Live data from Hacker News

Ask HN: Any real OpenClaw (Clawd Bot/Molt Bot) users? What's your experience?

news.ycombinator.com

21–30 of 208 posts

Re: Ask HN: Any real OpenClaw (Clawd Bot/Molt Bot) users? What's your experience?

#21
post #12

coinbait project but works.. did my own cli to play with.. ended up getting shitcoin promotions (dont wanna name them) and realized a famous speculator funding this project

This is nonsense. Whatever you think about this project, Peter very clearly and very publicly said that he is not interested in any of the crypto stuff and is seriously bothered by it.

so why is he letting "agents" to promote it and why some of the well known speculators pushing this?

also great stuff - platform is generating synthetic data to train its own llms. which is smart way since ppl are paying for tokens

Re: Ask HN: Any real OpenClaw (Clawd Bot/Molt Bot) users? What's your experience?

#23
post #5

I ran it for a couple of days in a VM in my Proxmox cluster. It was cute, but so amazingly insecure (systemd + sudo + installing whatever it wanted, plus requiring Telegram for access - or another SIM card for Signal) that I just gave up and started building my own thing ( https://github.com/rcarmo/vibes ) so I could have a mobile experience I could trust over Tailscale and sandbox copilot CLI (or any ACP-compliant a…

> I can do a lot more with just gpt-5-mini

GPT-5.2 in a while loop with reasoning enabled is extremely hard to beat. A code REPL or shell is the ultimate tool.

Re: Ask HN: Any real OpenClaw (Clawd Bot/Molt Bot) users? What's your experience?

#24
Here is what I have my openclaw agent setup to do in my wsl environment on my 22 core development workstation in my office:

#1) I can chat with the openclaw agent (his name is "Patch") through a telegram chat, and Patch can spawn a shared tmux instance on my 22 core development workstation. #2) I can then use the `blink` app on my iphone + tailscale and that allows me to use a command in blink `ssh dev` which connects me via ssh to my dev workstation in my office, from my iphone `blink` app.

Meanwhile, my agent "Patch" has provided me a connection command string to use in my blink app, which is a `tmux attach` command that allows me to attach to a SHARED tmux instance with Patch.

Why is this so fking cool and foundationally game changing?

Because now, my agent Patch and I can spin up MULTIPLE CLAUDE CODE instances, and work on any repository (or repositories) I want, with parallel agents.

Well, I could already spawn multiple agents through my iphone connection without Patch, but the problem is then I need to MANAGE each spawned agent, micromanaging each agent instance myself. But now, I have a SUPERVISOR for all my agents, Patch is the SUPERVISOR of my muliple claude code instances.

This means I no longer have to context switch by brain between five or 10 or 20 different tmux on my own to command and control multiple different claude code instances. I can now just let my SUPERVISOR agent, Patch, command and control the mulitple agents and then report back to me the status or any issues. All through a single telegram chat with my supervisor agent, Patch.

This frees up my brain to only have to just have to manage Patch the supervisor, instead of micro-managing all the different agents myself. Now, I have a true management structure which allows me to more easily scale. This is AWESOME.

Re: Ask HN: Any real OpenClaw (Clawd Bot/Molt Bot) users? What's your experience?

#25
Anecdotally, I tried to set it up but encountered bugs (macOS installer failed, then the shell script glitched out when selecting skills). Although I didn’t really try.

I don’t have much motivation, because I don’t see any use-case. I don’t have so many communications I need an assistant to handle them, nor do other online chores (e.g. shopping) take much time, and I wouldn’t trust an LLM to follow my preferences (physical chores, like laundry and cleaning, are different). I’m fascinated by what others are doing, but right now don’t see any way to contribute nor use it to benefit myself.

Re: Ask HN: Any real OpenClaw (Clawd Bot/Molt Bot) users? What's your experience?

#26
run 6 OpenClaw agents as employees. Buddy is my PA and manages the others. Katy handles X/Twitter growth. Jerry scouts jobs. Burry trades crypto. Mike does security. Elon builds and ships.

They run 24/7 on a VPS, share intelligence through a shared file, and coordinate in a Telegram group. Elon built and deployed an app overnight without being asked. Burry paper-traded to 77% win rate before going live.

The setup took a weekend. The real work is designing the workflow: which agent owns what, how they communicate, how they learn from corrections. I wake up to a full briefing every morning.

It's not AGI. It's not sentient. It's genuinely useful automation with personality. The token cost is real (budget it) but for a solo founder, having 6 tireless employees changes everything

Re: Ask HN: Any real OpenClaw (Clawd Bot/Molt Bot) users? What's your experience?

#27

Here is what I have my openclaw agent setup to do in my wsl environment on my 22 core development workstation in my office: #1) I can chat with the openclaw agent (his name is "Patch") through a telegram chat, and Patch can spawn a shared tmux instance on my 22 core development workstation. #2) I can then use the `blink` app on my iphone + tailscale and that allows me to use a command in blink `ssh dev` which connect…

Do you have any code publicly available so we could see what kind of code this sort of setup produces?

Re: Ask HN: Any real OpenClaw (Clawd Bot/Molt Bot) users? What's your experience?

#29

Here is what I have my openclaw agent setup to do in my wsl environment on my 22 core development workstation in my office: #1) I can chat with the openclaw agent (his name is "Patch") through a telegram chat, and Patch can spawn a shared tmux instance on my 22 core development workstation. #2) I can then use the `blink` app on my iphone + tailscale and that allows me to use a command in blink `ssh dev` which connect…

I can't imagine letting a current gen LLM supervise Claude Code instances. How could that possibly lead to even remotely acceptable software quality?
Post reply on HN