We just launched Hosted OpenClaw Instances with full managed hosting, dashboard, terminal access etc. all for $0.99/mo
And it just takes 30 seconds to set up!
https://t.co/8wf7fxuDLa
Building stateful AI agents is amazing. Dealing with the infrastructure to deploy them? A nightmare☠️
So I turned @an_engineer_log 's new soul saving launch, Agent 37, into a 6-panel slice-of-life comic to show how you can fix it!
(Swipe right 👉or keep reading to see the story 👇)
@Shpigford for anyone wondering what claude did, they basically disabled agent sdk based apps like conductor from using subscription tokens - https://t.co/0n5wSWO2es
1. Easiest to start with apis for devs building on top of openclaw or hermes, cheaper than VPS (7x cheaper than aws), APIs to provision dynamically rather than buying from a clunky UI.
2. Indie devs, startup founders, building agents
3. pain point; no more spending time on infra provisioning for stateful agents, go to market faster
I will soon be introducing a bill to give the public a 50% ownership stake in the largest AI companies in America.
This would guarantee that the trillions created by AI are used to improve the lives of all of us — and block oligarch decisions that harm the American people.
Haha, I love this guy's roasting style !
"I get that business insurance is similar Nobel level type of pursuit as ground breaking physics and the Manhattan project..."
https://t.co/dcANpWTZTy
I get that business insurance is similar Nobel level type of pursuit as ground breaking physics and the Manhattan project. Hopefully the blast radius will be contained.
I don’t think the disagreement is whether hard problems require intensity.
The disagreement is whether intensity has to become a permanent operating model, and whether working seven days a week is the thing that compounds.
My argument is that for most startups, the real compounding advantage is not raw hours. It is clearer thinking, better judgment, learning, and a team that can sustain high-quality work for a long time. You can always spend a lot of time working, but the PMF might never arrive.
There are moments where extraordinary effort is necessary. Launches, incidents, existential deadlines, customer commitments. Those moments matter, and great teams rise to them.
But if the company requires heroics every day of the eek, that usually points to a system problem. It means the operating model depends on burning reserve capacity instead of building it. Company that is constantly on fire is company that is not operating well.
Whenever you put something out there, people will argue and people can argue the way I run Linear. The reason I comment on these things to offer some counter point.
There is a growing cliché in startup culture where founders and startups feel the need to perform intensity publicly. How hard they work, how little they sleep, how many tokens they spend, how busy they are, how much personal sacrifice they make.
You almost never see this from the most successful companies or people. Even if they work that way, they usually don’t make it the story, because they have more important things to talk about, like the product, the customers, the insight, the strategy, the quality of the work.
That’s my issue with the narrative and why I think startups shouldn't blindly follow it. Not that is bad to work hard but grindmaxxing narrative can become the greater goal and become counterproductive. The performative intensity becomes the thing, and loosing sight of what actually matters.
Lets check back in 7 years.
@vincent_koc@EdgeDimi@theo@openclaw This was 2026.5.27
If you're referring to this as fast mode - https://t.co/2oM03IlfjW then no, it was not turned on, but I doubt this was a model latency issue. Something about the harness is taking too long, on smaller spec hosts.
@vincent_koc@EdgeDimi@theo@openclaw You still have a long way to go Vincent, but I am hoping you get there. This was just 2 versions ago btw, and you can see how bad it is..
https://t.co/jZj3b2yV0q
Hermes vs Openclaw on performance.
Openclaw still has a long way to go...
1. This is the latency for first message response on an instance with similar specs.
2. Further adding some channel plugins like whatsapp in Openclaw make it worse.
Back in my 20's I used to dream of the day I had my own Macbook.
I certainly couldn't afford it and years later when I finally got one at work, it was one of the happiest moments of my life.. 😅
https://t.co/fJ9Q9zYue3