I've been working on this project. I built this in about two days, using it to build itself at the tail end of the effort. It's not perfect, but I see the promise in it. It stops the thrashing the LLMs can do when they're looking for types or trying to resolve anything like that.
What of today's agents work like this? None of the ones I've tried would do something like that, but instead would grep/search the file, then do a smaller edit (different tools do those in different ways).
Overall, it does feel like a strawman argument against "Traditional" when almost none of the tooling actually works like that.
Apologies - I had the LLM generate the readme and it looks like it got a bit overzealous. I'll get some actual benchmarks and cost usage analysis going. I've tamed the README somewhat. Please check it out!
I've been working on this project. I built this in about two days, using it to build itself at the tail end of the effort. It's not perfect, but I see the promise in it. It stops the thrashing the LLMs can do when they're looking for types or trying to resolve anything like that.