Engram is a macOS application that turns OneNote notebooks — exported as opaque, unsearchable PDFs — into a searchable, interlinked Markdown vault for Obsidian. Built for people who take handwritten notes on an iPad, it transforms scattered ink on paper into a navigable second brain. Named after the neural engram, the physical trace a memory leaves behind, the project aims to give those traces a durable, structured home.
Engram — from ink to structure, from notes to memory.
Everything runs locally for privacy: an on-device vision language model (Qwen2.5-VL via mlx-vlm) reads handwriting, typed text, diagrams, and photos directly on your Mac. The pipeline parses each PDF, extracts pages, summarizes them with the local VLM, rolls up section overviews, writes the vault, and adds cross-links. The result is a dual structure: a folder hierarchy (Notebook → Section → Note) alongside a knowledge graph of automatically cross-linked concepts, with original pages preserved as embedded PDFs and illegible sections flagged to avoid hallucination. Incremental builds reprocess only changed or new notes.
Engram is an honest v0.1 prototype that prioritizes privacy, reliability, and reproducibility over polish.