From Obsidian Vault to AI-Powered Knowledge Graph in Minutes

Description and use

Combine your Obsidian vault with Chaos Cypher to automatically extract entities and relationships from Markdown, build an enriched graph, and enable semantic search and chat, while preserving manual links.

Problem

Obsidian vaults contain rich content but their graph view only shows manually typed links, missing many implicit relationships and entities.

Outcome

The vault becomes a searchable, chat‑ready knowledge graph that surfaces hidden connections while preserving manual links.

Workflow

• Zip a focused folder of at least ~10 notes, excluding private ones.
• Upload the ZIP/TAR.GZ via the archive loader; it strips frontmatter and preserves headings.
• Confirm detected domain; indexing creates embeddings for semantic search and RAG chat.
• Wait for extraction; the graph is built from prose.
• Explore AI‑discovered entities and relationships in the graph.
• Ask questions via RAG chat to get citations back to original notes.
• Optionally script the import with POST /api/v1/sources or CLI command chaoscypher source add my-vault.zip.

Evidence

Chaos Cypher adds the missing layer. It reads the Markdown itself, extracts entities and relationships with an LLM, and makes the whole vault searchable and chat-ready -- without requiring a single connection to be pre-linked.

Source

The steps above walk through the UI, but the same pipeline is reachable without opening a browser.

Source