repowisegraphify-labs/graphify

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.

Python★ 132,681
Use in your agentAsk this codebase

github.com/graphify-labs/graphifyIndexed at 847a93fUp to date with upstream

What is graphify?

graphify is a Python tool for turning codebases and related documents into queryable knowledge graphs. It parses code locally with tree-sitter and represents connections as graph edges that can be queried instead of searching files.

Written by a model from the README and the source

940 files and 10,991 symbols in 6 modules, led by Python (553 files) and TypeScript (2).

Start reading

Code health

6.4out of 10Fair

This codebase scores 6.4 out of 10 for code health, which we rate fair. It also scores maintainability 6.8 and static performance 9.2 out of 10. The three are scored separately and never blended into one number. Risk is concentrated, as it usually is: 91 of 940 files are git hotspots, and they average 4.3 — which is where the fixes pay off most.

Full health report

On the leaderboards:#36 of 49 Python repos

Use graphify-labs/graphify in your agent

Point Claude Code, Cursor, Codex or VS Code at this repository. Your agent gets the index this page is built from: cited answers, callers, history and health for any file.

  1. 1.In Claude, open Customize → Connectors, click +, then Add custom connector. On a Team or Enterprise plan an owner adds it first under Organization settings → Connectors.
  2. 2.Paste the server URL below as the Remote MCP server URL, then click Add.
  3. 3.Click Connect. A Repowise sign-in window opens. Approve access.
  4. 4.Repowise's tools are now available in your Claude chats.

Connect with one click. Sign in with Repowise (OAuth), no API key to copy. Works in Claude on the web, desktop, and mobile.

Docs
bash
https://api.repowise.dev/mcp/graphify-labs/graphify
Editors need an API key: sign in to create one.Sign in to connect

This repo is public, so anyone with a Repowise account and an API key can connect.

Try asking

  • get_overview()
  • get_answer("how is graphify put together?")
  • get_why("why is graphify structured this way?")

Explore graphify

Key features of graphify

  • graphify creates local code maps using tree-sitter AST parsing without sending code to an LLM.
  • graphify labels connections as EXTRACTED or INFERRED so direct source relationships can be distinguished from resolved ones.
  • graphify resolves calls, imports, inherits, and mixes_in links across about 40 languages.
  • graphify provides graph queries, path tracing, and concept explanations against graph.json.
  • graphify maps documents, PDFs, images, and video or audio into the same graph.

How graphify-labs/graphify works

The /graphify command enters through an AI coding assistant and maps a project into graph data. graphify/extract.py handles extraction from project inputs, while graphify/extractors/engine.py provides the extraction engine. graphify/cli.py exposes installation and command-line operations, and graphify/__main__.py provides the module entry point. The process produces graphify-out/graph.html for interactive browsing, GRAPH_REPORT.md for highlights, and graph.json for querying. Tests in tests/test_extract.py, tests/test_languages.py, and tests/test_detect.py cover extraction, language handling, and detection behavior.

The codebase has 940 files and 10,991 symbols in 6 modules, led by Python, TypeScript and Dockerfile. Code health is 6.4 out of 10, rated fair.

Getting started with graphify

  1. Install the graphify CLI with uv.
    uv tool install graphifyy # install the CLI (or: pipx install graphifyy)
  2. Register the skill for your AI assistant.
    graphify install # detects your assistant and registers the skill
  3. Run graphify in your AI assistant.
    /graphify .

Commands copied from the README

graphify-labs/graphify FAQ

What is graphify?

graphify turns codebases and related documents into queryable knowledge graphs. It supports local AST parsing and graph-based queries.

How does graphify work?

graphify parses code with tree-sitter and creates explained graph edges. It writes graph.html, GRAPH_REPORT.md, and graph.json to graphify-out/.

How do I install graphify?

Install graphify with uv tool install graphifyy, then run graphify install and use /graphify . in your AI assistant.

What language is graphify written in?

graphify is written primarily in Python. Its indexed source also includes TypeScript and Dockerfile files.

How is the graphify code organized?

graphify contains the main implementation, tests contains extraction and language tests, tools contains supporting utilities, and scripts contains scripts.

Who is graphify for?

graphify is for people using AI coding assistants who want to map code, documentation, and media into a queryable knowledge graph.

What license does graphify use?

graphify uses the Apache-2.0 license.

The summary, features and answers on this page are written by a model from the README and the source, and refreshed with each index.

About this page

Get a page like this for your own codebase

Repowise built this map of graphify-labs/graphify from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Index your repo freeSee how Repowise worksFree for 2 public repos, with a page like this one.

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed.