Live data from Hacker News

Moltworker: a self-hosted personal AI agent, minus the minis

blog.cloudflare.com

41–50 of 74 posts

Re: Moltworker: a self-hosted personal AI agent, minus the minis

#41

These breathy blogposts are getting way ahead of their service uptime. Advertising CF Workers while your CF Worker fleet is under impact is certainly a vibe > Workers Rate limit Degradation > Update - We are continuing to work on a fix for this issue. https://www.cloudflarestatus.com/incidents/dk0d6pjt9vjx

I wouldn't think the blog writers are the same engineers dealing with the rate limit degradation.

Re: Moltworker: a self-hosted personal AI agent, minus the minis

#42

There is so much branding and "look at our success" marketing that this project comes off as heavily astro-turfed. Im sure in a month or two we will hear about the new startup the developers are making around this tool. Ultimately its a convenience wrapper that makes it easy to wire up Claude or Chatgpt to a chat platform like discord, but its claiming to be far more revolutionary for reasons I dont yet know.

Yeah, Anthropic must love that people are sharing access to their entire online lives with them.

Re: Moltworker: a self-hosted personal AI agent, minus the minis

#43
post #40

It's certainly easier than setting up and maintaining a VPS and probably less expensive for most users, but your data is not private. Cloudflare can always read everything that goes through Moltworker and its attached storage. Hosting Moltbot on your own hardware reigns supreme.

I think if you care about privacy and security, you wouldn't run moltbot in the first place (or wouldn't give it access to anything you wanted to keep private).

Re: Moltworker: a self-hosted personal AI agent, minus the minis

#44
post #40

It's certainly easier than setting up and maintaining a VPS and probably less expensive for most users, but your data is not private. Cloudflare can always read everything that goes through Moltworker and its attached storage. Hosting Moltbot on your own hardware reigns supreme.

I think if you care about privacy and security, you wouldn't run moltbot in the first place (or wouldn't give it access to anything you wanted to keep private).

That overstates it a bit. Yeah, it's mostly vibe-coded and the main dev has publicly said he has yet to review the reported vulnerabilities. I am aware that it can be easily pwned with prompt injection from its data sources.

I'm running it on my old Mac mini right now and I have not given it access to untrusted inputs like my email inbox. It only has access to my filesystem (synced to my laptop with Syncthing), local applications like Apple Reminders, and OpenRouter. I already find it useful for augmenting web searches with stuff that's in my Obsidian vault.

Re: Moltworker: a self-hosted personal AI agent, minus the minis

#45

There is so much branding and "look at our success" marketing that this project comes off as heavily astro-turfed. Im sure in a month or two we will hear about the new startup the developers are making around this tool. Ultimately its a convenience wrapper that makes it easy to wire up Claude or Chatgpt to a chat platform like discord, but its claiming to be far more revolutionary for reasons I dont yet know.

Yeah, Anthropic must love that people are sharing access to their entire online lives with them.

Probably more glad that people are paying subscription fees to do digital assistant stuff... without them having to directly provide the assistant interface. That way they won't be directly blamed for the wave of hacked accounts from people foolish enough to connect this to their email.

Re: Moltworker: a self-hosted personal AI agent, minus the minis

#47
post #44

Earlier quoted context omitted.

I think if you care about privacy and security, you wouldn't run moltbot in the first place (or wouldn't give it access to anything you wanted to keep private).

That overstates it a bit. Yeah, it's mostly vibe-coded and the main dev has publicly said he has yet to review the reported vulnerabilities. I am aware that it can be easily pwned with prompt injection from its data sources. I'm running it on my old Mac mini right now and I have not given it access to untrusted inputs like my email inbox. It only has access to my filesystem (synced to my laptop with Syncthing), local…

If you’re letting it access websites then presumably it’s open to prompt injection from those sites you’re accessing? I guess the attack surface is reduced if it doesn’t have access to anything useful beyond that.

Re: Moltworker: a self-hosted personal AI agent, minus the minis

#48

Clawdbot/Moltbot looks to be a supply-chain attack waiting to happen, and I pity the poor soul who finds out when this ticking time bomb eventually detonates.

That’s what first came to my mind, the multiple integrations and cascaded connections probably will introduce multiple attack vectors. But, what’s the hype with motlbot anyway? I can just open any AI app and ask whatever, especially moltbot already uses the same AI vendors.

Re: Moltworker: a self-hosted personal AI agent, minus the minis

#49
post #4

On one hand, with the top comments of the rebrand post showing how many insecure deployments there are, something like this alongside cloudflare zero trust is probably a much more secure solution. On the other hand, I just wanna point out > Firstly, Cloudflare Workers has never been so compatible with Node.js. Where in the past we had to mock APIs to get some packages running, now those APIs are supported natively by…

Yep I had the same experience with Astro a couple years ago. Tried to deploy to Cloudflare and it was not working so ended up with Netlify. Tried again a few months ago and it worked flawlessly. Funny enough, they have since "bought" Astro and so I only expect it to get better

Re: Moltworker: a self-hosted personal AI agent, minus the minis

#50

There is so much branding and "look at our success" marketing that this project comes off as heavily astro-turfed. Im sure in a month or two we will hear about the new startup the developers are making around this tool. Ultimately its a convenience wrapper that makes it easy to wire up Claude or Chatgpt to a chat platform like discord, but its claiming to be far more revolutionary for reasons I dont yet know.

I'm not sure it's astroturfed exactly; but the hype is not coming from technical professionals. Like you find a linkedin post with a thousand likes about this or similar projects, and everybody is either #opentowork or ~~Agentic Head of AI Brainstorming at My Bedroom~~ Also clawdbot is objectively a pretty inconvenient way to hook Claude Code up to a chat app. I made a bare-bones one that takes 2 minutes to run with…

So if I have CC running say on a VPS then that's where your thing needs to run too right?
Post reply on HN