Memory for AI harnesses that recalls a multi-graph, not a .md file or RAG chunks and a shrug.
-
Updated
Aug 1, 2026 - TypeScript
Memory for AI harnesses that recalls a multi-graph, not a .md file or RAG chunks and a shrug.
Graphnosis — local, encrypted, deterministic job memory layer where agents live and lend each other skills.
Graphnosis indexes your Obsidian vaults for better AI job memory cross-session for all AI clients.
Local-first encrypted storage + sync primitives extracted from Graphnosis App. Device-key derivation, encrypted append-only oplog, multi-graph query federation, sensitivity-tiered redaction.
Add a description, image, and links to the graphnosis topic page so that developers can more easily learn about it.
To associate your repository with the graphnosis topic, visit your repo's landing page and select "manage topics."