Turn your projects into knowledge graphs for artificial intelligence
Graphify transforms different types of data such as code files, database schemas and documentation into a queryable knowledge graph structure. This Python-based tool aims to create a central data layer for various AI coding assistants.
Updates
- November 8, 2026: Stars 143,093 → 144,077, latest release v0.9.104 (November 8, 2026).
- November 6, 2026: Stars 141,955 → 143,093, latest release v0.9.103 (November 5, 2026).
- November 4, 2026: Stars 141,332 → 141,955, latest release v0.9.102 (November 3, 2026).
- November 3, 2026: Stars 140,169 → 141,332, latest release v0.9.101 (November 2, 2026).
What you get
- The code turns your files and documents into a queryable information network.
- It uses native and fast tree-sitter technology for code analysis.
- It facilitates the transition between concepts by establishing connections between files.
Installation
uv tool install graphifyy # install the CLI (or: pipx install graphifyy)
graphify install # register the skill with your AI assistantRunning it
/graphify .If you don't write code
I converted this project directory into a knowledge graph using Graphify. Now, using this structure, I want you to analyze the relationships between concepts in the project, explain how complex code blocks are connected to each other, and detail the role of master nodes such as 'APIRouter' in the system. Please distinguish between information coming directly from the source code and inferred connections by taking into account the 'EXTRACTED' and 'INFERRED' tags when performing your analysis.
Repository: https://github.com/Graphify-Labs/graphify. Follow the official instructions in the README of this repository for setup and execution.
Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.
Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.
Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.
Related dictionary terms
Links
TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-07-14: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.