feat: GraphML export (--graphml flag) for Gephi and yEd

Author: safishamsi

README.md

@@ -107,6 +107,7 @@ All commands are typed inside Claude Code:
 
 /graphify ./raw --html             # also export graph.html (browser, no Obsidian needed)
 /graphify ./raw --svg              # also export graph.svg (embeds in Notion, GitHub)
+/graphify ./raw --graphml          # also export graph.graphml (Gephi, yEd, any GraphML tool)
 /graphify ./raw --neo4j            # generate cypher.txt for Neo4j import
 /graphify ./raw --mcp              # start MCP stdio server for agent access
 ```
@@ -218,7 +219,7 @@ graphify/
 ├── cluster.py    Leiden community detection, cohesion scoring
 ├── analyze.py    god nodes, bridge nodes, surprising connections, suggested questions, graph diff
 ├── report.py     render GRAPH_REPORT.md
-├── export.py     Obsidian vault, graph.json, graph.html, graph.svg, Neo4j Cypher, Canvas
+├── export.py     Obsidian vault, graph.json, graph.html, graph.svg, graph.graphml, Neo4j Cypher, Canvas
 ├── ingest.py     fetch URLs (arXiv, Twitter/X, PDF, any webpage); save Q&A to .graphify/memory/
 ├── cache.py      SHA256-based per-file extraction cache; check_semantic_cache / save_semantic_cache
 ├── security.py   URL validation (http/https only), safe fetch with size cap, path guards, label sanitisation

graphify/export.py

@@ -1,4 +1,4 @@
-# write graph to HTML, JSON, SVG, Obsidian vault, and Neo4j Cypher
+# write graph to HTML, JSON, SVG, GraphML, Obsidian vault, and Neo4j Cypher
 from __future__ import annotations
 import json
 import math
@@ -586,6 +586,23 @@ def _safe_rel(relation: str) -> str:
     return {"nodes": nodes_pushed, "edges": edges_pushed}
 
 
+def to_graphml(
+    G: nx.Graph,
+    communities: dict[int, list[str]],
+    output_path: str,
+) -> None:
+    """Export graph as GraphML — opens in Gephi, yEd, and any GraphML-compatible tool.
+
+    Community IDs are written as a node attribute so Gephi can colour by community.
+    Edge confidence (EXTRACTED/INFERRED/AMBIGUOUS) is preserved as an edge attribute.
+    """
+    H = G.copy()
+    node_community = {n: cid for cid, nodes in communities.items() for n in nodes}
+    for node_id in H.nodes():
+        H.nodes[node_id]["community"] = node_community.get(node_id, -1)
+    nx.write_graphml(H, output_path)
+
+
 def to_svg(
     G: nx.Graph,
     communities: dict[int, list[str]],

tests/test_export.py

@@ -3,7 +3,7 @@
 from pathlib import Path
 from graphify.build import build_from_json
 from graphify.cluster import cluster
-from graphify.export import to_json, to_cypher
+from graphify.export import to_json, to_cypher, to_graphml
 
 FIXTURES = Path(__file__).parent / "fixtures"
 
@@ -52,3 +52,30 @@ def test_to_cypher_contains_merge_statements():
         to_cypher(G, str(out))
         content = out.read_text()
         assert "MERGE" in content
+
+def test_to_graphml_creates_file():
+    G = make_graph()
+    communities = cluster(G)
+    with tempfile.TemporaryDirectory() as tmp:
+        out = Path(tmp) / "graph.graphml"
+        to_graphml(G, communities, str(out))
+        assert out.exists()
+
+def test_to_graphml_valid_xml():
+    G = make_graph()
+    communities = cluster(G)
+    with tempfile.TemporaryDirectory() as tmp:
+        out = Path(tmp) / "graph.graphml"
+        to_graphml(G, communities, str(out))
+        content = out.read_text()
+        assert "<graphml" in content
+        assert "<node" in content
+
+def test_to_graphml_has_community_attribute():
+    G = make_graph()
+    communities = cluster(G)
+    with tempfile.TemporaryDirectory() as tmp:
+        out = Path(tmp) / "graph.graphml"
+        to_graphml(G, communities, str(out))
+        content = out.read_text()
+        assert "community" in content