Glossary
Knowledge graphs for AI coding assistants
The vocabulary of code knowledge graphs, defined in plain English. If you want the full picture of how these pieces fit together, read how Graphify works; if you want to know where a graph actually earns its keep day to day, see the use cases.
Knowledge graphA data structure that stores entities and typed relationships between them, so software can follow how things connect instead of searching flat text.Code graphA knowledge graph built from a codebase: functions, classes, config, and docs become nodes; calls, imports, and references become edges.NodeA single entity in the graph — a function, class, file, table, or doc page — carrying attributes like name, path, and kind.EdgeA typed, directed relationship between two nodes — calls, imports, defines, references — each carrying a provenance tag.Community (cluster)A group of nodes densely connected to each other and only loosely connected to the rest of the graph — usually a real subsystem like auth or billing.God nodeA node with a disproportionate number of edges — the module everything imports — where changes carry the most risk.Confidence tagsGraphify's provenance labels — EXTRACTED, INFERRED, AMBIGUOUS — attached to every edge so you always know what was found versus what was guessed.MCP serverA server implementing the Model Context Protocol — the open standard that lets AI assistants call external tools, like a code graph.RAG (retrieval-augmented generation)A pipeline that chunks documents, embeds them as vectors, and retrieves the most similar chunks at query time — lookup by resemblance, not structure.Vector embeddingA list of numbers representing the meaning of a piece of text, used to measure similarity — answers 'what looks like this?', not 'what calls this?'Tree-sitter / ASTAn AST is the parsed structure of source code; tree-sitter is the open-source parser library Graphify runs entirely locally to extract it.Token reductionThe context-window savings from answering with graph structure instead of pasting whole files into an assistant's context.Traversal / hopFollowing edges from node to node — one hop is a single edge, a traversal is a path of them. How graphs answer multi-step questions.Blast radiusEverything transitively affected by a change — the callers of a function, their callers, and the configs and tests that reference them.
Graphify is open source (MIT) and free — see pricing for the honest breakdown, or go deeper on the mechanics in concepts.