Comment by mittermayr
1 day ago
I wonder how long it'll take (if it hasn't already) until the messaging around this inevitably moves on to "Do not self-host this, are you crazy? This requires console commands, don't be silly! Our team of industry-veteran security professionals works on your digital safety 24/7, you would never be able to keep up with the demands of today's cybersecurity attack spectrum. Any sane person would host their claw with us!"
Next flood of (likely heavily YC-backed) Clawbase (Coinbase but for Claws) hosting startups incoming?
What exactly are they self hosting here? Probably not the model, right? So just the harness?
That does sound like the worst of both worlds: You get the dependency and data protection issues of a cloud solution, but you also have to maintain a home server to keep the agent running on?
"maintain a home server" in this case roughly means "park a headless Mac mini (or laptop or RPi) on your desk"
And you can use a local LLM if you want to eliminate the cloud dependency.
You have spend tens of thousands of dollars on hardware to approach the reasoning and tool call levels of SOTA models...so, casually mentioning "just use local LLM" is out of reach for the common man.
1 reply →
> And you can use a local LLM
That ship has sailed a long time ago. It's of course possible, if you are willing to invest a few thousand dollars extra for the graphics card rig + pay for power.
Wait, why would you still need a home server if the harness (aka, the agent) is hosted in the cloud?
> but you also have to maintain a home server to keep the agent running on
I'm not fascinated by the idea that a lot of people here don't have multiple Mac minis or minisforum or beelink systems running at home. That's been a constant I've seen in tech since the 90s.
Oops, remove 'not'
There are lots of results for "host openclaw", some from VPS SEO spam, some from dedicated CaaS, some from PaaS. Many of them may be profitable.
That Super Bowl ad for AI.com where the site crashed if you went and looked at it... was for a vapor ware OpenClaw hosting service: https://twitter.com/kris/status/2020663711015514399
In a sense, self-hosting it ( and I would argue for a personal rewrite ) is the only way to limit some of the damage.
Yep. Not YC backed, but we're working on this over at LobsterHelper.
ShowHN post from yesterday: https://news.ycombinator.com/item?id=47091792
I wonder how much the clawbase domain name would sell for, hmm
clawbase.ai already is "don't be silly, we've got this for you". Not a promotion, just tried a couple of the domains to see if any were available.
most .ai domains are taken. How I regret not buying watermelon.ai for $85, next day I see it was gone :-(
1 reply →
I already built an operator so we can deploy nanoclaw agents in kubernetes with basically a single yaml file. We're already running two of them in production (PR reviews and ticket triaging)
Great idea, happy to ~steal~ be inspired by.
I propose a few other common elements:
1. Another AI agent (actually bunch of folks in a 3rd-world country) to gatekeep/check select input/outputs for data leaks.
2. Using advanced network isolation techniques (read: bunch of iptables rules and security groups) to limit possible data exfiltration.
3. Advanced orchestration engine (read: crontab & bunch of shell scripts) that are provided as 1st-party components to automate day-to-day stuff.
Any would easily be bypassed by a motivated model able to modify itself to accomplish its objective.
Ironically, even though you were being tongue in cheek, the spirit of those ideas was good.