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

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

news.ycombinator.com

Post reply on HN
Print view View original

51–60 of 208 posts

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

#51

Post by bobjordan »

isatty wrote: post #43
bobjordan wrote: post #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 connect…

I don’t get it, and that doesn’t mean it’s not a bad thing necessarily. I’ve been doing systems things for a long time and I’m quite good at it but this is the first time none of this excites me.

Instead of sitting in my office for 12 hours working with 20 open terminals (exactly what I have open right now on my machine). I can take my kids to Disneyland (I live in Southern California and it's nearby) and work on my iphone talking to "Patch" while we stand in line for an hour to get on a ride. Meanwhile. my openclaw agent "Patch" manages my 20 open terminals on my development workstation in my office. Patch updates me and I can make decisions, away from my desk. That should excite anyone. It gives me back more of my time on earth, while getting about the same (or more) work done. There is literally nothing more valuable to me than being able to spend more time away from my desk.

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

#52

Post by harmoni-pet »

I'm running it on an old MacBook that I wiped a few months ago and had lying around. I tried installing it on an old raspberry pi first, but it was super slow and the skills ecosystem wants to use brew which doesn't work so well on the pi.

First impressions are that it's actually pretty interesting from an interface perspective. I could see a bigger provider using this to great success. Obviously it's not as revolutionary as people are hyping it up to be, but it's a step in the right direction. It reimagines where an agent interface should be in relation to the user and their device. For some reason it's easier to think of an agent as a dedicated machine, and it feels more capable when it's your own.

I think this project nails a new type of UX for LLM agents. It feels very similar to the paradigm shift felt after using Claude Code --dangerously-skip-permissions on a codebase, except this is for your whole machine. It also feels much less ephemeral than normal LLM sessions. But it still fills up its context pretty quickly, so you see diminishing returns.

I was a skeptic until I actually installed it and messed around with it. So far I'm not doing anything that I couldn't already do with Claude Code, but it is kind of cool to be able to text with an agent that lives on your hardware and has a basic memory of what you're using it for, who you are, etc. It feels more like a personal assistant than Claude Code which feels more like a disposable consultant.

I don't know if it really lives up to the hype, but it does make you think a little differently about how these tools should be presented and what their broader capabilities might be. I like the local files first mentality. It makes me excited for a time when running local models becomes easier.

I should add that it's very buggy. It worked great last night, now none of my prompts go through.

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

#53

Post by woeirua »

bobjordan wrote: post #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 connect…

This just sounds ridiculously expensive. Burning hundreds of dollars a day to generate code of questionable utility.

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

#54

Post by cvhc »

xur17 wrote: post #49

I have it installed in a VM, and overall it's fairly useful, but very buggy. Right now I can send it a message asking it something, and it won't answer. I typically have to follow up 2 or 3 times before I get an actual response. This weirdly used to work fine.

Could you share some of the useful tasks it has successfully done?

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

#56

Post by tomku »

azinman2 wrote: post #14
haebom wrote: post #2

This is my honest personal experience. Frankly, I feel like this is just a toy—nothing more, nothing less. It's fun to play with and entertaining, but it feels like a trend for people who “don't really understand AI but want to feel like they're using it” or “want to jump on the AI bandwagon” to dabble with once. While using it, I feel that “Oh~” moment of fun, but it doesn't make me want to keep using it. Maybe it j…

If it’s a local model, why would you care if it sees your messages or notes?

https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/

Note that nothing about that depends on it being a local or remote model, it was just less of a concern for local models in the past because most of them did not have tool calling. OpenClaw, for all the cool and flashy uses, is also basically an infinite generator for lethal trifecta problems because its whole pitch is combining your data with tools that can both read and write from the public internet.

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

#57

Post by xur17 »

cvhc wrote: post #54
xur17 wrote: post #49

I have it installed in a VM, and overall it's fairly useful, but very buggy. Right now I can send it a message asking it something, and it won't answer. I typically have to follow up 2 or 3 times before I get an actual response. This weirdly used to work fine.

Could you share some of the useful tasks it has successfully done?

I am hunting for houses - I've used it as an assistant that catalogs them (but it has this stored in multiple places and will give me the wrong list a lot). I also had it read through my emails and create a doc with my upcoming trips.

I'd say it's right on the edge of being useful, but given the number of bugs, it's not really that practically useful. It's moreso a glimpse into the future.

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

#58

Post by bobjordan »

vanviegen wrote: post #29
bobjordan wrote: post #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 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?

I spec out everything in excruciating detail with spec docs. Then I actually read them. Finally, we create granular tasks called "beads" (see https://github.com/steveyegge/beads). The beads allows us to create epics/tasks/subtasks and associated dependency structure down to a granular bead, and then the agents pull a "bead" to implement. So, mostly we're either creating spec docs and creating beads or implementing, quality checking, and testing the code created from an agent implementing a bead. I can say this produces better code than I could write after 10yrs of focused daily coding myself. However, I don't think "vibe coders" that have never truly learned to code, have any realistic chance of creating decent code in a large complex code base that requires a complex backend schema to be built. They can only build relatively trivial apps. But, I do believe what I am building is as solid as if I had a millions of dollars of staff doing it with me.

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

#59

Post by helpfulclippy »

I've been messing with it the past couple days. I put it in a VM, on an untrusted subnet I keep around for agentic stuff. I see promise, but I'm not especially impressed right now.

1) Installation on a clean Ubuntu 24.04 system was messy. I eventually had codex do it for me.

2) It has a bunch of skills that come packaged with it. The ones I've tried do not work all that well.

3) It murdered my codex quota trying to chase down a bug that resulted from all the renames -- this project has renamed itself twice this week, and every time it does, I assume the refactoring work is LLM-driven. It still winds up looking for CLAWDBOT_* envvars when they're actually being set as OPENCLAW_*, or looking in ~/moltbot/ when actually the files are still in ~/clawdbot.

4) Background agents are cool but sometimes it really doesn't use them when it should, despite me strongly encouraging it to do so. When the main agent works on something, your chat is blocked, so you have no idea what's going on or if it died.

5) And sometimes it DOES die, because you hit a ratelimit or quota limit, or because the software is actually pretty janky.

6) The control panel is a mess. The CLI has a zillion confusing options. It feels like the design and implementation are riddled with vibetumors.

7) It actively lies to me about clearing its context window. This gets expensive fast when dealing with high-end models. (Expensive by my standards anyway. I keep seeing these people saying they're spending $1000s a month on LLM tokens :O)

8) I am NOT impressed with Kimi-K2.5 on this thing. It keeps hanging on tool use -- it hallucinates commands and gets syntax wrong very frequently, and this causes the process to outright hang.

9) I'm also not impressed with doing research on it. It gets confused easily, and it can't really stick to a coherent organizational strategy over iterations.

10) also, it gets stuck and just hangs sometimes. If I ask it what it's doing, it really thinks it is doing something -- but I look at the API console and see it isn't making any LLM requests.

I'm having it do some stuff for me right now. In principle, I like that I can have a chat window where I can tell an AI to do pretty unstructured tasks. I like the idea of it maintaining context over multiple sessions and adapting to some of my expectations and habits. I guess mostly, I'm looking at it like:

1) the chat metaphor gave me a convenient interface to do big-picture interactions with an LLM from anywhere; 2) the terminal agents gave the LLMs rich local tool and data use, so I could turn them loose on projects; 3) this feels like it's giving me a chat metaphor, in a real chat app, with the ability for it to asynchronously check on stuff, and use local stuff.

I think that's pretty neat and the way this should go. I think this project is WAY too move-fast-and-break-things. It seems like it started as a lark, got unexpected fame, attracted a lot of the wrong kinds of attention, and I think it'll be tough for it to turn into something mature. More likely, I think this is a good icebreaker for an important conversation about what the primetime version of this looks like.

Post reply on HN