Back to browse
GitHub Repository

Local note engine that uses LLM to build and evolve a knowledge graph

10 starsTypeScript

Local note engine uses LLM to organize notes into a knowledge graph

by AlexWasHeree·May 24, 2026·11 points·4 comments

AI Analysis

MidShip ItSolve My Problem

Hierarchy emerges by subdivision, but Obsidian plugins already auto-tag and link notes.

Strengths
  • Three-stage pipeline separates classification from structural organization rather than simple tagging.
  • Human-in-the-loop proposals let users edit changes before committing them.
  • Obsidian vault integration avoids locking users into a proprietary format.
Weaknesses
  • README admits code smells and instability, requiring manual CLI configuration steps.
  • Crowded category where established tools like Mem and Obsidian plugins exist.
Category
Target Audience

Obsidian users, note-takers, personal knowledge management enthusiasts

Similar To

Obsidian Smart Connections · Mem.ai · Logseq

Post Description

i take a lot of notes but rarely find time to organize them so the value of most notes in my personal context quietly disappears.

Notecast is a local note engine i've been building to help me with that. it runs a three stage LLM pipeline (Classify -> Organize -> Consolidate) that automatically builds and maintain a knowledge graph from the notes. the theme hierarchy emerges by subdivision as notes accumulate. Any change generates a proposal that can be edited and commited by the user.

It is early stage and a lot of architectural and domain logic decisions might change but the core is working and is already useful.

It has Obsidian vault integration. I recommend using it (just set vaultPath on configurations)

I'm actively developing it this year and would love feedback.

Similar Projects

Productivity●●Solid

A note-taking app where notes connect themselves

Unnamed drafts and automatic resurfacing are the two gutsy choices here — start writing and the app tries to pull up related notes for you. It's a neat UX shortcut if the semantic matching is strong, but the landing page hides how recall is implemented (model, privacy, offline), and in a crowded space with Mem/Reflect clones that detail matters.

SlickSolve My Problem
yamatokaneko
103mo ago