LLMs make it gloriously simple to fork and patch and existing repo. If you run into a merge conflict down the line, its a snap to fix too.
Just make the changes you want to your favorite harness and move on.
Just make the changes you want to your favorite harness and move on.
In my experience "throw another agent at it/fork it" consistently creates unsupervised trainwrecks.
off: I'm working on my spare time on a code mode lisp alternative (great opportunity to learn lisp) and might switch to it fully as long as I built some simple evals (I'm concerned about token usage, which is why i forked pi the first time)
If I don't find anything which fits me I might fork it, but even that little effort is not really worth it if theres something which fits me better.
I already found maki which...seems to do the exact same job pi did for me, and I wanna check out crush as well.