| ▲ | zclaw: personal AI assistant in under 888 KB, running on an ESP32(github.com) |
| 22 points by tosh 9 hours ago | 15 comments |
| |
|
| ▲ | throwa356262 an hour ago | parent | next [-] |
| "LLM backends: Anthropic, OpenAI, OpenRouter." And here I was hoping that this was local inference :) |
| |
| ▲ | micw an hour ago | parent | next [-] | | Sure. Why purchase a H200 if you can go with an ESP32 ^^ | |
| ▲ | __tnm 19 minutes ago | parent | prev | next [-] | | 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 43 minutes ago | parent | prev [-] | | right, 888 kB would be impossible for local inference however, it is really not that impressive for just a client | | |
| ▲ | Dylan16807 28 minutes ago | parent [-] | | 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 39 minutes ago | parent | prev | next [-] |
| 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 | parent | prev | next [-] |
| Serious question: why? What are the use cases and workflows? |
| |
| ▲ | grzracz 9 minutes ago | parent | next [-] | | I don't fully get it either. At least agents build stuff, claws just run around pretending to be alive? | |
| ▲ | milar an hour ago | parent | prev [-] | | for fun! |
|
|
| ▲ | johnea an hour ago | parent | prev [-] |
| I don't really need any assistance... |
| |
