I primarily "only" use it as a run-manager that can spin up another agent in a tmux which I can then join by ssh on my cell phone. Then, I can monitor the work from my cell phone and choose to either directly interact with the tmux pane or else just message my openclaw agent to do it for me. That right there is the only "killer" app I've found for it. I do also use it to post to my x.com account and that's also pretty useful. Neither of these uses assume any super long context over time will be retained. But, to me, the run-manager use case is pretty great.
OpenClaw’s memory is unreliable, and you don’t know when it will break
91–100 of 196 posts
Re: OpenClaw’s memory is unreliable, and you don’t know when it will break
#92If you look at my comment history, you'll see what seems to be someone defending OpenClaw (even though I stopped using it). I have some issues with the article, but I agree with some of the conclusions: It's great tinkering with it if you have time to spare, but not worth using weeks of your time trying to get a perfect setup. It's just not that reliable to use up so much of your time. I will say, it's still amongst…
> I could tell it (via Telegram) to add something to my TODO list at home while I'm in the office. It would call a custom API I had set up that adds items to my TODO list.
All the existing, commodity todo list apps on the market can't address your use cases?
At least I can't tell there is anything you can't do on your personal phone.
Re: OpenClaw’s memory is unreliable, and you don’t know when it will break
#93Earlier quoted context omitted.
None of those things require openclaw. You could accomplish them with something like Google Drive and Claude Code CLI.
The difference is I would have to do that myself. It has access to gdrive and cc and does it for me when I send it a message in chat. Sometimes when I’m out I even just send it voicys.
Method 1: run Claude Code in YOLO mode and use natural language instructions to get something done
Method 2: send natural language instructions to OpenClaw to use Claude Code to do the same thing
Sorry my tiny brain says to me method 2 is doing the same thing with extra steps
Re: OpenClaw’s memory is unreliable, and you don’t know when it will break
#94You probably don't know how to setup memory.
The killer usecase is letting you make whatever you want, instead of being at the mercy of what your OS/platform dictates.
Your idea of a killer idea is a whatsapp summarizer lol.
Re: OpenClaw’s memory is unreliable, and you don’t know when it will break
#95[flagged]
Re: OpenClaw’s memory is unreliable, and you don’t know when it will break
#96Why aren't databases the solution to many memory problems? Maybe this is a naive question: For example, for the invitations in the OP: Have Openclaw write incoming rsvps to a database, probably a flat file here, and use the db as persistent memory: OpenClaw can compose outgoing update emails based on the database. Don't even suggest to OpenClaws that it try to remember the rsvps - its job is just writing to and readi…
Mostly because it can’t or shouldn’t remember everything - eventually the context window gets too big. But how does it know what to forget and what’s important and should be remembered?
Re: OpenClaw’s memory is unreliable, and you don’t know when it will break
#97From my perspective there are some people that have never built real processes in their life that enjoy having some processes now. But agent processes are less reliable slower and less maintenable then a process that is well-defined and architectured and uses llm’s only where no other solution is sufficient. Classification, drafting, summarizing. I’ve had a Whatsapp assistant since 2023, jailbraked as easy assistant.…
This. So many junior engineers showing me AI flows that could just be a script with a few parameter inputs
Re: OpenClaw’s memory is unreliable, and you don’t know when it will break
#98It would’ve happened eventually anyway, but OpenClaw is basically what kickstarted the beginning of the end of token subsidies. It’s a almost begging to be used wastefully. And agents would miss and lose nothing without it. It’s devoid of a reason to exist.
I don't think this is fair (and I say this as someone who doesn't see much a point of OpenClaw). To me it's very obvious that Claude Code itself is the beginning of the end of token subsidies.
When Claude Code was released, there was a community leaderboard where people competed who could waste the most tokens. Let that sinks.
I know people, especially people who write code, like to blame "the other clueless people" for ruining their cheap token plan. But we're not stuck in the traffic. We're the traffic.
Re: OpenClaw’s memory is unreliable, and you don’t know when it will break
#99From my perspective there are some people that have never built real processes in their life that enjoy having some processes now. But agent processes are less reliable slower and less maintenable then a process that is well-defined and architectured and uses llm’s only where no other solution is sufficient. Classification, drafting, summarizing. I’ve had a Whatsapp assistant since 2023, jailbraked as easy assistant.…
Fully agree with your comment regarding real processes. Being a Six Sigma Black Belt, studying processes and reducing the errors is critical. The Openclaw processes at the moment scare me.
Make a skill.md called six sigma black belt audit refactor and publish it
Re: OpenClaw’s memory is unreliable, and you don’t know when it will break
#100If you look at my comment history, you'll see what seems to be someone defending OpenClaw (even though I stopped using it). I have some issues with the article, but I agree with some of the conclusions: It's great tinkering with it if you have time to spare, but not worth using weeks of your time trying to get a perfect setup. It's just not that reliable to use up so much of your time. I will say, it's still amongst…
i would just enterit in the todo app on my phone.