Export Graph

Export the complete knowledge graph from .code-graph/graph.db to a readable JSON file.

Prerequisites

• Graph must be built first: run /graph-build if .code-graph/graph.db doesn't exist
• Requires Python 3.10+ with tree-sitter, tree-sitter-language-pack, networkx

Steps

1. Export graph — Run via Bash:

   python .claude/scripts/code_graph export --json
   

   Default output: .code-graph/graph-export.json

2. Export specific files only (optional):

   python .claude/scripts/code_graph export --files src/auth.py src/api.py --json
   

   This exports only nodes and edges belonging to the specified files.

3. Custom output path (optional):

   python .claude/scripts/code_graph export -o custom-path.json --json
   

4. Report results: File path, node count, edge count, file size.

Output Format

{
  "version": "1.8.4-easyclaude",
  "stats": { "total_nodes": N, "total_edges": N, "files_count": N, "languages": [...] },
  "nodes": [
    { "kind": "Function", "name": "login", "qualified_name": "auth.py::login", "file_path": "...", "line_start": 10, "line_end": 25, "language": "python" }
  ],
  "edges": [
    { "kind": "CALLS", "source": "api.py::handler", "target": "auth.py::login", "file_path": "...", "line": 15 }
  ]
}

Implicit Edges in Export

The exported JSON includes ALL edge types, including implicit connections:

• MESSAGE_BUS — cross-service bus message producer-to-consumer links
• TRIGGERS_EVENT — entity CRUD to event handler links
• PRODUCES_EVENT — event handler to bus producer links
• TRIGGERS_COMMAND_EVENT — command to command event handler links
• API_ENDPOINT — frontend HTTP call to backend route links

These edges are created by the implicit connector and API connector during build/sync.

Use Cases

• Inspect graph contents for debugging
• Feed into external analysis tools
• Verify graph correctness after build
• Share graph snapshot with team members