Graphify: Map a codebase and its docs into a graph you can query

What it does

Graphify reads a project and builds a knowledge graph: a map where each node is a concept and links show how things connect, such as which code calls or imports other code. The source says code is parsed locally with tree-sitter (a tool that reads code structure) with no AI model, and nothing leaves your machine. Docs, PDFs, images and video go through your assistant's model for a semantic pass. Each link is tagged EXTRACTED (stated in the source) or INFERRED (worked out by graphify), so you can see what was read directly.

How to use it

Input: a project folder with code and optional docs. Action: install it, then type /graphify in your AI coding assistant. Output: a persisted graph (the source says you get three files, including an interactive graph.html) that you can query. You can ask a plain-language question, trace the path between two things, or ask it to explain one concept.

Common use cases

• Ask a plain-language question about a codebase and get back the related part of the graph.
• Trace how two pieces of code connect instead of reading files one by one.
• Add docs, PDFs, images or video to the same graph as the code.