graphify
starsforks
How to install graphify?
graphify-labs/graphify
$git clone https://github.com/Graphify-Labs/graphifyA 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.
README.md
| 1 | # graphify |
| 2 | |
| 3 | [](https://github.com/safishamsi/graphify/actions/workflows/ci.yml) |
| 4 | |
| 5 | **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. |
| 6 | |
| 7 | 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. |
| 8 | |
| 9 | > 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. |
| 10 | |
| 11 | ``` |
| 12 | /graphify . # works on any folder - your codebase, notes, papers, anything |
| 13 | ``` |
| 14 | |
| 15 | ``` |
| 16 | graphify-out/ |
| 17 | ├── graph.html interactive graph - click nodes, search, filter by community |
| 18 | ├── obsidian/ open as Obsidian vault |
| 19 | ├── wiki/ Wikipedia-style articles for agent navigation (--wiki) |
| 20 | ├── GRAPH_REPORT.md god nodes, surprising connections, suggested questions |
| 21 | ├── graph.json persistent graph - query weeks later without re-reading |
| 22 | └── cache/ SHA256 cache - re-runs only process changed files |
| 23 | ``` |
| 24 | |
| 25 | ## Install |
| 26 | |
| 27 | **Requires:** [Claude Code](https://claude.ai/code) and Python 3.10+ |
| 28 | |
| 29 | ```bash |
| 30 | pip install graphifyy && graphify install |
| 31 | ``` |
| 32 | |
| 33 | > The PyPI package is temporarily named `graphifyy` while the `graphify` name is being reclaimed. The CLI and skill command are still `graphify`. |
| 34 | |
| 35 | > **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. |
| 36 | > **macOS (externally managed):** Use `pipx install graphifyy` if `pip install` fails with an "externally-managed-environment" error. |
| 37 | |
| 38 | Then open Claude Code in any directory and type: |
| 39 | |
| 40 | ``` |
| 41 | /graphify . |
| 42 | ``` |
| 43 | |
| 44 | <details> |
| 45 | <summary>Manual install (curl)</summary> |
| 46 | |
| 47 | ```bash |
| 48 | mkdir -p ~/.claude/skills/graphify |
| 49 | curl -fsSL https://raw.githubusercontent.com/safishamsi/graphify/v1/skills/graphify/skill.md \ |
| 50 | > ~/.claude/skills/graphify/SKILL.md |
| 51 | ``` |
| 52 | |
| 53 | Add to `~/.claude/CLAUDE.md`: |
| 54 | |
| 55 | ``` |
| 56 | - **graphify** (`~/.claude/skills/graphify/SKILL.md`) - any input to knowledge graph. Trigger: `/graphify` |
| 57 | When the user types `/graphify`, invoke the Skill tool with `skill: "graphify"` before doing anything else. |
| 58 | ``` |
| 59 | |
| 60 | </details> |
| 61 | |
| 62 | ## Usage |
| 63 | |
| 64 | ``` |
| 65 | /graphify # run on current directory |
| 66 | /graphify ./raw # run on a specific folder |
| 67 | /graphify ./raw --mode deep # more aggressive INFERRED edge extraction |
| 68 | /graphify ./raw --update # re-extract only changed files, merge into existing graph |
| 69 | |
| 70 | /graphify add https://arxiv.org/abs/1706.03762 # fetch a paper, save, update graph |
| 71 | /graphify add https://x.com/karpathy/status/... # fetch a tweet |
| 72 | |
| 73 | /graphify query "what connects attention to the optimizer?" |
| 74 | /graphify path "DigestAuth" "Response" |
| 75 | /graphify explain "SwinTransformer" |
| 76 | |
| 77 | /graphify ./raw --watch # auto-sync graph as files change (code: instant, docs: notifies you) |
| 78 | /graphify ./raw --wiki # build agent-crawlable wiki (index.md + article per community) |
| 79 | /graphify ./raw --svg # export graph.svg |
| 80 | /graphify ./raw --graphml # export graph.graphml (Gephi, yEd) |
| 81 | /graphify ./raw --neo4j # generate cypher.txt for Neo4j |
| 82 | /graphify ./raw --mcp # start MCP stdio server |
| 83 | |
| 84 | graphify hook install # post-commit git hook - rebuilds graph on every commit automatically |
| 85 | ``` |
| 86 | |
| 87 | Works with any mix of file types: |
| 88 | |
| 89 | | Type | Extensions | Extraction | |
| 90 | |------|-----------|------------| |
| 91 | | Code | `.py .ts .js .go .rs .java .c .cpp .rb .cs .kt .scala .php` | AST via |
People who liked this also viewed
6 picksType
- firecrawl-mcp-server🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.MCP ServersJul 2026
- sembleFast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+readMCP ServersJul 2026
- duckduckgo-mcp-serverA Model Context Protocol (MCP) server that provides web search capabilities through DuckDuckGo, with additional features for content fetching and parsing.MCP ServersJul 2026
- wikipedia-mcpA Model Context Protocol (MCP) server that retrieves information from Wikipedia to provide context to LLMs.MCP ServersMay 2026
- arxiv-mcp-serverA Model Context Protocol server for searching and analyzing arXiv papersMCP ServersJul 2026
- mcp-searxngPrivate web search for AI assistants via SearXNG — supports Claude, Cursor, and any MCP clientMCP ServersJul 2026
