This is absolutely glorious. We used to talk about "smart devices" and IoT… I would be so curious to see what would happen if these connected devices had a bit more agency and communicative power. It's easy to imagine the downsides, and I don't want my email to be managed from an ESP23 device, but what else could this unlock?
yauneyz [3 hidden]5 mins ago
Genuinely curious - did you use a coding agent for most of this or does this level if performance take hand written code?
throwa356262 [3 hidden]5 mins ago
"LLM backends: Anthropic, OpenAI, OpenRouter."
And here I was hoping that this was local inference :)
micw [3 hidden]5 mins ago
Sure. Why purchase a H200 if you can go with an ESP32 ^^
__tnm [3 hidden]5 mins 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 [3 hidden]5 mins ago
right, 888 kB would be impossible for local inference
however, it is really not that impressive for just a client
Dylan16807 [3 hidden]5 mins 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.
Is there a heartbeat alternative? I feel like this is the magic behind OpenClaw and what gives it the "self-driven" feel.
g947o [3 hidden]5 mins ago
Serious question: why? What are the use cases and workflows?
eleventyseven [3 hidden]5 mins ago
It's just a pipe between LLM APIs and a bunch of other API/CLIs. Like you can have it listen via telegram or Whatsapp for a prompt you send. Like to generate some email or social post, which it sends to the LLM API. Get back a tool call that hits your email or social API.
The reason people were buying a separate Mac minis just to do open claw was 1) security, as it was all vibe coded, so needs to be sandboxed and 2) relay iMessage. If you don't need to relay iMessage, a raspberry pi could host it on its own device.
grzracz [3 hidden]5 mins ago
I don't fully get it either. At least agents build stuff, claws just run around pretending to be alive?
milar [3 hidden]5 mins ago
for fun!
johnea [3 hidden]5 mins ago
I don't really need any assistance...
throwa356262 [3 hidden]5 mins ago
Me neither.
But I have 10-15 ESP32's just waiting for a useful project. Does HN have better suggestions?
HN.zip
And here I was hoping that this was local inference :)
however, it is really not that impressive for just a client
The reason people were buying a separate Mac minis just to do open claw was 1) security, as it was all vibe coded, so needs to be sandboxed and 2) relay iMessage. If you don't need to relay iMessage, a raspberry pi could host it on its own device.
But I have 10-15 ESP32's just waiting for a useful project. Does HN have better suggestions?
a kid-pleaser at the very least