graphify
MCP ServerGraphify-Labs/graphify
Graphify maps entire project codebases, documentation, and media into an interactive local knowledge graph, enabling AI assistants to query the graph instead of grepping raw files.
105.6k 10.3kApache-2.0Updated 2026-08-12
87
GreatOverview
The Graphify skill utilizes tree-sitter AST parsing to construct a deterministic, local-first knowledge graph of software repositories without consuming LLM API tokens for code. It outputs an interactive HTML visualization, structured reports, and a queryable JSON graph that helps AI coding assistants instantly comprehend architecture, community structures, and code relationships.
Capabilities
- ▸Local AST-based code parsing across roughly 40 programming languages
- ▸Automatic detection of god nodes and software subsystems
- ▸Relationship extraction with explicit confidence tags for explicit vs inferred links
- ▸Generation of interactive graph visualizations and summary reports
- ▸Path tracing and concept explanation via CLI commands
Best for
Answering complex architectural or codebase queries by referencing the knowledge graph instead of reading raw files, Mapping code, documentation, PDFs, images, and videos into a unified relationship network, Tracing dependencies, inheritance, and connection paths between distinct modules or concepts
Works with
Claude CodeCodexChatGPTGemini CLICursorGitHub CopilotOpenCode
Evoa Score breakdown= Σ (score × weight)
87Task usefulness20%88 → +17.6
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%95 → +14.3
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%100 → +15.0
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%48 → +5.8
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%80 → +12.0
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%90 → +9.0
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%100 → +8.0
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%100 → +5.0
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total86.6 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Code parsing is performed locally via tree-sitter without transmitting source code externally. Optional semantic passes over documents or media may send data to configured backend models or APIs.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.