Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Transform your codebase into a single Markdown doc for feeding into AI

tesserato.web.app

Post reply on HN
Print view View original

61–70 of 172 posts

Re: Show HN: Transform your codebase into a single Markdown doc for feeding into AI

#61

Post by tesserato »

pmx wrote: post #4

How does this compare to / differ from https://github.com/yamadashy/repomix ?

Some advantages of CodeWeaver are that it is compiled, so it might be faster; you can grab a compatible executable from the releases section instead of using `go install` so, no dependencies. You can manually specify what to exclude via a comma-separated list of regular expressions so it might be more flexible. I never used Repomix so, those assumptions might not hold. On the other hand, remix seems to be awfully more complete, a full-fledged solution to convert source code to monolithic representations. I wrote CodeWeaver because I only needed something that worked and, occasionally, I could trust to keep sensitive data away from sketchy LLMs (And wasn't aware of other solutions).

Re: Show HN: Transform your codebase into a single Markdown doc for feeding into AI

#63

Post by tesserato »

Conasg wrote: post #60

I made a similar tool in Golang, https://github.com/foresturquhart/grimoire . It tries to be a bit cleverer, by prioritising files that have had many commits, respecting .gitignore files, and excluding useless content like binaries or vector images.

I can think of no use case where binaries are desired in such representation, so I might bake binary exclusion into CodeWeaver as well. SVGs, on the other hand, might be wanted sometimes, in web design contexts. I'll take a look at your implementation and see what I can learn.

Re: Show HN: Transform your codebase into a single Markdown doc for feeding into AI

#64

Post by Keyframe »

BowBun wrote: post #40
Keyframe wrote: post #19

Wouldn't it be wonderful to have a tool where you interact with AI interactively through the codebase via IDE / vim / emacs tree? Say, you open your codebase and start with prompts and AI+tool navigates to a function or a place where it needs to and modifies stuff while chatting to you about it? Or you jump to somewhere, highlight where you are to scope down the focus of it (while it still retains all of the code in…

This doesn't sound good to me, you end up with a large codebase that no human has actually laid eyes on. When you get a bug weird enough that you can't reason the LLM through it, then what? What if a bug is because of interactions between two systems, and you don't own one of them? What if there's an issue due to convoluted business process failures, that just end in a bug report like "my data is missing!"? I honestl…

Nothing like that at all. For example I have a few codebases kind of large (for certain quantity of large) where I know the code since either I wrote it or participated heavily in. Talking snippets at a time loses a ton of context which would yield better offered solutions if you had, well.. the whole context.

Re: Show HN: Transform your codebase into a single Markdown doc for feeding into AI

#65

Post by codecraze »

Conasg wrote: post #60

I made a similar tool in Golang, https://github.com/foresturquhart/grimoire . It tries to be a bit cleverer, by prioritising files that have had many commits, respecting .gitignore files, and excluding useless content like binaries or vector images.

Nice! Written in go. I like that :)

Re: Show HN: Transform your codebase into a single Markdown doc for feeding into AI

#66

Post by DrPhish »

crisbal_ wrote: post #33

I use the following for feeding into AI find . -print -exec cat {} \; -exec echo \; Which will return for each file (and subfolders) the filename and then the content of the file. Then `| pbcopy` to copy to clipboard and paste it into ChatGPT or similar.

That's very nice and compact. I do the same with a short bash script, but wrap each file in triple-backticks and attempt to put the correct language label on each eg:

Filename: demo.py

```python

   ...python code here...
```

Re: Show HN: Transform your codebase into a single Markdown doc for feeding into AI

#67

Post by singpolyma3 »

crisbal_ wrote: post #33

I use the following for feeding into AI find . -print -exec cat {} \; -exec echo \; Which will return for each file (and subfolders) the filename and then the content of the file. Then `| pbcopy` to copy to clipboard and paste it into ChatGPT or similar.

I guess this only works for very small codebase?

Re: Show HN: Transform your codebase into a single Markdown doc for feeding into AI

#68

Post by OsrsNeedsf2P »

singpolyma3 wrote: post #67
crisbal_ wrote: post #33

I use the following for feeding into AI find . -print -exec cat {} \; -exec echo \; Which will return for each file (and subfolders) the filename and then the content of the file. Then `| pbcopy` to copy to clipboard and paste it into ChatGPT or similar.

I guess this only works for very small codebase?

Correct, but it's the same as what OP shared.

You should use Aider/Cursor for proper indexing/intelligent codebase referencing

Re: Show HN: Transform your codebase into a single Markdown doc for feeding into AI

#70

Post by cruffle_duffle »

rapind wrote: post #29

Somewhat related. I built an Elm app all in one file as an experiment and to see if I like it. It's a little over 7k lines and I'm occasionally adding more to it. It's actually pretty straightforward if you're in a language with lexical scoping, and it simplifies some things, like includes / cyclical, no modules, no hunting through files, etc. I feel like this set up could integrate really well w/ AI models. I've fou…

The big problem with that is you’ll eventually blow your context window feeding the model with stuff that it mostly doesn’t need in order to complete its task.
Post reply on HN