This is a submission for the OpenClaw Writing Challenge
Context
This is going to be short post. The goal is for me is understanding OpenClaw and to see why people use OpenClaw. I did quick research on OpenClaw and I will detail on what I find as a bare bone and why you should not consider OpenClaw yet.
Disclaimer: Take this post as a grain of salt since there is a very good chance that there is something I did not mention about OpenClaw whether it is good or bad since this is researched on a surface level and is based on what I have seen so far.
With that said, to get things out of the way really quick:
I know this sounds contradictory since you read the title to not use OpenClaw from a guy who never uses OpenClaw.
I don't hate it. From what I have seen, I think OpenClaw is a great tool for developers and is accessible for developers getting into AI Agents. However, seeing it rise quite quickly into popularity, it does raise concerns for me and I will tell you why. First, we need to know what OpenClaw is.
Okay, What is OpenClaw?
Based on their official website, it's an AI that does things. In other words, it's literally Jarvis from Iron Man. It can read/write emails for you, open browsers, build and use your GitHub to host a website...pretty much anything a human can do using a computer. If you can do a task on a computer, OpenClaw can do it.
On paper, this sounds legendary. An AI agent that can do anything?
Heck Yea!
Gone with the days where we use GitHub Copilot to do programming tasks.
However, if you think about it, it sounds very scary since OpenClaw can do anything. Even though it is scary, there are positives that I can give credit to OpenClaw.
Good Side of OpenClaw
Here are some good things I heard about OpenClaw!
1. Open Source!
From the name itself "OpenClaw", one would assume it is Open Sourced, which it is! Their repository has over 300k Stars and a lot of people are contributing to it. It's great to see it open source because it gives people transparency, especially when it's an AI agent that can do anything. Puts away the stress if you are worried about a program doing malicious things. Feel free to visit their repository for more details!
🦞 OpenClaw — Personal AI Assistant
EXFOLIATE! EXFOLIATE!
OpenClaw is a personal AI assistant you run on your own devices It answers you on the channels you already use. It can speak and listen on macOS/iOS/Android, and can render a live Canvas you control. The Gateway is just the control plane — the product is the assistant.
If you want a personal, single-user assistant that feels local, fast, and always-on, this is it.
Supported channels include: WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, BlueBubbles, IRC, Microsoft Teams, Matrix, Feishu, LINE, Mattermost, Nextcloud Talk, Nostr, Synology Chat, Tlon, Twitch, Zalo, Zalo Personal, WeChat, QQ, WebChat.
Website · Docs · Vision · DeepWiki · Getting Started · Updating · Showcase · FAQ · Onboarding · Nix · Docker · Discord
New install? Start here: Getting started
Preferred setup: run openclaw onboard in your terminal
OpenClaw Onboard guides you step by step…
2. Easy to set up!
With being open source, they also have documentation for setting up OpenClaw! It's free, can host it locally, and you are open to use OpenRouter to add your API keys into OpenClaw, so you can manage your token usage.
3. Partnered with VirusTotal for Security!
On their page, they mentioned that they recently partnered with VirusTotal for security. They mention the importance of it, but the thing that is important is sensitive information, which they covered on their blog:
Feel free to read more about it here: https://openclaw.ai/blog/virustotal-partnership
What's the issue?
If OpenClaw is in a good spot at the moment, what's the issue?
The issue isn't the progress they are making. Don't get me wrong, right now, they are making good progress on fixing the issues, it's open source, and taking security seriously. It comes down to these things in my opinion that stops me from using OpenClaw.
1. An AI that does...anything
When it comes into being a programmer, you will have to take some risks such as npm installing packages to your computer and other things you need. I am conformable with this since I am aware of what I am installing.
I am currently not conformable with an AI agent doing the tasks and doing things in the background that I am not aware of. I like to be aware of things of what the AI agent is doing. Now, you may be asking:
What's different from GitHub Copilot CLI?
I might not be using it to the fullest potential, but the way I used it, it is more sand boxed. By that, I mean that I used the CLI in my Visual Studio Code only. It's more focused and If I asked anything, the minimum it will do is asking permission to search documentation online. I like this simplicity and aware of what the agent is doing and asking for permission every time.
When you have OpenClaw, you can ask to do a task, but it will do whatever it takes to complete that task. Since it is just "out of the open" on your computer, you have to be careful on how you prompt something to the AI Agent, which doesn't sit right with me since I am quite picky on how I word things and making sure the AI agent understand my requests.
You could argue that I should buy a Mac Mini (which seems to be the trend) to use OpenClaw by itself. But..why though?...
It's too much money and It's not my forte to buy a whole new computer just to run an AI agent for that purpose.
2. How much Tokens do you have?
Even running OpenClaw with Ollama, it still takes a lot of space just to run an AI agent. Typically, people will use AI on the cloud for this case which burns tokens...a lot.
I recently asked the Virtual Coffee Community that me and @jarvisscript are in. One person spoke their experience using OpenClaw where that person stated:
I’m using the $20/month ChatGPT subscription to run OpenClaw, and having it use my $200/month Claude subscription to run Claude Code. I definitely wouldn’t pay that much just for OpenClaw, but I already have the Claude subscription for work and OpenClaw is providing me with > $20/month in value so it’s worth it for me to buy the ChatGPT subscription.
If you are okay spending money to get the best out of OpenClaw, that's totally fine. In my opinion, I like to use free tools and ensuring the expectation of using that tool is worth it.
3. Too early (for me) to trust OpenClaw
Just because it became successful in a short amount of time, it doesn't mean that it is immune for it to fail. You can probably name a good amount of companies and projects being successful early on and quite quickly too, but it resulted in failure for many reasons. I always have this quote in mind:
The quicker the rises, the harder the fall.
I am not saying OpenClaw will fail, I am saying be cautious about the tools that was just release to the public before using it. That tends to be with me whenever I am using any services and tools.
Imagine this, let's say a company rises really quickly and that so many people sign up to use their services. Because of the rise of quick popularity, hackers will see this as an opportunity. If something really bad happens (like a databreach), not only the company will have a bad reputation, but MILLIONS OF DATA will be leak.
This is the worst case scenario. The reason I brought this up is because of what happen to FTX that made me think of this scenario.
Note: FTX did not have a data breach. But the "feeling" of the event that happened is the same (at least for me).
What is FTX and why is it important?
If you don't know, FTX is a crypto exchange that went bankrupt because of fraud. In summary, they lied on their financial report that they claim that they have a lot of money, but in reality, they were in severe debt. As a result, the company went bankrupt and MILLIONS of people lost a lot of money as a result.
Keep in mind that FTX is not a "random" company. It is quite well sponsored and a lot of Online Influencers promote it (even the mainstream media). There were a lot of trust in the community and believe that FTX will keep their money safe, which was not the case.
I hope you can understand where I am coming from. If you would like to learn more, Coffeezilla made a video on why FTX collapsed in detail:
Sure, the example I gave did not align to the FTX incident. What I am trying to say is that in this context for OpenClaw having a vulnerability that affects millions, it is quite scary to think (for an AI agent that does ANYTHING).
I am not stopping you from using OpenClaw if you believe that it hits all the green flags you expect such as being trustworthy, transparency, and such (which seems to be the case with OpenClaw!).
Again, I am saying that the tool is too early for me to use it and I would rather wait a bit before using it to see how it goes, especially in the state of the AI bubble.
Conclusion
Overall, I wouldn't recommend using OpenClaw just yet. I recommend waiting for a bit to see where it goes. Typically, for me, I wait for a year or so to see how far it has gotten. If everything is all good, then I would consider using it.
However, if you are a type of person where you are really bold and want to explore the unknown with zero anxiety, feel free to use it at your own risk. It's just that it doesn't sit right with me having an AI agent that is doing the work with minimum supervision. It's too much of a hassle for me.
Top comments (0)