What problem does it solve? Understanding a large mixed corpus — a new codebase, a reading list of papers, or a personal notes folder — requires reading everything manually, and connections across documents stay hidden. graphify turns any folder into a persistent, queryable knowledge graph with community detection and an honest audit trail showing which relationships were extracted versus inferred. ## Core Features & Use Cases - Knowledge graph extraction: Combines deterministic AST parsing for code with parallel LLM subagents for docs, papers, and images, tagging every edge as EXTRACTED, INFERRED, or AMBIGUOUS with confidence scores. - Clustering and analysis: Detects communities, identifies god nodes and surprising cross-document connections, and generates a plain-language GRAPH_REPORT.md plus GraphRAG-ready graph.json. - Multiple export targets: Produces interactive HTML, Obsidian vaults with canvas, SVG, GraphML, Neo4j Cypher/push, and an MCP server for live agent queries. - Use Case: Point it at an unfamiliar repository to get a labeled community map of its architecture, then run /graphify query or /graphify path to explore how modules connect before touching any code. ## Quick Start Run /graphify on the current directory to build a knowledge graph and open the generated graph.html report.
