HN Explorer

Show HN: Instantly visualize any codebase as an interactive diagram (gitdiagram.com)

222 points by ahmedkhaleel ↗ HN
GitDiagram is an open-source micro dev-tool that I made this past week

Given any public GitHub repository it generates diagrams in Mermaid.js with Claude 3.5 Sonnet

I extract information from the file tree and README for details and interactivity (you can click components to be taken to relevant files and directories)

Also, you can replace "hub" with "diagram" in any repository URL to access its diagram

I created this because I wanted to contribute to open-source projects but quickly realized their codebases are too massive for me to dig through manually, so this helps me get started

I do still plan on adding other features like private repository access if that becomes a thing people want

This project was heavily inspired by https://gitingest.com/ so make sure to check that out as well!

Hopefully this tool can help you and feedback is always welcome!

62 comments

[ 2.4 ms ] story [ 80.6 ms ] thread
whalesalad
I hope you have a cap set on your billing!
ahmedkhaleel
yup, i did that, i have it currently on balance mode so its not using anything without my knowledge
visch
:D , he got a star from me for the ease!
ahmedkhaleel
haha thanks so much! really went for that with this project. hopefully wont cause any issues
owenpalmer
Inputted llvm-project, resulted in this error:

  Repository is too large (>200k tokens) for analysis. Claude 3.5 Sonnet's max context length is 200k tokens. Current size: 1448461 tokens.
karmakaze
I tried with sorbet/sorbet:

> File tree and README combined exceeds token limit (50,000). Current size: 159829 tokens. This GitHub repository is too large for my wallet, but you can continue by providing your own Anthropic API key.

Without having an idea of the output it would produce, I can't tell if it's worth it. I'm not particularly interested in this test example so it's something I might try for an easy win, but probably tweak and maintain whatever it produces--or discard it and make something by hand. Showing something subjectively incorrect is good motivation.

lor_louis
I tried it on a personal repo and it never ended up generating a diagram.

Might be a bug, so here's the repo. https://github.com/lorlouis/cedit

ahmedkhaleel
i see a diagram there now, might've taken a while to load https://gitdiagram.com/lorlouis/cedit
billyp-rva
I guess to get the discussion going: the diagrams look nice, but I think the erroneous and missed connections limit their usefulness. In this example, there is a connection from "Line manager" (line.h/.c) to "Memory Allocator" (xalloc.h/.c), but it doesn't look like such a dependency exists in the codebase. Meanwhile, "Syntax Highlighter" does directly import xalloc.h, but there is no dependency shown in the diagram.
lor_louis
As the author of the repo I was surprised how close to my mental model the graph was. (I haven't worked on this repo in a while so my mental model is a bit fuzzy)

And yeah it seems to be missing a few connections but the ones that are there are correct line.h depends on str.h which links str.c which depends on xmalloc.c/h.

But had I been a new contributor to the project I would have found the missing links between modules pretty frustrating.

My guess is that the graph is only good enough to give and overview of what things are dependent on what if I were working on a monorepo and I had to justify to my manager that team B needs to do something for us.

I like the idea though, a lot of direct code to graph tools are too noisy and that tends scares non technical people away.

mparnisari
It never generated a diagram for mine :(
ahmedkhaleel
thats unfortunate, whats the url? ill check it out
shahzaibmushtaq
I learn faster with visualization, whether it's a stat or a codebase. Much appreciated!
ahmedkhaleel
yup, exact same here, glad to see my project helping others alike
corysama
To save everyone a lot of time and OP some money, here is https://github.com/id-Software/Quake-III-Arena diagrammed:

https://gitdiagram.com/id-Software/Quake-III-Arena

https://imgur.com/a/gwoabtk

Clicking on any box takes you directly to either a file or a folder in the repo. AFAICT, the boxes, wires, groups, labels are all inferred by the AI.

ahmedkhaleel
yup, if you look at the backend its basically just a pipeline of information extracted from the file tree and readme using Claude 3.5 Sonnet, sick diagram tho
jesse__
Tried https://github.com/scallyw4g/bonsai and I believe it hung after the green loading bar completed. Left it for several minutes
ahmedkhaleel
yea i just checked the db, nothing there. thats weird, ill try loading it myself
jesse__
Looks like it works now, although the diagram it generated is pretty watery.

It mis-judged that the "work queue system" is kind of off by itself, when in fact almost all of the important work in the engine goes through the work queue. It did do a good job of at least approximately figuring out the render pipeline stages. Somehow it thinks that "input processing" isn't related to the platform layer, which doesn't make any sense at all.

Seems like a pretty reasonable result for a weekend project, nice work :)

ComputerGuru
Bug: url checker is case sensitive. For those of us that type out the url from memory on a stupid touch-type device with auto incorrect, you’ll get things like Http(s)://Github

Also might want to coalesce https and http

Not sure if it queues jobs for processing so that when I refresh after a failure it is continuing where it left off or if it is starting over anew? “Progress bar” makes it hard to say.

Aside: I dislike the “modern progress bar” that’s just a scrolling marquee of pithy quips. One of the difficult problems I worked on for a SW project was adding sane progress to a multi-stage backup tool so that the completed percentage and ETA correctly represented a mix of millions of single kb files and random multi-gb files, backed up across multiple pipelines on multiple cores, asynchronously piping from one stage to the next with buffering. Needed to add a good progress metric without poisoning cpu core caches or hurting the efficiency of how work was being divided. This doesn’t seem as hard by comparison!

Sorry for only having tangentially relevant things to report at this time; still waiting for it to finish with the fish-shell codebase so I can give some good feedback!

billyp-rva
Didn't get a response (expected), but I would caution everyone to keep expectations low. Generating system diagrams from code is extremely difficult, if not impossible, even with AI [0].

[0] https://www.ilograph.com/blog/posts/diagrams-ai-can-and-cann...

mulmboy
This is a poor quality blog. They "upload" source code to chatgpt so who knows if it's in context or ragd plus it looks like they reuse the chat from a previous prose -> code session. They criticise LLM for high level diagram despite using a garbage prompt and rejecting the idea of iterating on the diagram.

Anecdotally I've had great success with code to diagram via LLM including fine details. But as with anything LLM you need to really get the context right. This can not be overemphasized. And iterate with the LLM, goodness.

billyp-rva
As mentioned in the blog, iterating on generating a diagram from a repo kind of defeats the purpose. The information is in the repo; if the LLM isn't going to analyze it properly, you might as well just tell it exactly what to diagram (like in the previous section on "whiteboarding"). It is much more capable at that.

If you have some examples of an LLM doing better, by all means please share.

mulmboy
"properly" is the key word here. You've got to communicate what you want. Or at least communicate something like what your goal is from the diagram, why you want it, so the LLM knows the audience it's targeting.

Like imagine giving the same prompt (instruction, directive, task) to a human - you would in all likelihood get out a similar high level diagram because you've not provided even the slightest whiff of what you want to use the diagram for.

The blog's takeaway is essentially "LLM didn't read my mind so no good". They're tools to be used and you get out what you put in.

chris_5f
This is just amazing. I tried out with my startup's repo and it was a blast. Shared with my community
antonpirker
This looks really nice!

I tried it with mine: https://gitdiagram.com/getsentry/sentry-python

A view things:

There are way more integrations in the integration layer, so maybe they should be either shown or a "..." somewhere should tell people that there is more.

The "Hub" is deprecated so it would be cool, that this fact is shown somewhere.

Otherwise really cool!

WillAdams
Failed with:

https://github.com/WillAdams/gcodepreview

which is probably the weirdest structure one could imagine (Literate Program as a .tex file containing Python and OpenSCAD code for https://pythonscad.org/ ) there the Python file is the core, there is an intermediate OpenSCAD file which wraps it, and then a top-level OpenSCAD file which the user interacts with.

Minervaskell
Final boss: https://github.com/torvalds/linux

Error message: Repository is too large (>200k tokens) for analysis. Claude 3.5 Sonnet's max context length is 200k tokens. Current size: 1334798 tokens.

Cool project though! Kudos!

Animats
Nice.

I put in a repository of mine that implements a UI in Rust, and it gave me a reasonable diagram. It's just a top-level structure of the program, though. No detail. Not much info about connections between components. The layout was kind of weird.[1]

Another one, from a fork I have of a rendering library.[2] It found the big parts, but provides little insight.

Here's a JPEG 2000 decoder. Even less insight.[3]

The progress messages are bogus. They have no relationship to what's going on. Progress messages indicating progress appear for a bad URL.

[1] https://gitdiagram.com/John-Nagle/ui-mock

[2] https://gitdiagram.com/John-Nagle/rend3-hp

[3] https://gitdiagram.com/John-Nagle/jpeg2000-decoder

thih9
Note: the messages that are displayed during diagram generation seem to describe the current progress - but actually they are generic/comedic messages that run in an endless loop.

Also, I tried this with https://github.com/rails/rails and it never finished.

dylan604
Are any of them kicking the llama’s ass while reticulating spines?
thih9
It’s mostly re-reticulating splines that I find annoying. By that I mean: running it all in a loop, endlessly - showing neither a result nor an error message.

But you’re right, reticulating splines and similar generic/comedic messages do have a long tradition.

dylan604
Getting useful feedback from remote servers via webui is my least fave.
thih9
A simple timeout would already be an improvement. Or some generic information about how long is the process supposed to take.
layer8
I tried this with a larger project, and after looping through the obviously-fake progress messages for a couple of minutes, it resulted in “Failed to generate diagram. Please try again later.”
btown
I really, really like this approach! Rather than trying to build a full graph of related low-level components from function calls etc., which is almost always overwhelming, this just finds the "vibes" of how modules are named in the filesystem, and how they relate to common design patterns - which in many cases is exactly what you want for exploring a codebase or understanding the scope of its offering.

https://github.com/ahmedkhaleel2004/gitdiagram/blob/main/bac... - the prompts in question. Don't sell yourself short as per the comments, they're very well designed prompts!

Using an inexpensive LLM to summarize each file might be an interesting next step, putting few-word summaries alongside the filenames in much the same setup you currently have! But, honestly, it may not be particularly necessary for large existing open-source projects that have already bikeshedded their file naming over many iterations, and/or have highly intentional structures for maintainability.

uncomplexity_
Of course I have to test it with https://gitdiagram.com/torvalds/linux

"Estimated cost: $8.07 USD" lol

Edit: "Repository is too large (>200k tokens) for analysis. Claude 3.5 Sonnet's max context length is 200k tokens. Current size: 1334798 tokens."

freakynit
Same lol... my immediate test case for this was this repo...

""" Repository is too large (>200k tokens) for analysis. Claude 3.5 Sonnet's max context length is 200k tokens. Current size: 1334798 tokens. """

abrookewood
Looks great, but would love to see it work with Private Repos.