Post

jake
@yetanotheruseless.com

So after running this a while, I can confidently say that Modal is def. not going to break the bank. I am using it all the time (from mobile, laptop, claude code cloud, claude dot ai chat) and I'm averaging about $0.10/day (plus about $0.02/day on Qwen3 embeddings). fast, cheap, globally reachable

jake@yetanotheruseless.com

So since everyone and their grunkle is publishing their stateful agent setup, I might as well publish mine. Meet Yaucca (pronounced like it looks): Yet Another Useless Claude Code Agent: github.com/jakemannix/y... [1/n]

github.comGitHub - jakemannix/yaucca: Yet Another Useless Claude Code Agent — persistent long-term memory for Claude CodeYet Another Useless Claude Code Agent — persistent long-term memory for Claude Code - jakemannix/yaucca
jake
@yetanotheruseless.com

It means that my ADHD stream-of consciousness which naturally spreads across many projects (some of whom touch on each other) and surfaces (idea comes to me when on my phone in a parking lot...), plus random "ah need to remember to get milk!", can all get baked into "me and Claude"

0 reposts5 likes

jake
@yetanotheruseless.com

every conversation flows from one to the next, and I have hooks that tells Claude to check for relevant other stuff - which is sometimes annoying "this would be great for your talk next week!" (no, it won't, I've got that under control thx), but often helpful context so I don't keep repeating myself

jake
@yetanotheruseless.com

and when I need to have a very focused, specialized Claude, who is On Topic? My stateful yaucca-enabled Claude can spin off a sub-agent with a specialized prompt for just that task, and none of my stateful-agent memories and other stuff cluttering up its context. Best of all worlds!

jake
@yetanotheruseless.com

it's... more focused. Claude memories stores stuff you've talked about, but it's mostly summaries, it seems. What yaucca (and letta, and a few other impls) does is grab 3 different bits of memory into context: