Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Klaus – OpenClaw on a VM, batteries included

klausai.com

Post reply on HN
Print view View original

81–90 of 104 posts

Re: Show HN: Klaus – OpenClaw on a VM, batteries included

#81

Post by gbro3n »

kennywinker wrote: post #44
jimbob45 wrote: post #32

Earlier quoted context omitted.

Would having a locally-hosted model offset any of these costs?

Yes, but that comes at the cost of using a dumber llm. The state of the art ones are only available via commercial api, and the best self-hostable models require $10,000+ gpus. This is a problem for coding as smarter really has an impact there, but there are so so so many tasks that an 8b model that runs on a $200 gpu can handle nicely. Scrape this page and dump json? Yeah that’s gonna be fine. This is my conclusion…

I saw that the Hetzner matrix like has GPU servers < £300 per month (plus set up fee). I haven't tried it but I think if I was getting up to that sort of spend I'd be setting up Ollama on one of those with a larger Qwen3 max model (which I hear is on par with Opus 4.5?? - I haven't been able to try Qwen yet though so that could be b*****ks).

Re: Show HN: Klaus – OpenClaw on a VM, batteries included

#84

Post by WA »

Frannky wrote: post #80

I found ZeroClaw plus Hetzner to be a good option. I've been using it for a week, and it's stable and robust. Complex abilities unlocked calling a FastAPI server with one skill for each endpoint

FastAPI server on the same Hetzner box? The endpoints are written by ZeroClaw?

Re: Show HN: Klaus – OpenClaw on a VM, batteries included

#86

Post by hhh »

gbro3n wrote: post #81
kennywinker wrote: post #44

Earlier quoted context omitted.

Yes, but that comes at the cost of using a dumber llm. The state of the art ones are only available via commercial api, and the best self-hostable models require $10,000+ gpus. This is a problem for coding as smarter really has an impact there, but there are so so so many tasks that an 8b model that runs on a $200 gpu can handle nicely. Scrape this page and dump json? Yeah that’s gonna be fine. This is my conclusion…

I saw that the Hetzner matrix like has GPU servers < £300 per month (plus set up fee). I haven't tried it but I think if I was getting up to that sort of spend I'd be setting up Ollama on one of those with a larger Qwen3 max model (which I hear is on par with Opus 4.5?? - I haven't been able to try Qwen yet though so that could be b*****ks).

I have tried most of the major open source models now and they all feel okay, but i’d prefer Sonnet or something any day over them. Not even close in capability for general tasks in my experience.

Re: Show HN: Klaus – OpenClaw on a VM, batteries included

#87

Post by raizer88 »

stavros wrote: post #56
raizer88 wrote: post #39

Earlier quoted context omitted.

I am still searching for a compose up -d to this day, but without success. And the other poster want me to create a k8s cluster for a bot?!?!

Try mine: https://github.com/skorokithakis/stavrobot It does indeed only need compose up -d.

Does it support local llm, on openai standard, and out of the box web browsing?

Re: Show HN: Klaus – OpenClaw on a VM, batteries included

#89

Post by stavros »

raizer88 wrote: post #87
stavros wrote: post #56

Earlier quoted context omitted.

Try mine: https://github.com/skorokithakis/stavrobot It does indeed only need compose up -d.

Does it support local llm, on openai standard, and out of the box web browsing?

What's web browsing? Yes on the rest.

Re: Show HN: Klaus – OpenClaw on a VM, batteries included

#90

Post by raizer88 »

stavros wrote: post #89
raizer88 wrote: post #87

Earlier quoted context omitted.

Does it support local llm, on openai standard, and out of the box web browsing?

What's web browsing? Yes on the rest.

Web browsing as give the bot access to the web with an headless chrome install.
Post reply on HN