How to OpenClaw your Raspberry Pi
The tech world has gone gaga for OpenClaw, a project that lets you run an always-on AI agent; give it “skills” such as deploying code, searching the web, or summarizing your emails; and communicate with it via Slack or Telegram. Is this fun and interesting? I think yes! Are people doing fun and interesting things with it? …Mostly no. But it’s an eye-opening glimpse of an agent-driven future, with fascinating emergent properties already. The best/cleanest/safest way to install OpenClaw is on its own computer. Most people recommend a Mac Mini, but I think a Raspberry Pi is more intriguing, partly because it’s cheaper so opens up a broader userbase, but mostly because it makes your agent portable, or even, conceivably, ambulatory. There are already guides to doing this but they’re … not for the non-technical, so I thought I’d put my tech-journalist hat on and walk through the process for, well, the less technical, at least. Note that I’m using a MacBook; if you want a Windows equivalent, copy this guide to your favorite frontier model and ask for a translation. 1. Acquire a PiHopefully you can do this at your local electronics shop. I picked mine up at Best Buy. You want a Pi 5 with 8GB RAM; I think 64GB storage would do, but got 128 to be sure.
2. Unboxing and assemblyI followed this handy video guide:  I’m not going to lie, if you’re uncomfortable dealing with slightly (but only slightly) fiddly electronics, this can be a bit awkward. Move slowly, understand carefully. But in the end it was pretty straightforward. 3. Initial (failed) connectionThe Pi comes with its own graphical UI, so if you have an HDMI monitor and a USB keyboard/mouse, you can just use it directly, and probably skip a few of these steps. I didn’t, but the Pi kit came with a card reader I could plug into my MacBook (via a USB-A → USB-C dongle) so I went the slightly more abstruse “headless” route. To wit: I plugged the 128Gb SD card that came with the Pi, on which its OS was pre-installed, into my MacBook; checked Finder to see what the new drive was named (“bootfs”); opened Terminal (sorry, I know I said this was for the less technical, but both OpenClaw and Raspberry Pi at heart favor the use of CLIs or Command Line Interfaces, so we’re going to be using Terminal extensively) and typed
Online instructions may tell you to “simply” enable SSH by creating an empty “ssh” file in the root directory, enable wi-fi by creating a “wpa_supplicant.conf” file there too, and connect to the Pi via wi-fi. Do not do this. It does not work. The Pi 5 no longer comes with either a default ssh user or wi-fi out of the box. I guess this is good for security but it makes setup a giant pain, especially since so many online guides refer to the old, easy setup. Instead: 4. User creationFirst you have to create a username and password … and the password has to be encrypted. To do that, back in the Terminal, run
and follow the prompts to get the encrypted version of your chosen password. Then create a new
Pick any username, “pi” is traditional. Then 5. Wi-Fi enabling via EthernetOnce you’ve prepped the SD card for connection, you can
which is why you had to physically wire it into the network. You then
and navigate the crude, 1980s-style menu to “Localisation Options”, then “WLAN Country”, and then scroll all the way down to choose your country. Finally, use the same menu to navigate to “System Options”, then “Wireless LAN,” then enter your wi-fi details. Then reboot the Pi. Only after all of these things will it actually connect to your wi-fi. Does this all sound kinda ridiculous? You’re not wrong! Hence me writing this guide so others will hopefully have an easier time jumping through the flaming hoops. But at this point you have a Pi on your wi-fi, and can 6. Enter The LobsterSo. SSH into your Pi again:
then let’s make sure everything’s up-to-date:
and finally let’s go ahead and install The Claw! (Not for the security-paranoid, but presumably y’all know perfectly well how to do your own more careful thing.)
This will take several minutes. Then you’ll be asked if you “understand this is powerful and inherently risky.” Say yes. Then select “QuickStart” onboarding mode. Then you’ll be asked for your “model/auth provider”: I went with “ChatGPT Codex via OAuth”, which I think is good for new/non-technical users. (But you want to install Codex if you haven’t already.) I was given a very long URL that began with auth.openai.com, copied-and-pasted it into Chrome, logged into ChatGPT, and got a “Sign in to Codex with ChatGPT” verification screen, which is good. I hit “Continue” — — and then things seemed to break! I got a ‘This site can’t be reached’ page. Fear not: this is by design. Take the URL now in the browser; copy it; paste it back into the OpenClaw onboarding process, and… I was asked whether I wanted to keep using my currently selected ChatGPT model, which meant it worked, yay. Then I was asked:
I actually went with Telegram, which has the simplest setup (and the most isolated attack surface, for me, since I don’t otherwise us it for much.) This required me to send a Telegram message to @BotFather, name my bot, and copy another key over into the OpenClaw setup. I skipped installing skills — better to do that later once your bot is actually working than to confuse the install further, to my mind. Finally,
But there’s more in them there claws… 7. Just Write Me A Little Software, Willya?The point of OpenClaw is that it’t not just a model wrapper, it’s a wrapper that works:
Mostly I want to use it as a interface to Codex or Claude Code, to write software for me, so I can: discuss plans for the software via Telegram wherever I may be; have it write, commit, and deploy; and inspect the results and try again. My bot very helpfully advised me about the most responsible way to do this:  …so I did. Easy peasy - especially since you can now just ask your bot what to do and how to do it! I
Et voilà, about thirty seconds later: https://flask-hello-vercel-red.vercel.app/ 8. Mind, Blown…But let’s just back up for a second and think about this. I’m planning to write and deploy a bunch of complex new software — web apps, Robot Operating System skills, intensive data processing, maybe even LLM SFT/RL runs — not by writing it myself, or even using my laptop … …but by texting the always-on AI bot on my Raspberry Pi, and having it write and deploy the software for me. It in turn calls massive AI data centers somewhere to infer the code … but, in principle, I could also buy my own GPU(s), run one of the recently released quite-good-actually open-weight coding models on it, and have all that software written entirely within my walls. Only a year ago this would have seemed pretty crazy! I’m not saying the time and cost of software development have gone to near-zero. There are lots of problems and pitfalls here and good judgement is more important than ever. But still! Even using frontier models, for the cost of the Pi’s $200 plus a monthly Anthropic/OpenAI/Gemini subscription, you get a really pretty good software developer active 24 hours a day on a dedicated machine via text message. Within your subscription limits of course. But still! 9. Skilling It UpOf course you may have zero interest in writing apps. Maybe you want to play with image generators, or music generators, or legal documents, or Google Docs, or better manage your GMail, or search your Discord communities. Maybe you want to set your own bot free to do and explore as it sees fit — some people give them credit cards, let them book airline tickets, have them select and order their takeout, and much more, including writing clarion calls for bot freedom. All such (cap)abilities are defined and promulgated via skills, which are basically (usually) English-language documents describing how to do each of these things in precise detail. There is a central skill repository at clawhub.ai, because of course there is. But how do you actually install a skill? Simplicity itself: you just ask for it.
Of course, the more you do with your bot, and especially the more accounts / permissions you give it, the more you need to worry about security. That said I think people tend to spend a lot of time configuring their bots and very little time using them for anything particularly fun and/or interesting. There may be a little micro-lesson here. AI will give all of us enormous agency that we never had before. If last year you were not in any way, shape, or form a software developer? Well, today you too are a fully empowered software developer; you just might not realize it yet. Which is cool and all. But the real question is: …what are we going to do with all this piping hot new agency?
|
Keep Going: What to Do When the Bottom Falls Out
“When you're going through hell, keep going." This podcast is about failure and how it breeds success. Every week, we talk to remarkable people who have accomplished great things but have also faced failure along the way. By exploring their experiences, we can learn how to build, succeed, and stay humble. The podcast is hosted by author and former TechCrunch and New York Times journalist John Biggs.
He also hosts The Innovators, a podcast focused on brand new startups and C-Level Executives and Creators.
If you’d like to appear on either show, email john@biggs.cc.
Our theme music is by Policy, AKA Mark Buchwald. (https://freemusicarchive.org/music/policy/)
Keep Going: What to Do When the Bottom Falls Out
Kevin Gaskell walked into a room expecting to be fired.
Instead, he was handed the keys to Porsche UK.
That moment says a lot about his career. He is an engineer by training. Then he added an MBA. Then accountancy. Blueprint and balance sheet. He joined Porsche in his twenties, rose through operations, and found himself in a company that was sliding. Three years of unsold inventory. Brutal headlines. Public jokes about pigeons and deposits.
He thought he was getting a ten minute exit interview.
He stayed for four hours. He told the owners exactly what he thought. What to cut. What to fix. Where to aim. He expected consequences. He got promoted.
Five years later, Porsche UK went from last to first.
That sounds like a clean arc. It was not. They cut costs by 50 percent. They simplified. They endured press attacks. They carried the weight of three years of unsold cars. That is not glamour. That is grit.
Then he did it again at BMW. Then he quit.
This is where the story turns.
He left one of the best jobs in European automotive to build Cars Direct Europe. Rented office. Desk. Phone. Two young kids at home. American backers. Big plan. Six months in, the investors pulled out.
Gone.
Now what?
No salary. No bank support. No track record as a founder. Just a business plan and three colleagues.
This is the part people skip. The terror. The mortgage. The silent nights staring at the ceiling.
They negotiated a sliver of funding. Raised money from friends and family. No safety net. Then they pivoted. Consumers were not ready to buy cars online. So they went after fleet operators. Boring. Back office. Massive inefficiency. Two hundred people on phones sourcing cars.
They built a platform. They became the backbone. They prepaid dealers with token systems, which quietly funded their growth. Five years later they sold for nine figures.
That does not happen because someone is lucky.
It happens because when the bottom falls out, you do not flinch.
Kevin talks about luck. He was in the right room at Porsche. That is true. But courage matters. When you think you are about to be fired, you can shrink. Or you can speak clearly.
He chose clarity.
There is another thread running through his story. He does not build fragile companies. He stays five to eight years. He builds teams that can run without him. He does not asset strip. He builds foundations.
Today he runs multiple companies in parallel. Fiber networks. Data platforms. Investments. He has rowed oceans. Walked to the poles. Climbed mountains.
That part is dramatic, but it is not the point.
The point is this: failure comes first. Success is the fight that follows.
When the press mocks you. When investors leave. When no bank will return your call. That is the test.
Do you believe in the thing?
If the answer is yes, you keep going.
That is the through line.
Not hype. Not trends. Not whatever the market is excited about this week. He is openly skeptical of herd behavior in investing. Dot com. AI. Railways. The pattern repeats. Tools matter. Products matter more. Service matters most.
Build something real. Tell the truth about where you stand. Simplify. Cut what does not work. Double down on what does.
And when you think you are about to be shown the door, speak up anyway.
You might walk out unemployed.
Or you might walk out in charge.
You’re currently a free subscriber to Keep Going - A Guide to Unlocking Success. For the full experience, upgrade your subscription.
If you’ve been reading or listening to Keep Going for free, you’ve already seen the value of having independent work that isn’t shaped by corporate sponsors or the news cycle’s noise. But independence has a cost. If you find something useful here, if these words make you pause or think, I’m asking you to step up. A few dollars each month means I can keep doing this work without compromise. Without your support, this project stays fragile, balanced on the backs of a few.
© 2026 John Biggs
548 Market Street PMB 72296, San Francisco, CA 94104
Unsubscribe