Use Graphs in Graphify Cloud to explore code relationships within a repository or across your workspace.

​

Choose your scope

Expand Graphs in the sidebar:

• Single Repository focuses on one indexed codebase.
• Cross-Repository follows relationships that cross repository or service boundaries.

Choose the repository context you need before interpreting a node or connection. A missing connection can reflect the selected scope or the indexed source rather than the absence of a runtime dependency.

​

Structure and reusable patterns

Where enabled in Cloud, the existing Graphs page offers Structure, Graph, and Patterns. Existing graph links continue to open the detailed explorer.

• Structure shows declared package boundaries, directory groupings, repository dependencies, consumers, and declared external libraries. A directory grouping is not a declared architectural boundary.
• Graph keeps the detailed node and relationship explorer.
• Patterns shows resolved implementations and source-derived conventions from the indexed revision. Search for a component, utility, or static style token, then select View examples.

An Inferred convention needs at least three distinct production consumer files in a coherent scope. Tests, stories, generated code, and vendored dependencies do not count. Dynamic or unresolved evidence is omitted. Repetition is evidence of usage, not correctness or a universal preference. The evidence drawer shows sources, scope, indexed revision, coverage, and available snapshot/control history. Correct saves an attributed decision through Memory and ignores the inferred convention. Ignore this convention persists across reindexing; enable Include ignored conventions to restore it. These controls apply to repository guidance and require write access. Catalogs are optional. Older indexes and unsupported coverage remain usable in the Graph view. Opening this page does not trigger reindexing. Snapshot history starts with available catalogs; Graphify does not reconstruct earlier personal design choices.

​

Explore the map

Search for a node, inspect its neighbors, and use community filters to narrow the canvas. Node and edge totals help describe the current graph; provenance categories explain how its connections were obtained. The graph is useful for tracing a call path, finding dependent code, and identifying boundaries between services. Follow source references when you need to inspect the implementation behind a relationship.

​

Read provenance

Graphify distinguishes extracted relationships from inferred or ambiguous ones. Keep those labels visible when using graph context to assess a change. A traversable connection provides evidence to investigate; it is not a formal proof of application behavior. See Edges and provenance for the evidence labels and Formal verification for behavior comparisons.

​

Keep the graph current

The canvas reflects an indexed build. Check Repositories and Builds when recent code is missing. Wiki provides a written view of the same indexed repository, while MCP makes workspace context available to your coding assistant.