Graphify-Labs/graphify：README 來源編輯指南

Graphify-Labs/graphify 的 README 將專案描述為「Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.」。本文只整理倉庫可直接核對的內容，不把 star、Fork 或宣傳語當成品質證明。README 在「README」下寫到：🇺🇸 English | 🇨🇳 简体中文 | 🇯🇵 日本語 | 🇰🇷 한국어 | 🇩🇪 Deutsch | 🇫🇷 Français | 🇪🇸 Español | 🇮🇳 हिन्दी | 🇧🇷 Português | 🇷🇺 Русский | 🇸🇦 العربية | 🇮🇷 فارسی | 🇮🇹 Italiano | 🇵🇱 Polski | 🇳🇱 Nederlands | 🇹🇷 Türkçe | 🇺🇦。這說明的是專案邊界，不是已完成的生產驗證。

從 README 的「README」與相關條目，可以先判斷它是否處理你的實際問題：Every edge is explained. Each connection is tagged EXTRACTED (explicit in the source) or INFERRED (resolved by graphify), so you can tell what was read directly from what was inferred.。若需求不同，不應只因專案熱度就採用。本文保留原始專案名、命令與元件名，方便回到一手來源核對。 README 另外列出一項可核對的資訊：Code maps for free, fully local. Code is parsed with tree-sitter AST: deterministic, no LLM, nothing leaves your machine. (Docs, PDFs, images and video use your assistant's model, or a configured API key, for a semantic pass.)。這類原文條目可用來設計試跑步驟，但不能取代實際環境測試。

README 將運作方式分散在「README」等段落。可確認的線索包括：> Want this always-on, updating in the background across your code, docs, and meetings rather than only on demand? That is what we are building at graphify.com.。本文不把未寫出的架構、效能或安全邊界補成結論；真正的執行鏈仍要配合目錄、設定檔與版本標籤檢查。

第一次安裝應從 README 指出的入口開始。目前可核對的命令是： $ graphify explain "APIRouter" 如果倉庫沒有命令，本文不會自行編造步驟，而是建議先閱讀「What it does」，確認系統依賴、預設埠與首次初始化。

日常使用取決於專案文件。README 的「README」段落提到：Works in Claude Code, Cursor, Codex, Gemini CLI, GitHub Copilot, and 15+ more , pick your platform.。設定檔、環境變數、權限與資料目錄只在來源明確時才會記錄；沒有寫出的預設值，應在測試環境驗證並保留回滾副本。 同一部分也提到：Not a vector index. No embeddings, no vector store: a real graph you traverse. Ask a question, trace the path between two things, or explain one concept.。