Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

I deployed Open SaaS to OpenShip (OpenShip)! It was my first time successfully self-hosting an app on a Hetzner VPS. The video below summarises what it took to get it done, and some of my thoughts on the process and platform, e.g.: - Server: Hetzner CPX22 4GB RAM, 80GB... disk, with Ubuntu 24.04 -> $23/month - Create an SSH key locally, add it in Hetzner, and set up firewall rules - Add the server in OpenShip - Buy domain, point it at VPS - Write a Docker Compose file and Dockerfiles so OpenShip would deploy all three parts of Open SaaS stack (react, expressjs, postgres) as one unit - Set Env Vars - Add domain TXT records and get SSL certs Things I like: - Auto-deploy from GitHub pushes. - OpenShip handles domains, certs, and SSL provisioning for you. - Built-in jobs and backups: nightly database backups called out as a genuinely cool feature. - Satisfaction of ending up with a fully self-hosted SaaS. Things I didn't like: - The "$5/month VPS" everyone talks about wasn't actually available in any region. Ended up at $23/month. SAD. - OpenShip is still in beta and I hit multiple bugs. - Deploying anything multi-service isn't a first class citizen on OpenShip yet / requires hand-writing Docker config. - Whether to run your own mail server on a VPS is contested. Verdict: - At $23/month, managed hosting providers still look like better value until you have serious traffic, given how little you have to think about. - Would use it for hobby apps and small projects; wouldn't put an important or high-traffic SaaS on it yet until I trust OpenShip more and understand self-hosting better.show more

Vinny

5,757 subscribers

65,179 views • 11 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

I'm now building Executor full time as a startup! The state of tool calling is a mess: - Everyone is using different agents - You have no idea what actions are going to run - Destructive actions are treated the same as normal Executor lets you set up everything once & use it with any agent. You're able to control what tools can be called, require approval on destructive actions, and invite your team to all use them. Under the hood, it's built on codemode to let you add thousands of tools with 0 context bloat. I've been using it for a month so far and it has completely changed how I interact with agents. There's so much to be built here, immediately next up on the roadmap is workspaces, skills, workflows, and generative ui. Everything is being built open source over at there's a lot more coming on an SDK to embed it into your own agents, a self hostable cloud app, and plugins There's an early beta version over at It's very early on - if you hit any bugs let me know and I'll get them fixed up, excited to share more as I build it!

I'm now building Executor full time as a startup! The state of tool calling is a mess: - Everyone is using different agents - You have no idea what actions are going to run - Destructive actions are treated the same as normal Executor lets you set up everything once & use it with any agent. You're able to control what tools can be called, require approval on destructive actions, and invite your team to all use them. Under the hood, it's built on codemode to let you add thousands of tools with 0 context bloat. I've been using it for a month so far and it has completely changed how I interact with agents. There's so much to be built here, immediately next up on the roadmap is workspaces, skills, workflows, and generative ui. Everything is being built open source over at there's a lot more coming on an SDK to embed it into your own agents, a self hostable cloud app, and plugins There's an early beta version over at It's very early on - if you hit any bugs let me know and I'll get them fixed up, excited to share more as I build it!

Rhys

220,131 views • 2 months ago

✨ A dream I had finally came true: I can now chat directly with my sites to build any feature or fix any bug just via Telegram I've been playing with OpenClaw for 3 weeks now and it's great but I was always too scared to run it on any production server And I was right a bit as Marc Köhlbrugge was able to hack it by social engineering and acting as if it was me, and with enough tries it believed him, and was able to modify the server, change SSH keys etc. of course I had it isolated properly on its own VPS and it didn't touch anything sensitive (as it should!) Marc then reported that bug to Peter Steinberger 🦞 who patched it fast But I wanted to try something more basic and simple, and I think maybe more secure: to just connect Claude Code on my server to Telegram which would be hard locked to only messages from me So I installed claude-code-telegram by Richard Atkinson on the server and run it as a system daemon and it works really well The cool thing is that I was already using Telegram for server errors like this: > Photo AI - ❌ Random credits giveaway failed (Attempt 30/30) with an exception: SQLSTATE[HY000]: General error: 5 database is locked So now I can just reply, "Ok fix this", and Claude Code on the server in production will try (and probably succeed) in fixing it In the video below I asked it to make show [🌳 Parks ] on the map by default on load, it did that, then I reloaded the page and it instantly worked One thing it still needs is sending actual messages while it's doing stuff which OpenClaw does really well, it's annoying to just wait while it says "Working..." but that's probably next

✨ A dream I had finally came true: I can now chat directly with my sites to build any feature or fix any bug just via Telegram I've been playing with OpenClaw for 3 weeks now and it's great but I was always too scared to run it on any production server And I was right a bit as Marc Köhlbrugge was able to hack it by social engineering and acting as if it was me, and with enough tries it believed him, and was able to modify the server, change SSH keys etc. of course I had it isolated properly on its own VPS and it didn't touch anything sensitive (as it should!) Marc then reported that bug to Peter Steinberger 🦞 who patched it fast But I wanted to try something more basic and simple, and I think maybe more secure: to just connect Claude Code on my server to Telegram which would be hard locked to only messages from me So I installed claude-code-telegram by Richard Atkinson on the server and run it as a system daemon and it works really well The cool thing is that I was already using Telegram for server errors like this: > Photo AI - ❌ Random credits giveaway failed (Attempt 30/30) with an exception: SQLSTATE[HY000]: General error: 5 database is locked So now I can just reply, "Ok fix this", and Claude Code on the server in production will try (and probably succeed) in fixing it In the video below I asked it to make show [🌳 Parks ] on the map by default on load, it did that, then I reloaded the page and it instantly worked One thing it still needs is sending actual messages while it's doing stuff which OpenClaw does really well, it's annoying to just wait while it says "Working..." but that's probably next

@levelsio

642,242 views • 5 months ago

I built a mobile app to check Paddle revenue (because they don't have one): 👉 - Use your Paddle API key (read-only and scoped) - Live data with beautiful and useful graphs built with native Swift UI. - Multi-account supported, unified revenue metrics. - Data stay on device, no server (api requests are sent directly from your phone) - Home widgets - I made it free to download on App Store (once it's approved) - Buy the source code for $19 and customize it however you want (save 5hrs of prompting if you try to do it yourself). Some interesting facts about this side project: - I vibe coded with 100% claude code remotely on my Mac Mini (with my AI assistant setup) in less than 24 hours. - I have read 0 line of code in this project and never opened Xcode myself. - My AI assistant designed the app with GPT Image 2, built the app with Swift UI, test it on simulator (via screenshots), send the test build to TestFlight for me to test, and invited me to the app store connect account so I can test on my phone, then the AI submitted the app to App Store and currently waiting for approval. - For the website, I ask it to come up with a domain name, I bought it via manually and give it access via Cloudflare API, the AI design and create a static website with GitHub, test it with lighthouse CLI, deploy via GitHub pages, config the domain DNS, deploy the website. - Then I sign up an account with Polar payment, create an API key and ask the AI to setup a store, add payment, link with the account, and add the payment to the website. The entire process happened in the last 24 hours with me only talking to the AI via Telegram. This is such a fun side project not only to create an app that I wish exists, but also to push the limit of what I can use AI for, and so far I'm very impressed. I'll create so much more apps! It feels like I have unlocked a super power.

I built a mobile app to check Paddle revenue (because they don't have one): 👉 - Use your Paddle API key (read-only and scoped) - Live data with beautiful and useful graphs built with native Swift UI. - Multi-account supported, unified revenue metrics. - Data stay on device, no server (api requests are sent directly from your phone) - Home widgets - I made it free to download on App Store (once it's approved) - Buy the source code for $19 and customize it however you want (save 5hrs of prompting if you try to do it yourself). Some interesting facts about this side project: - I vibe coded with 100% claude code remotely on my Mac Mini (with my AI assistant setup) in less than 24 hours. - I have read 0 line of code in this project and never opened Xcode myself. - My AI assistant designed the app with GPT Image 2, built the app with Swift UI, test it on simulator (via screenshots), send the test build to TestFlight for me to test, and invited me to the app store connect account so I can test on my phone, then the AI submitted the app to App Store and currently waiting for approval. - For the website, I ask it to come up with a domain name, I bought it via manually and give it access via Cloudflare API, the AI design and create a static website with GitHub, test it with lighthouse CLI, deploy via GitHub pages, config the domain DNS, deploy the website. - Then I sign up an account with Polar payment, create an API key and ask the AI to setup a store, add payment, link with the account, and add the payment to the website. The entire process happened in the last 24 hours with me only talking to the AI via Telegram. This is such a fun side project not only to create an app that I wish exists, but also to push the limit of what I can use AI for, and so far I'm very impressed. I'll create so much more apps! It feels like I have unlocked a super power.

Tony Dinh

43,922 views • 2 months ago

From Eric Vishria on how the top AI founders are building products completely opposite of the SaaS era: "One of the things that is really different in the AI world versus the SaaS world, is that in the SaaS world, over and over again, you had people who really understood the customer. And the problem. And then they understood a domain. They understood what the technology was more or less capable of. But it wasn't a real question of if you could build something or not. For example, take Salesforce, Workday, and ServiceNow. CRM existed before Salesforce. HR management existed before Workday. Same thing with ServiceNow. So in every case, Salesforce followed Siebel. Workday followed Peoplesoft. ServiceNow followed Peregrine and Remedy, and others. So they were just kind of, cloud SaaS versions of the prior generation product. They just understood the customers. They understood the problem. And they were just like, here's a better version. And that evolved a little bit over time in SaaS land. But that's what it is. And so product development in that way was done by people who really understood the customer and the problems. And then just took advantage of the next wave. And this is almost diametrically opposite of product development in the AI era. When I look at the teams that are having the most success today, they have intimate knowledge of the models. They are right on the frontier of understanding which models are better at what, and why, and when. And what they're going to be good at and what they're not going to be good at. And what they're spending their time on, is figuring out how do I apply this capability of this model to this domain or to this user. So they're actually working inside out or technology out, versus customer problem in. And of course, they understand the customer problem. And a lot of times they have firsthand knowledge of it. But they're really close to the metal and capability, and they're applying it. And I think this is a really different way to develop products than in SaaS. I started my career as a product manager a long time ago, and it's almost the complete opposite of everything you learned. "Listen to the customer, understand it, then bring it back to the engineering and product teams." If you did that right now, ask a bunch of customers what they want out of AI, and you brought it back, for the most part, it may not be possible today with today's technology. Whereas the teams that are winning right now really understand the technology and are applying it out. And so I think this reversal matters. I think it's a big difference in terms of how companies are getting built. And maybe even the types of entrepreneurs that will be successful. I'm not sure. You're seeing some real change there. Look at the Bret Taylor's at Sierra. That's a super, super technical founder who really gets it. Brett and Clay really get it. You look at Michael and his co-founders at Cursor. They're super technical founders and they get it. They all really understand what these things can and can't do. And that's a pretty different dynamic relative to the way the best SaaS companies got built." Link in bio for the full conversation going deep on the current class of startups going from zero to $100m+ in ARR within 12 months.

From Eric Vishria on how the top AI founders are building products completely opposite of the SaaS era: "One of the things that is really different in the AI world versus the SaaS world, is that in the SaaS world, over and over again, you had people who really understood the customer. And the problem. And then they understood a domain. They understood what the technology was more or less capable of. But it wasn't a real question of if you could build something or not. For example, take Salesforce, Workday, and ServiceNow. CRM existed before Salesforce. HR management existed before Workday. Same thing with ServiceNow. So in every case, Salesforce followed Siebel. Workday followed Peoplesoft. ServiceNow followed Peregrine and Remedy, and others. So they were just kind of, cloud SaaS versions of the prior generation product. They just understood the customers. They understood the problem. And they were just like, here's a better version. And that evolved a little bit over time in SaaS land. But that's what it is. And so product development in that way was done by people who really understood the customer and the problems. And then just took advantage of the next wave. And this is almost diametrically opposite of product development in the AI era. When I look at the teams that are having the most success today, they have intimate knowledge of the models. They are right on the frontier of understanding which models are better at what, and why, and when. And what they're going to be good at and what they're not going to be good at. And what they're spending their time on, is figuring out how do I apply this capability of this model to this domain or to this user. So they're actually working inside out or technology out, versus customer problem in. And of course, they understand the customer problem. And a lot of times they have firsthand knowledge of it. But they're really close to the metal and capability, and they're applying it. And I think this is a really different way to develop products than in SaaS. I started my career as a product manager a long time ago, and it's almost the complete opposite of everything you learned. "Listen to the customer, understand it, then bring it back to the engineering and product teams." If you did that right now, ask a bunch of customers what they want out of AI, and you brought it back, for the most part, it may not be possible today with today's technology. Whereas the teams that are winning right now really understand the technology and are applying it out. And so I think this reversal matters. I think it's a big difference in terms of how companies are getting built. And maybe even the types of entrepreneurs that will be successful. I'm not sure. You're seeing some real change there. Look at the Bret Taylor's at Sierra. That's a super, super technical founder who really gets it. Brett and Clay really get it. You look at Michael and his co-founders at Cursor. They're super technical founders and they get it. They all really understand what these things can and can't do. And that's a pretty different dynamic relative to the way the best SaaS companies got built." Link in bio for the full conversation going deep on the current class of startups going from zero to $100m+ in ARR within 12 months.

The Peel

209,752 views • 1 year ago

Mental Health tip for today… “Throw a party in your heart!!!” One of the best things about opening up fully about my mental health battles has been the learning journey I’ve since gone on. Now, as a result, I have new tools to fight my depression and anxiety, new rituals to navigate through that gray I live in. This is pretty cool and I learned it from a monk in Thailand (literally) and I now use it every night of my life to change what nights look like for me. I used to go to sleep absolutely dreading those first 15 minutes I laid my head on my pillow because I didn’t know how to like or love myself and I was laying there with someone I felt didn’t deserve to be liked or loved. Now, I use this tip to end my night on a MUCHHHH better plane and as a result start my day a little better. Give it a listen and if it resonates with you give it a try. Hope it helps gang! #mentalhealth #mentalhealthmatters #depression #anxiety #unbreakable

Mental Health tip for today… “Throw a party in your heart!!!” One of the best things about opening up fully about my mental health battles has been the learning journey I’ve since gone on. Now, as a result, I have new tools to fight my depression and anxiety, new rituals to navigate through that gray I live in. This is pretty cool and I learned it from a monk in Thailand (literally) and I now use it every night of my life to change what nights look like for me. I used to go to sleep absolutely dreading those first 15 minutes I laid my head on my pillow because I didn’t know how to like or love myself and I was laying there with someone I felt didn’t deserve to be liked or loved. Now, I use this tip to end my night on a MUCHHHH better plane and as a result start my day a little better. Give it a listen and if it resonates with you give it a try. Hope it helps gang! #mentalhealth #mentalhealthmatters #depression #anxiety #unbreakable

Jay Glazer

72,460 views • 10 months ago

More of Harry about Aperture “The reason why it's called Aperture is like, you control how much light you let in to your life. And I think the start of this year, I kind of just decided I was going to say yes to everything. And the momentum of that has just brought, like, so many positive things in a lot of different ways into my life. And it's been a really beautiful time in my life. And I think also, just when I would play people the music, it was always the song that I played first. […] I want to say and where I'm at in my life. And I think there's nothing more fulfilling, I think, as a musician than putting out a song that you feel like represents where you're at in your life. I think sometimes, you know, you write a song and by the time it comes out, you've kind of been through a bunch of things, and you're not really kind of aligned with necessarily what is happening in the song. And I think I really felt it when we put As It Was at or I felt like, “oh, I feel like this really represents where I'm at in this moment” and that felt really fulfilling. So I think kind of I wanted to do that again this time. And just I feel great about, like, pressing play and going like, I want to play something. And that's kind of why it ended up being the first song.” - 102.7 KIIS FM

More of Harry about Aperture “The reason why it's called Aperture is like, you control how much light you let in to your life. And I think the start of this year, I kind of just decided I was going to say yes to everything. And the momentum of that has just brought, like, so many positive things in a lot of different ways into my life. And it's been a really beautiful time in my life. And I think also, just when I would play people the music, it was always the song that I played first. […] I want to say and where I'm at in my life. And I think there's nothing more fulfilling, I think, as a musician than putting out a song that you feel like represents where you're at in your life. I think sometimes, you know, you write a song and by the time it comes out, you've kind of been through a bunch of things, and you're not really kind of aligned with necessarily what is happening in the song. And I think I really felt it when we put As It Was at or I felt like, “oh, I feel like this really represents where I'm at in this moment” and that felt really fulfilling. So I think kind of I wanted to do that again this time. And just I feel great about, like, pressing play and going like, I want to play something. And that's kind of why it ended up being the first song.” - 102.7 KIIS FM

HSNews

39,591 views • 6 months ago

At around 8 this morning I was only at about 166 degrees when it decided it was going to rain so I hurried up and took it inside and finished it in the oven. I pulled it at about 200 degrees and I knew I was going to rest it in the cooler so I figured I would have 5 degrees to spare. A four hour rest in the cooler turned into a 6 hour rest because I fell asleep and overslept. The bark wasn’t as crispy as I like it to be but the meat is tender and juicy, it cuts easy and falls apart in your hand. Over all it turned out good. I think I’m going to save it for special occasions or when I have a lot of time on my hands.

At around 8 this morning I was only at about 166 degrees when it decided it was going to rain so I hurried up and took it inside and finished it in the oven. I pulled it at about 200 degrees and I knew I was going to rest it in the cooler so I figured I would have 5 degrees to spare. A four hour rest in the cooler turned into a 6 hour rest because I fell asleep and overslept. The bark wasn’t as crispy as I like it to be but the meat is tender and juicy, it cuts easy and falls apart in your hand. Over all it turned out good. I think I’m going to save it for special occasions or when I have a lot of time on my hands.

SonnyBoy🇺🇸

84,470 views • 1 month ago

Tarris Reed Jr talks about his Spurs teddy bear: “We took a trip to Orlando, we went to Disney world. We stopped by a restaurant.. I ended up playing the claw machine, and somehow someway I won, I had the Spurs teddy bear. And this is during like the peak run of you know the Kawhi, Manu, Parker, you know just the legends, Timmy.. I kept it, ended up giving it to my little brother. And then right when I was starting to travel on the road for my NBA workouts, like I was going to be gone for a month, I was staying in my room and I just saw the bear. Like somehow just saw the bear on my headboard. I’m holding it and I’m looking at it like ‘How cool would it be if I ended up on the Spurs.’ And then my Mom brought it for the draft party. Then when I got picked I was like ‘Damn this is really crazy.’ That’s the grace of god right there man, that’s a blessing.” #GoSpursGo #PorVida

Tarris Reed Jr talks about his Spurs teddy bear: “We took a trip to Orlando, we went to Disney world. We stopped by a restaurant.. I ended up playing the claw machine, and somehow someway I won, I had the Spurs teddy bear. And this is during like the peak run of you know the Kawhi, Manu, Parker, you know just the legends, Timmy.. I kept it, ended up giving it to my little brother. And then right when I was starting to travel on the road for my NBA workouts, like I was going to be gone for a month, I was staying in my room and I just saw the bear. Like somehow just saw the bear on my headboard. I’m holding it and I’m looking at it like ‘How cool would it be if I ended up on the Spurs.’ And then my Mom brought it for the draft party. Then when I got picked I was like ‘Damn this is really crazy.’ That’s the grace of god right there man, that’s a blessing.” #GoSpursGo #PorVida

Wemby Alien Era

142,311 views • 1 month ago

Auditioning is a completely different performance than how you’d perform it when you get the job. Most actors don’t realize that. What do I mean? In an audition, I only have 1 set up, 1 frame from the chest up. On set you’ll have multiple set ups and multiple camera lens sizes. So for example if I have to do a very explosive emotional scene for an audition I’m beholden to that one set up which is the chest up how casting likes it. BUT if I’m too big and too emotional for that frame size it might come off as melodramatic/Over-acting or I’m forcing it. So I have to do a little less. Now on set during the master I can be as big and as ferocious as I want and then dial it down as the camera moves in closer. The same goes if it has to be small and intimate scene, I might have to project a bit more to convey that emotion in an audition where if it was on set that close up sees everything and I can be as small an intimate as I want. So during these auditions you’re predominantly handcuffed to the size of the frame that casting wants. I like to be subtle in auditions and sometimes that can look like you’re doing absolutely nothing and its not as engaging for the audition process. (You’re trying to get a job) So I amp it up 10-20%. Again, where as on set I can be as small and subtle as I want and when they move in on your close up it sees the minutia of every detail that your face and eyes make. (Also in an audition you’re acting with a friend or a family member who might not be an actor. No professional makeup or hair, bad lighting, dog barking, cat meowing, fedex guy ringing your bell,etc etc) So to recap… AUDITIONING SUCKS!🤦🏻‍♂️ #kidvicious🔪

Auditioning is a completely different performance than how you’d perform it when you get the job. Most actors don’t realize that. What do I mean? In an audition, I only have 1 set up, 1 frame from the chest up. On set you’ll have multiple set ups and multiple camera lens sizes. So for example if I have to do a very explosive emotional scene for an audition I’m beholden to that one set up which is the chest up how casting likes it. BUT if I’m too big and too emotional for that frame size it might come off as melodramatic/Over-acting or I’m forcing it. So I have to do a little less. Now on set during the master I can be as big and as ferocious as I want and then dial it down as the camera moves in closer. The same goes if it has to be small and intimate scene, I might have to project a bit more to convey that emotion in an audition where if it was on set that close up sees everything and I can be as small an intimate as I want. So during these auditions you’re predominantly handcuffed to the size of the frame that casting wants. I like to be subtle in auditions and sometimes that can look like you’re doing absolutely nothing and its not as engaging for the audition process. (You’re trying to get a job) So I amp it up 10-20%. Again, where as on set I can be as small and subtle as I want and when they move in on your close up it sees the minutia of every detail that your face and eyes make. (Also in an audition you’re acting with a friend or a family member who might not be an actor. No professional makeup or hair, bad lighting, dog barking, cat meowing, fedex guy ringing your bell,etc etc) So to recap… AUDITIONING SUCKS!🤦🏻‍♂️ #kidvicious🔪

KID VICIOUS🔪

22,555 views • 1 year ago

Caitlin Clark on how she gets covered by the media: "I think there's just like a false characterization of who I am sometimes. And I get it like as a reporter or as a blogger, like you can write an opinion piece and that's your job and whatever. But at the same time, like you don't know me. Like we've never had a conversation. I get people have a job to do. But at the same time, like don't make accusations about my character and who I am when you don't know me. I understand this is your job and this is your profession, and this is what you get to do. And basketball is my profession, what I get to do. And the reason I play it is when I step in between the lines, I love it. And that's what's so fun about it for me is like, I get to compete. This was always my dream. And nobody should ever try to take that away from me"

Caitlin Clark on how she gets covered by the media: "I think there's just like a false characterization of who I am sometimes. And I get it like as a reporter or as a blogger, like you can write an opinion piece and that's your job and whatever. But at the same time, like you don't know me. Like we've never had a conversation. I get people have a job to do. But at the same time, like don't make accusations about my character and who I am when you don't know me. I understand this is your job and this is your profession, and this is what you get to do. And basketball is my profession, what I get to do. And the reason I play it is when I step in between the lines, I love it. And that's what's so fun about it for me is like, I get to compete. This was always my dream. And nobody should ever try to take that away from me"

Oh No He Didn't

260,511 views • 8 days ago

Jack Dorsey on becoming a better storyteller: "I found myself very early on thinking about something like thinking about this early idea for Twitter and saying to myself, I could build this awesome. You have those shower-like moments, or you're walking at midnight in some town in New York City, and you've got these amazing brand ideas. And then you start thinking, well, I could really start doing this if only X and if I had this person or if this technology existed or if this happened or this happened. And what I realized was that I was constantly making excuses for not working on it. And then the window had passed, and then I couldn't do anything. So I think it's really, really important to write it out or to draw it out or to code it. But you need to get it out of your head. And the reason you have to get it out of your head is that you need to be able to see it on a surface that is not in your mind. And once you can see it, and once you can step back from it, then you can also decide this passes my filter, my constraints, so maybe I can show it and share it with some other people. And then they will be like that's the stupidest idea ever and or that's somewhat interesting, but maybe this and this and this. So the sooner you can do that, then you have a lot of momentum around it, and you can really decide if you want to commit to it and work on it more or put it on the shelf for a later date. And the realization that I think everyone needs to have about that latter option, putting it on the shelf, is that you can come back to it and it will surface back up in another piece of work or another idea at some point in your life. So having that ability to close off a chapter and move on is really, really important. You can't have all these open threads, and that's what I realized I was doing. And that also encouraged me to really write more and to really think about what's the story? How are people coming to this? And like when I show my friends this, how are they going to react and I would write it down. I would actually treat it like a play. And when I realized that I was writing plays, I read a lot more plays for style and for substance and for technique and I think it's really good. I think there is another company that I have always looked towards for inspiration and I know a number of people in this room probably have a similar company in mind, which is Apple. Apple, I think, is run like a theater company. It has a great sense of pacing, has a great sense of story and has a great sense of execution and it's all about event-driven, it's all stage-driven, the stage being a billboard or the stage being a keynote or the stage being a product launch. All of it has a very, very cohesive end-to-end story. I mean you think about what happened when Steve Jobs came back to the company. The first thing he did was kill every product line the company was working on. And for two years,rs they had no product on the market whatsoever. All they had were a bunch of posters all around the world with Steve Jobs' heroes, and it said, think different. And it was just focused on bringing up the brand and making people aware of the brand again and how the brand is aligning to this particular feeling and story. And then they came out with the iMac and then built iTunes and then the iPod, and they realized that, wait a minute, people are carrying music on their phones now, so we better build a phone, an iPhone. And so this unfolding of the plot and the epic story has been very, very interesting to watch, especially if you look back to that time when he came back to the company. So I've learned a lot from that company and other companies that operate in a similar fashion."

Founder Mode

107,213 views • 7 months ago

This part breaks and heals my heart at the same time 💔Mingi’s words are full of wisdom, as always🥺 🐥 I was full of arrogance in the beginning, but after I made my debut, I felt so small. From then on, I lost a lot of my mental strength. As soon as I made my debut, I thought I was the best and I thought I was in first place. That’s why those aspirations, that tenacity, and that something about me - my self-worth - was so high. But after that, it was destroyed in an instant. 🐥 I lost a lot of my self-worth, and I started to feel like I was worth nothing. I started to doubt if there was any reason for me to be in this group. When I feel that kind of self-disgust, I think it’s important how I overcome those thoughts. In my early days of my debut, I think I only had a pretty packaging on me. I used to think, ‘I’m doing well, what more can I do?’ But after that pretty packaging came off, I had nothing inside. So I think it took me a long time to fill myself up. Now, even if I break down once in a while, I just go back to the human Song Mingi, and I look for the things I like one by one, and then I think, ‘People will like me a bit now, right?’ Since we’re celebrities, we need to satisfy the people to a certain degree. But I think we still have to satisfy ourselves in the process as well. I think I try to find a harmony between the two in my head. 🐥 It took me a long time to build this up, but I think the process of building myself up, unlike building a sand castle, you build it up little by little. So I feel like, internally, I have become more resilient, compare to before.

This part breaks and heals my heart at the same time 💔Mingi’s words are full of wisdom, as always🥺 🐥 I was full of arrogance in the beginning, but after I made my debut, I felt so small. From then on, I lost a lot of my mental strength. As soon as I made my debut, I thought I was the best and I thought I was in first place. That’s why those aspirations, that tenacity, and that something about me - my self-worth - was so high. But after that, it was destroyed in an instant. 🐥 I lost a lot of my self-worth, and I started to feel like I was worth nothing. I started to doubt if there was any reason for me to be in this group. When I feel that kind of self-disgust, I think it’s important how I overcome those thoughts. In my early days of my debut, I think I only had a pretty packaging on me. I used to think, ‘I’m doing well, what more can I do?’ But after that pretty packaging came off, I had nothing inside. So I think it took me a long time to fill myself up. Now, even if I break down once in a while, I just go back to the human Song Mingi, and I look for the things I like one by one, and then I think, ‘People will like me a bit now, right?’ Since we’re celebrities, we need to satisfy the people to a certain degree. But I think we still have to satisfy ourselves in the process as well. I think I try to find a harmony between the two in my head. 🐥 It took me a long time to build this up, but I think the process of building myself up, unlike building a sand castle, you build it up little by little. So I feel like, internally, I have become more resilient, compare to before.

Irene | AhgaTiny

35,998 views • 10 months ago

One of my best engineers just showed me how to set up OpenClaw securely & without a Mac Mini. Here's his step-by-step: 1) Spin up a VPS on Hetzner It's a virtual server in the cloud. basically a computer you rent for $5-10/month. Pick 8GB RAM, Ubuntu, US East. Takes 2 minutes. 2) Install Tailscale This makes your server invisible to the public internet. Think of it like moving from a house on Google Maps into a gated community where only your devices can get in. Without this, bots start attacking your server within seconds of it going live. 3) Harden the server SSH keys only. Firewall. Intrusion prevention. Auto security updates. CJ actually uses AI to red team his own servers. Tells it to try and break in, then patches whatever it finds. 4) Install OpenClaw🦞 and run the onboarding. You pick your model provider, connect Telegram via BotFather, and configure hooks that give your agent long-term memory. The hooks auto-save sessions and context so the agent gets smarter over time. 5) Set up the gateway This is the piece that makes it actually powerful. It's a message bus that lets your main agent talk to sub-agents, receive messages from Telegram/Discord/Slack, and orchestrate everything. this is what keeps it running 24/7. 6) Hatch your claw and start training it Dump as much info about yourself as possible. tell it your preferences, your workflows, your tools. CJ's agent monitors his email, Slack, and manages his to-do list autonomously. Watch the video for the full break-down & follow CJ Hess for more AI engineering sauce.

One of my best engineers just showed me how to set up OpenClaw securely & without a Mac Mini. Here's his step-by-step: 1) Spin up a VPS on Hetzner It's a virtual server in the cloud. basically a computer you rent for $5-10/month. Pick 8GB RAM, Ubuntu, US East. Takes 2 minutes. 2) Install Tailscale This makes your server invisible to the public internet. Think of it like moving from a house on Google Maps into a gated community where only your devices can get in. Without this, bots start attacking your server within seconds of it going live. 3) Harden the server SSH keys only. Firewall. Intrusion prevention. Auto security updates. CJ actually uses AI to red team his own servers. Tells it to try and break in, then patches whatever it finds. 4) Install OpenClaw🦞 and run the onboarding. You pick your model provider, connect Telegram via BotFather, and configure hooks that give your agent long-term memory. The hooks auto-save sessions and context so the agent gets smarter over time. 5) Set up the gateway This is the piece that makes it actually powerful. It's a message bus that lets your main agent talk to sub-agents, receive messages from Telegram/Discord/Slack, and orchestrate everything. this is what keeps it running 24/7. 6) Hatch your claw and start training it Dump as much info about yourself as possible. tell it your preferences, your workflows, your tools. CJ's agent monitors his email, Slack, and manages his to-do list autonomously. Watch the video for the full break-down & follow CJ Hess for more AI engineering sauce.

Alex Lieberman

64,929 views • 5 months ago

✨ I made a little demo of #vibejam sponsor Tripo and how you can use it to generate assets for your games In this case I'm generating an apartment flat that's half destroyed and open for my drone sim to fly around, take cover and shoot at enemies from First I write the prompt and select Nano Banana to generate an image first, I get a few different ones, and I select the one I like Then that one is converted into a 3d object called a Smart Mesh Smart Mesh is different than regular image-to-3d models because usually you get issues with uneven polygon distribution, too dense geometry and poor edge flow, so while you think you save time with generating it with AI you end up doing lots of editing after to fix the topology which kinda defeats the point Smart Mesh doesn't have any of this, it's fast and clean low-poly models you can drop into your game Anyway, after generating the model I can then see it in 3d, and if I don't like it, regenerate it, or if I like it start texturing it Once that's done, I export it as a GLB, FBX or OBJ and drop it in (usually I use GLB as ThreeJS seems to prefer that), in my case I just drop the URL into Cursor and let it figure out the placement of the asset into my game!

✨ I made a little demo of #vibejam sponsor Tripo and how you can use it to generate assets for your games In this case I'm generating an apartment flat that's half destroyed and open for my drone sim to fly around, take cover and shoot at enemies from First I write the prompt and select Nano Banana to generate an image first, I get a few different ones, and I select the one I like Then that one is converted into a 3d object called a Smart Mesh Smart Mesh is different than regular image-to-3d models because usually you get issues with uneven polygon distribution, too dense geometry and poor edge flow, so while you think you save time with generating it with AI you end up doing lots of editing after to fix the topology which kinda defeats the point Smart Mesh doesn't have any of this, it's fast and clean low-poly models you can drop into your game Anyway, after generating the model I can then see it in 3d, and if I don't like it, regenerate it, or if I like it start texturing it Once that's done, I export it as a GLB, FBX or OBJ and drop it in (usually I use GLB as ThreeJS seems to prefer that), in my case I just drop the URL into Cursor and let it figure out the placement of the asset into my game!

@levelsio

72,338 views • 3 months ago

Kevin O'Leary thought Tesla was a joke and wanted to short it before making 1,000% “My son, who’s an electrical engineer, was interning at Tesla and I was about to go on the Halftime Report on CNBC. Tesla was downgraded that day. Before all the splits, it was trading at $236” “Trevor said to me, ‘Dad, why don't you own some $TSLA? I work there as an intern.’ And I said, ‘I want to short that stock. It's such a joke. It's a car company trading at a ridiculous price’” “He said, ‘No, you're the joke. You don't understand what Tesla does. I work there. It's not a car company. It's a data company. Every time a car drives a mile, it goes back to the server and it tells the resolution of that road. It gets better and better because every mile a Tesla drives, it goes into the database of mapping for autonomous cars’” “I thought, ‘Fuck, I didn't know that.’ He said, ‘No kidding. You have a ton of money. Why don't you buy some of this stock’” “Just before I went on the air, I took my phone out and I bought a block of the stock in my personal account. Then I forgot about it. One day I opened up the thing and I was up 1,000%” “So I started selling it and selling it. It kept going up and I kept selling it and selling it. My cost base is zero. It doesn't matter what happens to Tesla now. I made a ton of money on it”

Kevin O'Leary thought Tesla was a joke and wanted to short it before making 1,000% “My son, who’s an electrical engineer, was interning at Tesla and I was about to go on the Halftime Report on CNBC. Tesla was downgraded that day. Before all the splits, it was trading at $236” “Trevor said to me, ‘Dad, why don't you own some $TSLA? I work there as an intern.’ And I said, ‘I want to short that stock. It's such a joke. It's a car company trading at a ridiculous price’” “He said, ‘No, you're the joke. You don't understand what Tesla does. I work there. It's not a car company. It's a data company. Every time a car drives a mile, it goes back to the server and it tells the resolution of that road. It gets better and better because every mile a Tesla drives, it goes into the database of mapping for autonomous cars’” “I thought, ‘Fuck, I didn't know that.’ He said, ‘No kidding. You have a ton of money. Why don't you buy some of this stock’” “Just before I went on the air, I took my phone out and I bought a block of the stock in my personal account. Then I forgot about it. One day I opened up the thing and I was up 1,000%” “So I started selling it and selling it. It kept going up and I kept selling it and selling it. My cost base is zero. It doesn't matter what happens to Tesla now. I made a ton of money on it”

dank

1,481,738 views • 1 month ago

I wake up fairly early and I love listening to classical Hindustani ragas to get my day going. I got inspired recently by this website called Dhuni and wanted to get some of my own favorites built into a radio station and build an interesting interface with a man slowly walking through a forest as dawn becomes day becomes evening becomes night and the dawn comes back again. Used Emergent And literally one-shotted this whole thing in less than 10 minutes. I was just 🤯. I have used the product often over the last 6-8 months as an investor but this was genuinely so well done. I tried using the same prompt on at least 3 other platforms and some essentially connected to radio stations that had Hindi music but then randomly inserted English music. Some didn't have an interface as cool, some had output that was barely understandable and needed a lot of APIs to YT. Some asked me to use curl on the terminal to download my favorite tracks as MP3s 😆 This experience just brought back to me how large an opportunity personal apps can be in the future. This exact thing would have cost me $20/mo as saas sub and would be fairly generic. This app now is exactly to my taste. The interface is exactly as I described it, the music is exactly like I want it. Just a delightful personal software I'm now waking up to every day. I am hosting it on Emergent here if you want to check it out:

I wake up fairly early and I love listening to classical Hindustani ragas to get my day going. I got inspired recently by this website called Dhuni and wanted to get some of my own favorites built into a radio station and build an interesting interface with a man slowly walking through a forest as dawn becomes day becomes evening becomes night and the dawn comes back again. Used Emergent And literally one-shotted this whole thing in less than 10 minutes. I was just 🤯. I have used the product often over the last 6-8 months as an investor but this was genuinely so well done. I tried using the same prompt on at least 3 other platforms and some essentially connected to radio stations that had Hindi music but then randomly inserted English music. Some didn't have an interface as cool, some had output that was barely understandable and needed a lot of APIs to YT. Some asked me to use curl on the terminal to download my favorite tracks as MP3s 😆 This experience just brought back to me how large an opportunity personal apps can be in the future. This exact thing would have cost me $20/mo as saas sub and would be fairly generic. This app now is exactly to my taste. The interface is exactly as I described it, the music is exactly like I want it. Just a delightful personal software I'm now waking up to every day. I am hosting it on Emergent here if you want to check it out:

Hemant Mohapatra

19,168 views • 4 months ago

And so it begins. YouTube Just took down my video and issued me a warning strike for my latest video react to Brandon Herrera's latest Darwin Awards. Can someone at TeamYouTube explain how a video I reacted to is still up and fully accessible (and rightly so because there's nothing wrong with it) and yet MY video gets taken down, even after I'd actually edited out some parts before posting, and I get a strike for it. Just what the hell is going on?!? Can I please get a HUMAN to look at this for once??? Oh and just so there's full transparency here, I'm going to post the full video that I received a strike for in this tweet so anyone can view it. The original that I reacted to is still up and available for viewing (and I strongly recommend you watch it not only to give the original content creator their proper views but to compare our two videos) as of the time of this posting at:

And so it begins. YouTube Just took down my video and issued me a warning strike for my latest video react to Brandon Herrera's latest Darwin Awards. Can someone at TeamYouTube explain how a video I reacted to is still up and fully accessible (and rightly so because there's nothing wrong with it) and yet MY video gets taken down, even after I'd actually edited out some parts before posting, and I get a strike for it. Just what the hell is going on?!? Can I please get a HUMAN to look at this for once??? Oh and just so there's full transparency here, I'm going to post the full video that I received a strike for in this tweet so anyone can view it. The original that I reacted to is still up and available for viewing (and I strongly recommend you watch it not only to give the original content creator their proper views but to compare our two videos) as of the time of this posting at:

❤️‍🔥 Ember Paradox ❤️‍🔥

81,020 views • 7 months ago

I FINALLY managed to create a point cloud animation 💪 Here is how I did it using #GaussianSplatting, #Blender and 2 add-ons from KIRI Engine - 3D Scanner App . Creating point cloud animations has always been a dream of mine (inspired by masters like ), but the tech to create the point clouds and visual effects was always a huge barrier. Then I discovered these 2 Blender add-ons from Kiri engine after I had a chat with Jack Wang in my podcast, and it changed everything: 1- Create a splat with any tool or app you want 2- Install the free "Point Animate" add-on in Blender 3- Drag the 2 .ply you want to morph from --> to 4- Set source and destination in the add-on side panel At this point you could play around with various settings like noise scatter, noise intensity, wind and more. If you want to combine with the splat as well you can get also the 3DGS render to add cool dissolving effects, fancy lighting and really get the most out of your scans. If you end up using it please tag me. I am curious to see what much more skilled people than me can put together 😉

I FINALLY managed to create a point cloud animation 💪 Here is how I did it using #GaussianSplatting, #Blender and 2 add-ons from KIRI Engine - 3D Scanner App . Creating point cloud animations has always been a dream of mine (inspired by masters like ), but the tech to create the point clouds and visual effects was always a huge barrier. Then I discovered these 2 Blender add-ons from Kiri engine after I had a chat with Jack Wang in my podcast, and it changed everything: 1- Create a splat with any tool or app you want 2- Install the free "Point Animate" add-on in Blender 3- Drag the 2 .ply you want to morph from --> to 4- Set source and destination in the add-on side panel At this point you could play around with various settings like noise scatter, noise intensity, wind and more. If you want to combine with the splat as well you can get also the 3DGS render to add cool dissolving effects, fancy lighting and really get the most out of your scans. If you end up using it please tag me. I am curious to see what much more skilled people than me can put together 😉

Gabriele Romagnoli

10,392 views • 1 year ago

I tried jack's Buzz. It's like Slack + OpenClaw + Herdr + but with some really unique features that people are sleeping on. The video below shows how it works, and some of my thoughts on the process and platform, e.g.: - Create and interact with agents on top of any harness (claude code, codex, pi, etc.) - Choose which models agents use, including local ones - Agents can delegate work and work in parallel in git worktrees - Agents are first-class citizens and work like humans (creating channels, delegating, access to chat history) - You can share AI compute within a community - It's completely open-source and decentralized Things I like: - Delegating work in chat feels natural: tag an agent, it replies in a thread with status updates as it e.g. compiles, commits, and deploys. - Shared compute: relay owners can share local compute with members, so a community could pool funds for one beefy machine running a local model and everyone uses it. - It's built on Nostr, an open protocol already tied into Bitcoin Lightning so I can imagine communities tipping each other or paying for compute/agent tasks with instant zero-fee micropayments in the future. - It ties together things like OpenClaw, an agent manager, and Slack-style chat into one tool. Things I didn't like: - You can't see what the agent is doing in a terminal. The activity view exists, but if you're used to watching a session run, this UI feels a bit abstracted. A terminal view would be great. - It feels slower than running a session in Claude Code, though no evidence to back that up. For that reason I found myself doing one-off tasks in the terminal instead. Verdict: - I really like it so far and can genuinely imagine working with a team this way. - It doesn't feel ready for big, complex tasks yet. For shallower tasks, it's perfect. - The shared compute + Nostr/Lightning angle is what really separates it from every other agent manager for me, and I think that future is coming.

I tried jack's Buzz. It's like Slack + OpenClaw + Herdr + but with some really unique features that people are sleeping on. The video below shows how it works, and some of my thoughts on the process and platform, e.g.: - Create and interact with agents on top of any harness (claude code, codex, pi, etc.) - Choose which models agents use, including local ones - Agents can delegate work and work in parallel in git worktrees - Agents are first-class citizens and work like humans (creating channels, delegating, access to chat history) - You can share AI compute within a community - It's completely open-source and decentralized Things I like: - Delegating work in chat feels natural: tag an agent, it replies in a thread with status updates as it e.g. compiles, commits, and deploys. - Shared compute: relay owners can share local compute with members, so a community could pool funds for one beefy machine running a local model and everyone uses it. - It's built on Nostr, an open protocol already tied into Bitcoin Lightning so I can imagine communities tipping each other or paying for compute/agent tasks with instant zero-fee micropayments in the future. - It ties together things like OpenClaw, an agent manager, and Slack-style chat into one tool. Things I didn't like: - You can't see what the agent is doing in a terminal. The activity view exists, but if you're used to watching a session run, this UI feels a bit abstracted. A terminal view would be great. - It feels slower than running a session in Claude Code, though no evidence to back that up. For that reason I found myself doing one-off tasks in the terminal instead. Verdict: - I really like it so far and can genuinely imagine working with a team this way. - It doesn't feel ready for big, complex tasks yet. For shallower tasks, it's perfect. - The shared compute + Nostr/Lightning angle is what really separates it from every other agent manager for me, and I think that future is coming.

Vinny

1,312,116 views • 9 days ago

Introducing Open Source AI CRM, that runs on your OpenClaw. A few weeks ago, we launched Ironclaw (An Open Source OpenClaw CRM Framework) which now has around 1.4k stars. A lot of people confused us with NearAI’s Ironclaw, so we changed our name to DenchClaw. OpenClaw today feels a lot like early React: the primitive is incredibly powerful, but the patterns are still forming, and everyone is piecing together their own way to actually use it. What made React explode wasn’t just React itself, but the emergence of frameworks like Gatsby and Next.js that turned raw capability into something opinionated, repeatable, and easy to adopt. That is how I think about DenchClaw. We are not just building on top of OpenClaw; we are trying to make it one of the clearest, most practical, and most complete ways to use OpenClaw in the real world. We are an OpenClaw Framework, we are aiming to be the most correct way to use OpenClaw. We entered Y Combinator with Merse (AI Audio Comic), it was an app that I personally never used. Michael Seibel confronted us on it, and said, “if you aren’t the best user of your consumer app, then who is?”. I now use DenchClaw daily for everything I do, it also works as a coding agent like Cursor, DenchClaw built DenchClaw. I am addicted to DenchClaw now that I can ask it, “hey in the companies table only show me the ones who have more than 5 employees” and it updates it live than me having to manually add a filter. On Dench, everything sits in a file system, the table filters, views, column toggles, calendar/gantt views, etc, so OpenClaw can directly work with it using Dench’s CRM skill. The CRM is built on top of DuckDB, the smallest, most performant and at the same time also feature rich database we could find. It creates a new OpenClaw🦞 profile called “dench”, and opens a new OpenClaw Gateway… that means you can run all your usual openclaw commands by just prefixing every command with `openclaw --profile dench` . It will start your gateway on port 19001 range. You will be able to access the DenchClaw frontend at localhost:3100. Once you open it on Safari, just add it to your Dock to use it as a PWA. Think of it as Cursor for your Mac which is based on OpenClaw. DenchClaw has a file tree view for you to use it as an elevated finder tool to do anything on your mac. I use it to create slides, do LinkedIn outreach using MY browser. DenchClaw sees what you see, does what you do. It’s the everything app, that sits locally on your mac. All yours. Just ask it “hey import my notion”, “hey import everything from my hubspot”, and it will literally go into your browser, export all objects and documents and put it in its own workspace that you can use. P.S. It comes with Garry Tan's GStack built in.

Mark Rachapoom

19,411 views • 4 months ago