Sovereign reading & writing — e‑Ink‑first.
Local‑first. Offline‑ready. Paperwork‑minimal. Works great on 480×800 portrait and 800×480 landscape.
Sample mode finishes with minimal tokens and still produces a valid EPUB.
Features
Textbook Builder
Generate EPUBs by grade, language, and topic. Pick Sample (fast) or Full (multi‑chapter).
Form Helper
Fill PDFs from simple YAML schemas. Auto‑fill with your local model; review and export.
Letter Explainer
Summarize letters and generate checklists. Offline‑ready, privacy‑first.
How it works
Your browser opens a local app at http://127.0.0.1:8000. That app talks to your on‑device LLM runtime (e.g., Ollama) on localhost. No cloud calls.
Install & run locally (macOS)
Ollama example — replace model as desired.
brew install ollama ollama serve ollama run llama3:8b
Clone & run BookDook (this repo):
git clone https://github.com/yosun/bookdook.git cd bookdook/BookDook python3 -m venv .venv source .venv/bin/activate pip install -r requirements.txt export PLAIN_BACKEND=ollama ./.venv/bin/python cli/serve_frontend.py
Open the app: http://127.0.0.1:8000/layout/page.html
CLI quickstart
./.venv/bin/python cli/build_textbook.py --grade 5 --lang en --topic "Fractions" --mode sample ./.venv/bin/python cli/build_textbook.py --grade 5 --lang en --topic "Fractions" --mode full
FAQ
Can the hosted site use my local LLM directly? Not reliably. Open the local app above; it talks to your model securely on localhost.