> Graphify: shared understanding of your codebase for agents and developers. Canonical: https://graphify.com/blog/graphify-cli-10-million-downloads · Full index: https://graphify.com/llms-full.txt

# Graphify passes 10 million downloads on PyPI

*November 6, 2026 · Syed Fahad*

![pepy.tech download badge for graphifyy](/images/graphify-cli-10-million-downloads/pepy-badge.png)

Graphify is a code knowledge graph: it maps your repo into functions, classes, files and the links between them, so you and your coding agents can ask real questions and get answers with a file and a line. And open-source Graphify, published on PyPI as `graphifyy`, just passed **10 million downloads**. 🎉

As of November 6, 2026, [pepy.tech](https://pepy.tech/projects/graphifyy) counts **10,056,896** downloads. Ten million installs of a tool that helps agents understand code. We're still a little stunned.

The first version went up on PyPI in April 2026. Seven months and 270 releases later, here we are.

## What do the numbers actually show?

Totals are fun, but the shape of the curve is the part that made our team stop and stare.

![Daily PyPI downloads of graphifyy from August 5 to November 3, 2026, from pepy.tech data](/images/graphify-cli-10-million-downloads/downloads-daily-chart.png)

* **10,056,896** total downloads on PyPI (pepy.tech, Nov 6, 2026)
* **1,949,236** of them in the 30 days ending Nov 4, so roughly one in five installs ever happened this past month
* **about 481,000** downloads in the last week and **about 80,000** in a single day ([pypistats.org](https://pypistats.org/packages/graphifyy))

Download counts include CI machines and mirrors, so we don't read them as "ten million people". We read them as a trend: more teams are wiring Graphify into the places where their agents work every day, from laptops to build pipelines.

![The graphifyy project page on pepy.tech](/images/graphify-cli-10-million-downloads/pepy-page.png)

## Why are developers installing it?

Coding agents got very good at writing code and stayed surprisingly bad at knowing a codebase. Ask one what breaks when a function changes and it goes back to grepping and guessing.

Graphify gives the agent the structure instead. Run it on a folder and you get a graph of who calls what, who imports what, and what depends on what, served to your agent through [MCP](https://graphify.com/mcp). The CLI works with the assistants people already use, including Claude Code, Codex, Cursor, Gemini CLI and many more, and it reads about 40 languages.

That's the whole pitch, and judging by the counter, it lands. If you're new to the idea, our explainer on [what a code knowledge graph is](https://graphify.com/blog/what-is-a-code-knowledge-graph) is the best place to start.

![The graphifyy page on PyPI](/images/graphify-cli-10-million-downloads/pypi-page.png)

## Who made this happen?

You did. Every person who ran the install, filed an issue, sent a pull request, asked a sharp question on Discord or told a teammate "just try it on our repo" is inside that number.

Open source works because people show up for it. Thank you for showing up for this one. Open-source Graphify stays Apache 2.0, and the code lives on [GitHub](https://github.com/Graphify-Labs/graphify).

## What's next?

Ten million is a checkpoint, not a finish line. Next on the roadmap:

* Faster graph builds and fresher graphs as your code changes
* More agents and editors that can read the graph out of the box
* Even smoother paths between the CLI on your machine and the hosted Graphify app for your team

We'll keep shipping in the open and writing it up here as we go.

## Try Graphify

The quickest way in is the hosted app. Open [app.graphify.com](https://app.graphify.com), connect a repo, and ask your codebase a question.

Prefer to run it on your own machine? Install [open-source Graphify](https://github.com/Graphify-Labs/graphify):

```bash
uv tool install graphifyy
```

Come celebrate with us on [Discord](https://discord.gg/graphify). Here's to the next ten million.

## FAQ

### How many times has graphifyy been downloaded?

According to pepy.tech, graphifyy has been downloaded 10,056,896 times on PyPI as of November 6, 2026, including 1,949,236 downloads in the 30 days ending November 4.

### Where do the download numbers come from?

The totals come from pepy.tech, which reads PyPI's public download data. pypistats.org shows the same trend, with about 1.63 million downloads in the last month.

### What is graphifyy?

graphifyy is the PyPI package for open-source Graphify. It turns a folder of code, docs, papers, images or videos into a queryable knowledge graph that you and your AI coding agents can ask questions of.

### Is Graphify open source?

Yes. Open-source Graphify is Apache 2.0, and the code lives at github.com/Graphify-Labs/graphify.

### How do I try Graphify?

Open the hosted Graphify app at app.graphify.com and connect a repo. If you prefer to run it locally, install open-source Graphify with uv tool install graphifyy.