Knowledge Graph
Your knowledge connects itself. No manual linking.
The Auto-Linking Engine discovers and builds connections between your notes automatically, using three parallel strategies. Five graph renderers let you navigate your knowledge visually — from a domain overview to an individual note.
The Problem
Notes exist in silos. You wrote something about 'machine learning' in January and something about 'neural networks' in March — but there's no automatic connection between them, or between every note mentioning a specific person across 3 years.
The Solution
The Auto-Linking Engine (ALE) runs 3 parallel strategies: entity overlap (cosine-similarity KnowledgeNode matching), semantic similarity (pgvector ≥0.65 cosine distance), and temporal proximity (±7 days with shared content). 12 entity types extracted via LLM. 5 graph renderers: WebGPU-accelerated, Three.js 3D, Sigma.js, Cytoscape.js, BillionScale.
Key benefits
Connections build automatically — no manual linking ever required
12 entity types extracted: people, companies, places, events, concepts, technologies, and more
WebGPU-accelerated renderer handles graphs at any scale without performance loss
Three.js 3D mode: navigate your knowledge spatially in a three-dimensional space
Entity graph: find every note mentioning a specific person or concept in one click
4 zoom levels: from knowledge domain clusters to individual notes
Technical Depth
ALE runs asynchronously after capture. Entity extraction uses LLM-based NER (12 types). Semantic similarity computed with paraphrase-multilingual-MiniLM-L12-v2 (384-dim), stored in pgvector. Graph clustering uses Louvain community detection at 4 granularity levels.