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.

★ 148,296⑂ 14,225👁 426⑃ 2,806● 2,281▤ 256
PythonApache-2.0Created 2026-04-03www.graphify.com
Download: graphify 0.9.110graphify-0.9.110 ↓0.9.1102026-11-15
+643
Daily
+3,615
Weekly
148,296
stars
14,225
forks
426
watchers
2,806
prs
2,281
issues
256
releases

README

Read this in other languages

English | 简体中文 | 日本語 | 한국어 | Deutsch | Français | Español | हिन्दी | Português | Русский | العربية | فارسی | Italiano | Polski | Nederlands | Türkçe | Українська | Tiếng Việt | Bahasa Indonesia | Svenska | Ελληνικά | Română | Čeština | Suomi | Dansk | Norsk | Magyar | ภาษาไทย | Oʻzbekcha | 繁體中文 | Filipino | עברית





  
  
  
  
  
  
  
  
  
  



  Start free, no card required →
  
  Cut agent token spend by 80%. Graphify Cloud is always-on memory that governs your agents, keeps code quality high, and proves correctness with formal verification.


Type /graphify in your AI coding assistant and it maps your entire project (code, docs, PDFs, images, videos) into a knowledge graph you can query instead of grepping through files.

- 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.)
- 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.
- 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.

 [!NOTE]
 Want this always-on? Graphify Cloud keeps the graph live across your entire SDLC: monorepo and cross-repo support, formal verification, and code review with a bird's-eye view of your SDLC, plus connectors for Sentry, Jira, and more so incidents and tickets sit in the same graph as your code. Start free, no card required.


  


  The FastAPI codebase mapped by graphify. Every node is a concept, colors are detected communities, and the whole thing is clickable in graph.html.


Get started (30 seconds). Needs Python 3.10+ and uv (or pipx):

bash
uv tool install graphifyy       install the CLI (or: pipx install graphifyy)
graphify install                detects your assistant and registers the skill


Then, in your AI assistant:


/graphify .


That's it. You get three files:


graphify-out/
├── graph.html       open in any browser: click nodes, filter, search
├── GRAPH_REPORT.md  the highlights: key concepts, surprising connections, suggested questions
└── graph.json       the full graph: query it anytime without re-reading your files


The persisted graph includes graph.schema_version so integrations can detect
incompatible format changes, plus graph.graphify_version identifying the
Graphify release that produced it.

One install, any assistant, any OS. Claude Code, Cursor, Codex, Gemini CLI, GitHub Copilot, and 20+ more, on macOS, Linux, and Windows: pick your platform.

---

 See it in action


  


Once the graph is built you query it instead of reading files. Real output, graphify run on the FastAPI codebase shown above:

text
$ graphify explain "APIRouter"
Node: APIRouter
  Source:    routing.py L2210
  Commun

Top issues

Discussions

Latest release

graphify 0.9.110 v0.9.110 2026-11-15
- Fix: python a call through an aliased import (from mod import foo as bar; bar()) is linked from inside a method body and from a decorated function or class def, not just at module level (5214, thanks @hementhu).
- Fix: go a type's methods declared in an internal _test.go file (same package foo) fold into the type's package node instead of splitting it and dropping its method-call edges; an external package foo_test stays separate (5209, thanks @Yi-111-a).
- Fix: js a name bound in an enclosing scope and captured into a tracked nested closure no longer fabricates a false indirect_call to a sa

News & coverage (16)

Hacker NewsGraphify – Less token use for Claude Code▲ 3 · 0 comments · 2026-08-07Hacker NewsGraphify – Turn any codebase into a queryable knowledge graph▲ 2 · 0 comments · 2026-08-06Hacker NewsGraphify: Codebase Knowledge Graph▲ 2 · 0 comments · 2026-07-29Hacker NewsShow HN: Turn any folder of code, SQL schemas into a queryable knowledge graph▲ 2 · 0 comments · 2026-07-14Analytics InsightFrom Developer Interest to Recurring Use: Safi Shamsi Tracks Graphify’s Growth as an AI Coding Context Layer2026-11-08note[Verification] Is it true that "7 free repositories can do 80% of a designer's work"? I investigated the 72026-10-30noteHow graphify, which turns folders into knowledge graphs, changes the 'ask that person' culture in teams2026-10-19ForbesYour AI Agents Can Write Code. Can They Understand Your Business?2026-10-02InfoQGraphify: Unifying Codebase Context to Streamline Agentic Software Engineering2026-09-23noteTurning Your Codebase into a Knowledge Graph with Graphify — An Introduction to Drastically Reducing Token Consumption in AI Coding —2026-07-29
6 morealphamatch.aiGraphify: The Knowledge Graph Layer That Makes AI Coding Assistants Actually Smart2026-06-06xGraphify Brings Karpathy's LLM Knowledge Base Idea to Life in Days2026-04-06HackerNoonI Tested Graphify on a Real Python Repo. Here's What Happened2026-10-21Augment CodeGraphify v0.9.9: Benchmarks, a New Org, and Why the Graph Beats Grepping2026-07-07Augment CodeGraphify Turns Your Codebase Into a Knowledge Graph You Can Actually Query2026-06-30Augment CodeGraphify Ships v0.8.41: A Knowledge Graph Skill for 20+ AI Coding Assistants2026-06-18

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON