Live data from Hacker News

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

tesserato.web.app

81–90 of 172 posts

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

#81

Nice! Built something similar in Rust that supports local and remote repos: https://crates.io/crates/r2md

I thought of using Rust, but ultimately chose Go. I'll take a look and see how something similar came out in Rust!

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

#82
post #51

Tip: If you ever need to do this on a public GitHub repository you can use "gitingest". This will open a website that creates a copy of all the file contents of the repo (code, docs, ...) It's a great tool to use when using new/obscure code with LLMs in my opinion. The UX is so just easy and great, change the URL from https://github.com/user_name/repo_name > to https://gitingest.com/user_name/repo_name > //edit: fixe…

I copied the UX to my https://gitpodcast.com (creates podcast on a github repo, same replace `hub` with `podcast`)

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

#83
Anybody with experience of using something like this with a big codebase and Gemini 2M context window? I tried a while ago (before 2.0 Flash) to solve some refactoring tasks and even after spending some time on prompt wrangling I didn't manage to get good results out of it.

I don't know what kind of agent architecture Cursor uses internally but it seems much better designed at finding where changes need to be made.

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

#85
If I'm reading this correctly, why include all code into the markdown? It's almost like the AI model that would use this is necessarily using all concatenated code plus explanation of the code, I'm not sure which is better because the LLM then already has access to the entire code as part of markdown?

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

#88
post #83

Anybody with experience of using something like this with a big codebase and Gemini 2M context window? I tried a while ago (before 2.0 Flash) to solve some refactoring tasks and even after spending some time on prompt wrangling I didn't manage to get good results out of it. I don't know what kind of agent architecture Cursor uses internally but it seems much better designed at finding where changes need to be made.

In my experience with feeding large codebases to Gemini, simple tasks work ok (enumerate where such and such happens, find where a certain function is called, list TODOs throughout the code, etc), but tasks that require a bit more logic are trickier. Nevertheless, I had some success with moderate complex refactoring tasks in Python codebases.
Post reply on HN