G
Graphify-Labs/graphify
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.
在 GitHub 查看 ↗链接已于 2026-11-12 核查 · HTTP 200 · 打开的是厂商自己的官网
编辑判断
Live and reachable
- Maintained as of 2026-11-01 — 2 days ago, with 1650 open issues.
- The page this entry links to answered HTTP 200 at https://github.com/Graphify-Labs/graphify on 2026-11-02.
Checked 2026-11-02 · HTTP 200 · 491389 B · 37 KB 页面
数据来自我们对官网的实测，核对于 2026-11-02。
安装与配置
- 复制上面的命令
- 粘成
claude_desktop_config.json里mcpServers的一项（本地服务器用 command + args，示例见 客户端接法） - 重启客户端
客户端配置（取自该仓库的安装命令）
{
"mcpServers": {
"graphify-labs-graphify": {
"command": "uv",
"args": ["tool", "install", "graphifyy"]
}
}
}解析自我们于 2026-10-26 抓取的该仓库 README；我们未执行过。
command/args 来自仓库写明的安装命令；不确定时请以该项目 README 为准。
VS Code（.vscode/mcp.json —— 键名是 servers）
{
"servers": {
"graphify-labs-graphify": {
"command": "uv",
"args": ["tool", "install", "graphifyy"]
}
}
}VS Code 顶层键是 <code>servers</code>，其余与上面那份相同。
Claude Code（命令行）
claude mcp add --transport stdio graphify-labs-graphify -- uv tool install graphifyy
Claude Code 不收 JSON 文件，用这条命令直接加。
配置项的键名以你的客户端为准：客户端与 CLI
- ★ 数取值
- 147,212 ★ · Graphify-Labs/graphify · 取自 GitHub 搜索 API · （2026-11-13 20:00:50 核对）
- 来源明细
- 从该仓库的 GitHub 页面直接读取 · 条目类型：MCP 服务
- 收录与活跃
- 收录于 2026-10-26 · 最近见到 2026-11-14 · 共见到 21 次 · 被 1 个来源列出
- 安装
uv tool install graphifyy
常见问题（答案都来自我们的记录）
怎么安装？
该仓库给出的安装命令是
uv tool install graphifyy。我们的记录里它是仓库自己提供的；不保证在你的客户端上直接可用。它适合谁 / 用来做什么？
我们还没有为它记录标签。
谁维护它、还在更新吗？
仓库
Graphify-Labs/graphify；我们收录于 2026-10-26；最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。# graphify
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
A Claude Code skill. Type /graphify in Claude Code - it reads your files, builds a knowledge graph, and gives you back structure you didn't know was there.
Fully multimodal. Drop in code, PDFs, markdown, screenshots, diagrams, whiteboard photos, even images in other languages - graphify uses Claude vision to extract concepts and relationships from all of it and connects them into one graph.
> Andrej Karpathy keeps a /raw folder where he drops papers, tweets, screenshots, and notes. graphify is the answer to that problem - 71.5x fewer tokens per query vs reading the raw files, persistent across sessions, honest about what it found vs guessed.
/graphify . # works on any folder - your codebase, notes, papers, anything
graphify-out/
├── graph.html interactive graph - click nodes, search, filter by community
├── obsidian/ open as Obsidian vault
├── wiki/ Wikipedia-style articles for agent navigation (--wiki)
├── GRAPHREPORT.md god nodes, surprising connections, suggested questions
├── graph.json persistent graph - query weeks later without re-reading
└── cache/ SHA256 cache - re-runs only process changed files
## Install
Requires: Claude Code and Python 3.10+
bash
pip install graphifyy && graphify install
> The PyPI package is temporarily named graphifyy while the graphify name is being reclaimed. The CLI and skill command are still graphify.
> Windows: If graphify is not recognized after install, add the Python Scripts folder to your PATH: %APPDATA%\Python\Python3xx\Scripts (replace 3xx with your Python version, e.g. 313). Or use pipx install graphifyy which handles PATH automatically.
> macOS (externally managed): Use pipx install graphifyy if pip install fails with an "externally-managed-environment" error.
Then open Claude Code in any directory and type:
/graphify .
Manual install (curl)
bash
mkdir -p ~/.claude/skills/graphify
curl -fsSL https://raw.githubusercontent.com/safishamsi/graphify/v1/skills/graphify/skill.md \
> ~/.claude/skills/graphify/SKILL.md
Add to ~/.claude/CLAUDE.md:
graphify (~/.claude/skills/graphify/SKILL.md) - any input to knowledge graph. Trigger: /graphify
When the user types /graphify, invoke the Skill tool with skill: "graphify" before doing anything else.
## Usage
/graphify # run on current directory
/graphify ./raw # run on a specific folder
/graphify ./raw --mode deep # more aggressive INFERRED edge extraction
/graphify ./raw --update # re-extract only changed files, merge into existing graph
/graphify add https://arxiv.org/abs/1706.03762 # fetch a paper, save, update graph
/graphify add https://x.com/karpathy/status/... # fetch a tweet
/graphify query "what connects attention to the optimizer?"
/graphify path "DigestAuth" "Response"
/graphify explain "SwinTransformer"
/graphify ./raw --watch # auto-sync graph as files change (code: instant, docs: notifies you)
/graphify ./raw --wiki # build agent-crawlable wiki (index.md + article per community)
/graphify ./raw --svg # export graph.svg
/graphify ./raw --graphml # export graph.graphml (Gephi, yEd)
/graphify ./raw --neo4j # generate cypher.txt for Neo4j
/graphify ./raw --mcp # start MCP stdio server
graphify hook install # post-commit git hook - rebuilds graph on every commit automatically
Fully multimodal. Drop in code, PDFs, markdown, screenshots, diagrams, whiteboard photos, even images in other languages - graphify uses Claude vision to extract concepts and relationships from all of it and connects them into one graph.
> Andrej Karpathy keeps a /raw folder where he drops papers, tweets, screenshots, and notes. graphify is the answer to that problem - 71.5x fewer tokens per query vs reading the raw files, persistent across sessions, honest about what it found vs guessed.
/graphify . # works on any folder - your codebase, notes, papers, anything
graphify-out/
├── graph.html interactive graph - click nodes, search, filter by community
├── obsidian/ open as Obsidian vault
├── wiki/ Wikipedia-style articles for agent navigation (--wiki)
├── GRAPHREPORT.md god nodes, surprising connections, suggested questions
├── graph.json persistent graph - query weeks later without re-reading
└── cache/ SHA256 cache - re-runs only process changed files
## Install
Requires: Claude Code and Python 3.10+
bash
pip install graphifyy && graphify install
> The PyPI package is temporarily named graphifyy while the graphify name is being reclaimed. The CLI and skill command are still graphify.
> Windows: If graphify is not recognized after install, add the Python Scripts folder to your PATH: %APPDATA%\Python\Python3xx\Scripts (replace 3xx with your Python version, e.g. 313). Or use pipx install graphifyy which handles PATH automatically.
> macOS (externally managed): Use pipx install graphifyy if pip install fails with an "externally-managed-environment" error.
Then open Claude Code in any directory and type:
/graphify .
Manual install (curl)
bash
mkdir -p ~/.claude/skills/graphify
curl -fsSL https://raw.githubusercontent.com/safishamsi/graphify/v1/skills/graphify/skill.md \
> ~/.claude/skills/graphify/SKILL.md
Add to ~/.claude/CLAUDE.md:
graphify (~/.claude/skills/graphify/SKILL.md) - any input to knowledge graph. Trigger: /graphify
When the user types /graphify, invoke the Skill tool with skill: "graphify" before doing anything else.
## Usage
/graphify # run on current directory
/graphify ./raw # run on a specific folder
/graphify ./raw --mode deep # more aggressive INFERRED edge extraction
/graphify ./raw --update # re-extract only changed files, merge into existing graph
/graphify add https://arxiv.org/abs/1706.03762 # fetch a paper, save, update graph
/graphify add https://x.com/karpathy/status/... # fetch a tweet
/graphify query "what connects attention to the optimizer?"
/graphify path "DigestAuth" "Response"
/graphify explain "SwinTransformer"
/graphify ./raw --watch # auto-sync graph as files change (code: instant, docs: notifies you)
/graphify ./raw --wiki # build agent-crawlable wiki (index.md + article per community)
/graphify ./raw --svg # export graph.svg
/graphify ./raw --graphml # export graph.graphml (Gephi, yEd)
/graphify ./raw --neo4j # generate cypher.txt for Neo4j
/graphify ./raw --mcp # start MCP stdio server
graphify hook install # post-commit git hook - rebuilds graph on every commit automatically
收录徽章（可选）
想把收录标记放进 README 就复制这行，可选，不影响收录。
[](https://anclum.com/zh/s/graphify-labs-graphify/)
- 来源
- github · https://github.com/Graphify-Labs/graphify
- Traction
- 147,212 ★
- 收录于
- 今天