Instead of having to regenerate a zip file everytime you add/delete a memory... could we just use a git repo of markdown pages?
This buys you incremental writes, commit hash pinning and diffs for free. In addition to having a git archive outputting a zip export as well?
Main wrinkle is you would need to gitignore the sqlite database as it doesn't store very well in git (binary, changes lots per insert). But it's easy to regenerate anyway as a rebuild-able cache.
You don't have to regenerate a zipfile each time you do something - the zipfile is just to give a single file for distribution. It's just a zip of the directory.
Git is supported in the spec, though the tool doesn't yet handle it (soon! git is nice as you get a log "for free" which helps agents understand more about the memories).
As for sqlite in git: yes you can gitignore it, you could use git-lfs, you could use an out of band database. It would be great if there were another format more amenable to git to store vectors in. I looked at csv closely, but I was worried about float formatting/representational bugs. There is a gap in the market for a format here.
Found this video quite interesting. One bit was a bit funny where telling the AI model to not think about it, it ends up thinking about the concept in it's J-Space and the word "Dammn" as well
It was one of the first large-scale commercial applications of barcodes, and at one point 95% of railroad cars were equipped with it. Could've been a success, but it was a few decades too soo, and a handful of small but crucial implementation flaws doomed it to abandonment only a decade later.
So you want to generate C code instead of ByteCodes.... and then compile the C? I suppose, if you broke out the runtime memory management (and a few other things) into a library. But I am not sure why you would....
If you want pure speed, then you would rather have it generate machine instructions instead of higher-level ByteCode ops. But you would not be using a scripting language if you want pure speed.
Perhaps if you only want a double-arglist variant of C (you must call it scC!) then you could write a front end processor! And by you, I mean not me :-)
This buys you incremental writes, commit hash pinning and diffs for free. In addition to having a git archive outputting a zip export as well?
Main wrinkle is you would need to gitignore the sqlite database as it doesn't store very well in git (binary, changes lots per insert). But it's easy to regenerate anyway as a rebuild-able cache.