graphify

To build a knowledge graph from a folder of mixed files, you process the directory to parse code, docs, papers, and images, clustering concepts into communities. This creates a persistent graph with cross-document relationships stored locally.

Yes, you can merge knowledge graphs across multiple repository folders using cross-document discovery and merging. This supports cross-repo graphs and optional agent-driven semantic extraction to connect concepts across distinct codebases.

Converting files into a navigable knowledge graph generates three outputs: an interactive HTML visualization, GraphRAG-ready JSON for retrieval pipelines, and a plain-language GRAPH_REPORT.md for human-readable summaries.

Yes, the knowledge graph persists across multiple analysis sessions through persistent cross-session storage in a graphify-out directory. This preserves all discovered and inferred relationships across subsequent runs.

Community detection in a knowledge graph organizes related concepts into clustered groups based on their connections. This groups related code, documents, and papers together, making the navigable graph easier to analyze.