zclaw: personal AI assistant in under 888 KB, running on an ESP32 (github.com)

24 points by tosh 9 hours ago

v9v 9 minutes ago

[delayed]

throwa356262 an hour ago

"LLM backends: Anthropic, OpenAI, OpenRouter."

And here I was hoping that this was local inference :)

micw an hour ago

Sure. Why purchase a H200 if you can go with an ESP32 ^^

__tnm 29 minutes ago

haha well I got something ridiculous coming soon for zclaw that will kinda work on board.. will require the S3 variant tho, needs a little more memory. Training it later today.

peterisza an hour ago

right, 888 kB would be impossible for local inference

however, it is really not that impressive for just a client

Dylan16807 38 minutes ago

It's not completely impossible, depending on what your expectations are. That language model that was built out of redstone in minecraft had... looks like 5 million parameters. And it could do mostly coherent sentences.

theturtletalks an hour ago

Is there a heartbeat alternative? I feel like this is the magic behind OpenClaw and what gives it the "self-driven" feel.

g947o an hour ago

Serious question: why? What are the use cases and workflows?

grzracz 19 minutes ago

I don't fully get it either. At least agents build stuff, claws just run around pretending to be alive?

milar an hour ago

for fun!

johnea 2 hours ago

I don't really need any assistance...

throwa356262 an hour ago

Me neither.

But I have 10-15 ESP32's just waiting for a useful project. Does HN have better suggestions?

cameron_b 34 minutes ago

desk rover - https://www.huyvector.org/diy-cute-desk-robot-mo-chan

a kid-pleaser at the very least

pacifika an hour ago

Build a synthesizer

brcmthrowaway an hour ago

Why do you have so many? eWaste..

iwontberude 37 minutes ago

No, no, but we insist!