I ran this open source AI tool on a messy codebase and got 71x fewer tokens – here’s exactly what happened
Last updated on May 4, 2026 by the editorial team
Author(s): Mohammed Hassan Ali
Originally published on Towards AI.
I spent months observing developers who struggled with messy codebases. They often resorted to copying and pasting entire files into AI tools like Claude, only to receive vague and unhelpful answers. It was during this period that I discovered Graphify, an open source AI coding assistant that promised to revolutionize the way we handle code.
The power of Graphify lies in its ability to transform code files into a searchable knowledge graph. This approach drastically reduces the number of tokens used during queries – by a staggering 71 times compared to traditional methods. The process is efficient, thanks to Graphify’s three-pass extraction method that optimizes the handling of a variety of file types, ranging from code to documents.
One of the standout features of Graphify is its ease of installation and use. The tool is designed with a privacy-focused approach, ensuring that developers’ data remains secure. This makes it an ideal choice for developers seeking to enhance their coding workflows without compromising on privacy.
To learn more about how Graphify can transform your coding practices, read the full blog post on Medium by following this link.
We are building enterprise-grade AI. We will also teach you how to master it.
With a team of 15 engineers and over 100,000 students enrolled, Towards AI Academy offers comprehensive courses designed to equip you with the skills necessary to thrive in the world of AI. From fundamental concepts to advanced applications, our curriculum covers everything you need to know.
Start for free – no obligation:
→ 6-Day Agentic AI Engineering Email Guide — One Practical Lesson Per Day
→ Agents Architecture Cheatsheet — 3 years of architectural decisions in 6 pages
Our courses:
→ AI Engineering Certification — 90+ lessons from project selection to deployed product. The most comprehensive practical LLM course available.
→ Agent Engineering Course — Hands-on with production agent architectures, memory, routing, and evaluation frameworks — built from real enterprise engagements.
→ AI for Work — Understand, evaluate, and apply AI for complex work tasks.
Note: The content of the article contains the views of the contributing authors and not of Towards AI.
“`
