Hebbian Vault

Connects Claude to your Obsidian vault with search that learns from what you actually use. Exposes vault_search (BM25 + personalized PageRank + Hebbian usage scoring via RRF), vault_read for fetching notes with metadata, vault_neighbors for link traversal, and vault_hot to surface frequently accessed files. The Hebbian piece increments retrieval counts on every read, applies recency weighting, and decays stale files so your vault develops usage heatmaps over time. Works directly on the filesystem without Obsidian running. Tracking lives in a .hebbian sidecar directory by default, or inline in YAML frontmatter if you go Pro. Reach for this when keyword search alone misses the pages you keep coming back to, or when you want graph topology to influence ranking.