Launch HN: CodeViz (YC S24) – Visual maps of your codebase in VS Code

Congratulations on the launch - this looks great and I've been waiting for years for something like this! As a researcher who mostly uses Python, and explores/navigates a large number of repos for a short time, often written by other researchers not necessarily trained in software best practices, I was always frustrated (and surprised) that there was no VS Code extension or tool that gave me a quick overview/visualization to get a high level gist of different modules and code/data flow!

I tried this with a bunch of small open-source repos and it works great! I imagine using LLM might be a hard no for some people/enterprises - any plans to use stand-alone licenses with small local models? It seems like for what LLM is doing here (if I understand it right, help label the modules in natural language and perhaps help organize them into this hierarchy/modules) you don't necessarily need a SoTA model, right?

Also, this could be coming from LLMs, but I see that the visualizations are more biased towards terminology used in web-dev? (for example, one of my robot related repo was organized into front-end, back-end, etc. with I guess is kinda right but not exactly lol). It would be nice to see an interactive visualization where I can iterate on the initial viz with information I know, e.g., I drag and drop a module or rename it and then you probably do another pass with this feedback and LLMs and update my overall visualization with more domain specific labels and partitions?

Edit: Exploring CodeViz on a few more repos, and it seems like you have a set of hardcoded labels for the highest hierarchy in the architecture diagram? (so far, I've only seen Users, Databases, Backend, Frontend, and Shared Components). I am guessing this is something passed on in the prompts? It'll be nice to allow user to define their own set of labels/partitions at one or more levels and then try to create an architecture visualization that fits into these labels/constraints (although I am guessing at some point you have to be wary of hallucinations?)

This is cool but it is way to expensive and the free version is not that useful.

Tried it on the github.com/pulumi/pulumi codebase and I get 5 blocks and that's it. Seems nice but I'm not going to pay 20 bucks a month to view one layer deeper.

Hi and congrats on the launch! I run a company that also does software diagrams and we've often been posed the question of generating automated diagrams. We've never done so, primarily because I've never found auto-generated diagrams helpful yet. Code dependency graphs have existed for a generation now and I've just never seen one referenced by anyone. I wonder if things have changed now with LLMs.

The examples in your youtube video look good. I'm curious how they're generated. "We were surprised to find that a small fraction of code can generate a very accurate representation of the system." is a surprising statement to me. It's not been my experience that the code can reveal an accurate representation of human-understandable architecture beyond the call graph. The backend system generated from OpenHands (in your video) also looks pretty different from their own architecture diagram in their README: https://github.com/All-Hands-AI/OpenHands/tree/main/openhand... . How do you reconcile what an LLM says an architecture looks like with what maintainers prescribe? Is there a way to give feedback to it? (similar to pthangeda's comment on customization)

I wish there was a way to point this at a repo to test its efficacy. Though I understand that that'd be prohibitively expensive to do for free on the landing page.

I'm also curious how you guys distinguish yourself from https://docs.codesee.io/docs/review-maps-for-visual-studio-c... . They tried this for a few years but shut down recently (https://www.linkedin.com/posts/shaneak_update-codesee-has-be...)

“On mobile? Add a calendar reminder to install CodeViz”

This is genius

Since you are asking for feedback, I would seriously consider buying licenses for my team if:

- We are allowed to use our own API key to get your extension to talk directly with our LLM of choice. I understand you are using Claude right now, but we are on OpenAI & Copilot; since we already went through the hoops of "accepting that our codebase will be sent to an LLM", we are trying to control the level of exposure. OpenAI is already in, Claude isn't; and you definitely won't be so having our codebase go through your infra is a no go. Local LLM would be incredible, but it might be not technically achievable yet.

- The price is too steep. I get way more value out of Copilot than I get from CodeViz which is similarly priced. I understand you have LLM costs at the moment, but as the point above defends: it does not have to be that way. I would find it way more "fair" to have to insert my LLM API (even for the free version and/or trial, right now you are loosing money on that) and have a separate cost for the extension; possibly with a "lifelong for current version + 1 year of upgrade license". Let me pay the usage to the LLM monthly depending on my actual usage, and pay you to build a very nice prompt engineering system.

I, and I'm guessing most people, don't have a use case that warrants a subscription for such a service let alone one that costs $20/month.

Happy to pay a one time fee and the ability to use my local LLM

I'd love to try this against my spaghetti, but I can't send my company's IP to you or anthropic or anyone else. I'll have to try against open source projects we rely heavily on first.

Does my codebase leave my machine when using your extension with it?

there is a codevis application in the open for almost two years. it generates large scale software visualization for c, c++ and fortran (but it accepts other languages as plugins). i am the main developer of this tool, and im a bit shocked that another tool with similar intent and same name exists. woyod you be ok for me to demo what codevis (the kde one) do to your team? you can reach me at tcanabrava at kde.org the source of codevis is at invent.kde.org/sdk/codevis

Twice the monthly cost of Copilot seems crazy to me, and I’m nowhere near as subscription-hostile as most folks here.

I personally don’t like VS Code although if this works well I might open it just for this feature. I’d still be coding and taking notes in emacs though. Any thoughts on putting most of the smarts into a server process so that any editor can have a plug-in that talks to it?

Codeviz is such a cool project. Love having it in VSCode.

Does it show dead code? Like classes which are not being used by anything and are safe to delete?

I did something like this in chrome devtools a long time ago.

It was fun to look at various sites front end architecture.

I started to do complexity analysis as well, because, why not. But I got busy with actual work.

I wonder if I can dig it back from somewhere.

Going by the video, I see the diagrams have lines, but unfortunately no labels. Do lines always mean "dependency"? E.g. file dependency, dependency on a database or service, etc.

Seems like there is a lot of potential here, although a hard sell up against the licensing fees of products from e.g. Jetbrains. I’m sure yours will be better at its one thing than a more generalised product but it’s a tough market. Compared to what specialised engineering software costs (see Solidworks) it is cheap, but we are very stingy in software.

On a different note: I’m wondering, do you have any function calling built in? Is there room for combining LLM output with LSP calls?

Diagrams of code can be done with UML ¹. A fairly decent ² standard with a set of different diagrams that can be created to visualize code.

In those terms CodeViz will provide a form of simplified class diagrams and a function call mapping?

Will there be sequence diagrams in the future?

¹ https://www.uml.org/ ² It has fallen out of fashion, since many people found it too heavy, and a lot of people have hever heard of it.

wow looks really good. i've been expecting this space to get much better (because it never looked good) and this looks primising. congrats!

Doesn't mention a cost or trial period in your post or the website

After installing it, it doesn't even let you see the first thing without signing up for a trial period and even then doesn't mention a cost.

I understand you just launched it, but I look at the free trial and think "what else am I going to find out...", uninstalled for now but hope you find traction.

I have it a quick shot and I must say the UI is not easy to grasp. The graph is interesting and surprisingly well understanding my codebase.

But the navigation? Not easy to understand how to use it. Any video for helping us out see what we can do and how we can do it ?

Very cool. Have built something like this in the past - let me know if you are hiring.

There are so many cool projects for working with code repos posted on HN that I will never get to enjoy at work, because my repo is google3, and it has like 40 million files and 100 million classes. Oh well.

I am surprised there is no word "privacy" in this page, as of this comment!

Could be useful for me. Will keep an eye on this.

Yeah dude, take my money. I can't believe what I'm seeing. You've actually given me a reason to use a second monitor again.

I like your thing.

I have been forcing my bot to give me Mermaid diagrams, swim diagrams, markup tables of schemas, code, logic etc...

I like where you guys are going, but what I think would be really fun - would be a Node Based diagram logic, where the boxes that you show in the diagram are Code-geometry-Nodes - and could be connected with code blocks as such.

Watch @HarryBlends videos on Geometry Nodes in Blender for Inspiration:

https://www.youtube.com/@harryblends

https://www.youtube.com/watch?v=a-4oCHe-hDE

These are the best graphic/node based visuals for describing structured relationships in maths I've ever seen.

To give you some CyberPunk FutureVision of what your outpus could be like -- if it turned all the code nodes into atomic code legos and rather than drawing the diagram from the code - I can use the diagram to create the code.

--

WRT "...some code goes to anthropic..." while answering another, seems like you guys would do well to know these guys:

https://news.ycombinator.com/item?id=41381498

https://www.usevelvet.com/

As well as these guys:

https://news.ycombinator.com/item?id=41322281

https://github.com/instantdb/instant