files to import.
| Shortcut | Action |
|---|---|
Cmd+Shift+P / Ctrl+Shift+P |
Toggle sidebar |
MIT
This project was 90% vibe coded to illustrate how one can very easily read books together with LLMs. Code is ephemeral now and libraries are over — ask your LLM to change it however you like.