--- title: 'How to Use Tailscale with AI Agents' source: 'https://youtube.com/watch?v=eNn2tT-lrz4' video_id: 'eNn2tT-lrz4' date: 2026-07-14 duration_sec: 0 --- # How to Use Tailscale with AI Agents > Source: [How to Use Tailscale with AI Agents](https://youtube.com/watch?v=eNn2tT-lrz4) ## Summary David Andre explains how to use Tailscale with AI agents, covering what Tailscale is, how it works, and why it's essential for multi-agent setups. He demonstrates setting up Tailscale on a VPS, securing it, and using it with Hermes agent and Aperture for API key management. ### Key Points - **What is Tailscale?** [00:00] — Tailscale is a private network that connects all your machines together, allowing a single agent to control any number of other agents regardless of location. - **Why Tailscale matters for AI agents** [00:30] — Managing multiple agents manually is a nightmare; Tailscale enables one agent to command and fix others without manual involvement. - **Security: zero open ports** [01:30] — Tailscale connects machines through a private encrypted tunnel, eliminating the need for exposed ports and protecting VPS from bad actors. - **Multi-agent orchestration** [02:30] — Tailscale makes every machine show up in a single console with clean names, and you can connect from anywhere without SSH keys. - **Free tier and pricing** [03:30] — Tailscale is free for most users, with unlimited devices and up to six users. Only pay for the VPS itself. - **Access control lists (ACLs)** [04:30] — ACLs allow you to write rules limiting which devices can talk to each other, enhancing security. - **Setting up Tailscale** [05:30] — Go to tailscale.com, click get started, log in with GitHub or Google, and follow steps to add devices. - **Using Codex to set up VPS** [07:00] — David uses Codex (AI agent) to SSH into the VPS and install Tailscale, demonstrating agent-driven setup. - **Locking down the VPS** [11:00] — After Tailscale installation, David uses Codex to disable all ports and make the VPS only accessible via Tailscale. - **Installing Hermes agent via Codex** [13:00] — Codex installs Hermes agent on the VPS autonomously, using Tailscale and Aperture for API key management. - **Using Aperture for API keys** [15:00] — Aperture is Tailscale's AI gateway that stores API keys securely and distributes them across devices on the tailnet. - **Changing model via Tailscale** [19:00] — David sends a prompt to update the model in Hermes agent from GLM 5.2 to GPT 5.6, and Codex does it automatically. ### Conclusion Tailscale is a must-have for anyone running multiple AI agents, providing secure, easy management and orchestration. By following the steps, you can secure your VPS and streamline agent operations. ## Transcript My name is David Andre and here's how to use tail scale with AI agents. So first, what even is tail scale? Tail scale is a private network that connects all your machines together. And this matters a lot in the AI era because it allows a single agent to control any number of other agents, no matter if they're local on your computer or on a VPS. And these are just few of the reasons why Tailcale is growing exponentially. This is the 5-year graph on Google Trends. And you can see the popularity is exploding, right? More and more people are using tail scale on their devices. So in this video I'll explain what tail scale is, how it works, and why it's revolutionary with multi- aent setups. Now what you need to understand is that agents made telescale op. Everyone is running more AI agents than ever before. And doesn't matter if it's codex, cloud code, hermes, pi, cursor or something else. Both me and you are running more agents now than a year or two ago. But managing them one by one is a nightmare. Every small update crash needs manual fixing. You have Hermes on one VPS. it crashes. You have open claw on another VPS. It needs a model change. Takes so much time managing this manually. But if you put them on a tcale network, any one of your agents, maybe a PI agent on your MacBook, can command and fix any other agent quickly and without your manual involvement. Also, if you use tail scale, your machines can have zero open ports. Every open port is a point of exposure. It's a weakness since there are countless bots scanning the whole internet non-stop. But tail scale connects your machines through a private encrypted tunnel. So you don't need to have any exposed ports to the internet and this instantly makes all of your VPS a lot more protected from bad actors. Now multi-agent orchestration is what took scale to another level. It was already a great technology but nowadays where all of us are running multiple agents tail scale is going from a useful technology to a must have especially if you have a team or you're running agents for other people say friends or family. And that's because with tailscale, every machine you add shows up in a single tail scale console with a clean name that you quickly recognize. Also, you can connect to any of them just by the name from anywhere in the world. Another thing that makes Tails scale more secure is that your access is tied to your real identity like Google or GitHub account. So, there are no SSH keys needed. So, if your laptop ever gets stolen or one of your employees in your company leaves, you just revoke that specific device and it instantly loses access to the whole Telescale network. And what's nice is that Tailscale is free for most of us. The free tier includes unlimited devices and up to six different users, which is way more than most of us will ever need. You only pay for the VPS itself. For example, you can get one from Hostinger for super cheap. So, the entire networking layer costs you nothing when you're building solo or with a small team. Another reason why so many people love Telkale is that it's fast and direct. All the traffic goes directly between your machines, peer-to-peer, not through a middleman server. Telescale is built on wire guard and that's the fastest VPN protocol out there and that means that your agents can make tons of API calls and all of them stay fast. Real quick, if you're watching this video, please check if you're subscribed. According to YouTube Studio, the vast majority of you are not subscribed. So, please go below the video and click the subscribe button. It's completely free and it helps out a lot. Now, in a second, I'm about to show you how to set up tail scale on your own machine and how we can connect different agents to it. But the last concept you need to understand before we jump to the building is access control lists. By default, every device on your tailnet can talk to every other device. But with ACL's, you can write simple rules like this agent can only reach this one VPS or this person on my team can only access these agents. Stuff like that. So even if one computer or agent or person gets compromised, it can only do damage to the machines it's allowed, not to every single thing on the tail scale network. So now let me show you how to set up tailscale. And actually it's very easy. You don't have to be a developer at all. And then I'm going to show you how to use it with a multi- aent setup. So the first step is go to tailcale.com and go to top right and click on get started. And again you can get started completely for free. The free plan is very very generous. I'm just going to go with GitHub. And immediately once you log in you see the steps on how to add a second device. Right. So your device MacBook was added to your network. So here we will add the second device. But before we do that open up any terminal. So either the built-in terminal on Mac OS or Windows, doesn't matter. I would recommend using CMAX. This is the terminal I use. Again, CMAX is completely free. I'm going to type in tail scale up to make sure it's running. Tails scale status. Okay. And back in the browser, I'm going to click on Linux, and it's going to give us the install command for Linux. So then we need a second machine to connect it to. And again, that could be your friend, your parents, your other VPS. In this case, since we care about running a multi- aent setup, I'm going to go with a VPS and most if not all VPSs are Linux. Now again, you can use Telescale with any AI agent, any device, whether it's Linux, Windows, Mac OS, whether it's a VPS or whether it's 10 different VPSs. In fact, I run multiple different Hermes agents on Hostinger VPS. But Hostinger is what I use for all of my VPSs and it's also what everyone else on my team uses. So, if you don't have a VPS setup yet, I highly recommend getting one from Hostinger. It's very affordable. Also, it makes the setup super easy. I'm going to leave a link to the landing page below the video. Here, you can select either when you want to manage Hermes agent or Hermes on a VPS. I'm going to select that. With the KVM2 plan, this is more than enough to run 20 different AI agents, whether that's agent zero, open code, open claw, codeex, claw code, Hermes, doesn't matter. Just go with the KVM2 plan. Then select a period. I recommend going for 24 months because hardware prices are becoming more and more expensive. So, I wouldn't be surprised if in the future, maybe a year from now, renting a VPS is a lot more expensive than now. So, that's why I would lock in the longest period possible. Plus, if you go with 24 months, you get the highest discount. But, if you want to save even more money, go to the right, click on have a coupon code, and type in code David for additional 10% off. Here, it's asking if we want to have a prepaid API key. I we don't need that. We don't need the scraping or gentic mail VPS backups. We can skip that server. Just choose whatever is closest to you. I'm in Poland, Katovitz. So, Lithuania is good. And the operating system, either use Hermes agent or just go with plane OS, Ubantu because we're going to be setting up TSL. This might be the easier option. And then scroll back up and click continue. Now, login with your Hostinger account. If you don't have one, just create it. It's super easy. Takes like 20 seconds. And then finish the checkout by adding your card and your billing details. Now, once you complete the purchase, we might need to do some further configuration. So, just again select the Ubuntu as the operating system. Then generate a root password. This is very important, so make sure to save it somewhere, but don't worry if you forget it. Hostinger has an easy way to reset that. Then click on next. You can skip these two and click on finish setup. And now it's going to take usually one or two minutes to set up your VPS. And again, if you don't have a VPS, I highly recommend you get one from Hostinger. I've been using their VPSs for nearly 3 years now. It's what everyone on my team uses as well. And to get started, use the first link below the video with the code David to save additional 10% off. Thank you to Hostinger for sponsoring this video. So again, inside of Tailscale, you have many different options, right? We're going to go with Linux here, which gives us a curl command, which is the install script to install Tailscale on the VPS. And by the way, everything from this video, all of the scripts, terminal commands, skills, prompts, everything is going to be in a single package in the second link below the video. So, this is completely free. Feel free to get it. We're going to put all of that into a single bundle. Again, second link below the video. Feel free to grab it. All right, so the VPS has finished setting up. Click on the left manage VPS to get to the dashboard. And here we can see all the stats. Obviously, it's starting yet, so we don't see any of the graphs. But what matters is the root access, which is the SSH, and the root password. Now, we could do all of this manually. You know, we could open up a new terminal, SSH manually, and do all of that, but I actually want to show you the power of AI agents. In fact, you can open any terminal, launch up Cloud Code or, you know, Codex, and you can have them do this full setup for you. A lot of you are still underutilizing AI agents. You're not realizing what they can do. You're still stuck in 2025 or 2024 with the previous realm where you have to describe every task and come with the idea. No, you just need to give it the big intent. Models like GBD 5.6 or Fable 5 are like they're almost AGI. These models are super intelligent. Just describe what you're doing, the most abstract highle goal and the models will walk you through the steps. So in this case, since the latest model is Codex, we're going to use Codex. Okay. If you want to be like super fast, you'll just give the credentials to Codex. It's not the best practice. So I'm going to connect to the VPS myself. And then I'm going to tell Codex to operate it, right? So I'm going to say, do you see this Cmax workspace just so it kind of starts up? I'm using 5.6 medium. Do not use anything harder than medium, by the way. It's going to absolutely destroy your codeex limits. It's not necessary. U yeah, just stick on medium. So, I'm going to SSH here. Are you sure you want to continue? Yes. And then I'm going to paste in the password from earlier. And by the way, if you forgot that root password, just click on change right here inside of Hostinger panel. Super easy. Boom. Paste that in. And just like that, we are sshed, which again, if you don't know what SSH means, don't worry about it at all. You don't have to understand all these details, all these protocols. Just follow along what I'm doing. The only thing you need to understand is that SSH is a way for your MacBook to connect to the VPS. But we're going to use Tailskll now. So I'm going to say, do you see the other CMAX pane where I just SSH into my VPS? In the meantime, I'm going to switch to Brave browser. Copy this command command. Boom. Right here. Go back to Cmax and Okay. So the Codex can now see it. So I say run this on there. The goal is to install tails scale on the VPS. So just tell it the goal. In fact, I probably wouldn't even need to give it that command, right? Like it could probably just find it or figure it out by itself. Codeex is very smart, especially with 5.6 soul. And again, this setup I could do it myself, you know, I could run these terminals myself, but then I have to read the outputs of the terminal commands. I have to understand it. All of that it's slow. The future belongs to your agents. 99.9% of software will be used by agents. That includes tools, that includes APIs, that includes SAS. It's going to be used by AI agents. We humans, we're just going to manage them. You're going to tell the intent, you know, you're going to set the goal, set the intention of the company, of the team of agents, and then you're going to be monitoring them if something goes wrong. But you really need to think and start working in this era of the future. Stop trying to do everything yourself and micromanage these agents on how they implement things. You need to just give it the high level goal and let it do what it does. So Codex is already saying the next step is to run tail scale up to authenticate. So I'm going say do it and help me put it on the same Tails scale network as my MacBook is. Feel free to run terminal commands. Boom. You can see that Codex ran the command tcalap on the VPS and now it gives us the login. It's probably going to give it back to me. And you can see I have these commands where it like knows how to use Cmax. It knows to do a timeout and wait for the other pane to confirm. This is because of my skills. Okay, I have a specific skill for CMAX and a specific skill for managing VPS servers. So my agents know all of this and they can operate much more smoothly and much more quickly than other people's agents. So if you want to have access to all of my skills, just go to davidree.com/skills. Again, we're going to leave a link to this below video and just grab it. It's completely free. Let's switch back to Cmax and let's see. Okay, open this link. So, I'm going to copy this link Codex gave me. Boom. New tab. Paste that in. Uh, authenticate the device. So, just whatever you used at the beginning. If you use GitHub, use GitHub. If you use Google, use Google. Okay, there we are. Connect device. So, let's click connect and login successful. So, I'm going to take a screenshot. Boom. Go to back to Cmax. Paste it to correct. What now? Be concise. And by the way, if you ever make typo, do not correct it. Okay? That's a rookie mistake. When somebody's correcting typos in the agents, you you know they know nothing about LLMs and next token predictions. These are literally language models. They can understand you perfectly. So login succeeded. I'll verify the VPS MAC as each other. Done. VPS. Okay, great. So now let me show you the power of tail scale because now we have the same tail scale network on my MacBook and on the VPS which means we can seamlessly connect between one another. In fact, let me just ask correct. Can we now close the SSH and interact with the VPS through TKL? Answer in short, yes, you can close this SSH session then reconnect securely through TKL. Okay, I'll say do it in the other CMAX pane. Okay, so it asked for the password again, so I put it. But now let me ask Codex, are we now connected to the VPS via tail scale? Yes or no? In fact, it said in the previous message, so I didn't need to ask it. But yeah, great. So the first thing you should do before you install Hermes agent or anything else is tell you know Codex or cloud code whichever agent is helping you set this up to log down the VPS. Right? So I'm going to say now that we have tail scale installed I want you to log down the VPS disable all ports and make it as secure as possible so that it is only accessible through tail scale. And this already will put you ahead of 99% of people in the AI space. Most people don't have firewall enabled on their VPS. They have many open ports. They have no clue what they're doing. And all it takes is using a powerful agent to do this for you, right? Literally, a single prompt like this could be the difference between your VPS being exposed and being secure. Now, obviously, you do need to do the telescale setup, but in this video, I'm showing you all the steps. As you can see, you you don't have to be a developer. I'm talking to this Codex agent in plain English. Sometimes I'm asking the dumbest questions, and it's able to do what I want it to do because these agents are so powerful. Codex is a powerful harness. GBD 5.6 Six soul is a very powerful model. Tails scale is a powerful technology. If you use the right tools, you don't have to be a 10x developer. You can still achieve the same results. So it's asking me your Mac has this SSH key. You can password. Yes. It wants to confirm this. So I'm just going to say yes, and it's going to do whatever it needs to do. So now Codex is doing all the things it needs to do to make our VPS secure. I'm just going to let it run here. And there it is. VPS locked down successfully. All public inbound ports blocked. Only Telkale traffic allowed. Public SSH blocked. SSH password disabled. MAC SSH key access verified. Telescale direct connection verified. Nice. So the VPS is fully secure. Now in the next step, I'm going to show you some of the use cases of how I use it. Especially when an AI agent crashes or when AI agent needs updating. It's a hassle and that's why a lot of people go away from open claw or Hermes is because the setup can be lengthy. But even after you set it up, you know, the agents they crash, the gateway closes, there's issues and then fixing them takes a lot of time. You know, you need to SSH again, you need to remember the IP address, you need to remember the root password with tail scale. All of these problems are solved. Okay. So next I'm going to have CEX install Hermes agent on the VPS. So I'm going to type clear and say now install Hermes agent on the VPS. use deep API skill to find out all the install steps. And again, instead of me having to do this setup myself, we're going to use Codex to do that. Also, while it's running, another great thing to use with tails scale is Aperture. This allows us to save API keys securely between the different devices on our tail net. So instead of having one API key in Hermes, another one on your MacBook, another one in OpenClaw, Telescale invented Aperture, which is a better way to manage all of these secrets and environment variables across different devices. All right, checking in on CEX here. Let's see what's happening. Okay, DB API found official news installer. Okay, so I'm refreshing it. Okay, good. We're going to leave it running. And again, it just runs autonomously. In the meantime, we can set up Aperture. So here, click on get started. Select the same email address. Boom. Get started. Now next, select some host name. I'm just going to try David's. We're going to be taken. Oh, it's not taken. Amazing. So now we can just probably have our codec set it up. Okay. What are you doing? Get to work. Stop wasting time. And just use this command to install Hermes agent on the VPS. I don't know what was correct running. Personally, I think GBD 5.6 Soul is worse than Fable. I know a lot of people disagree, but I think Fable is significantly better than GBD 5.6. Anyways, here in Aperture, I'm just going to click the button authorize to tail scale. It's going to be faster. We don't have to have correct help with us. Select the same account again and then click connect device. Aperture will join your tnet as a new node. So, actually here inside of tcale, we can probably see it machines. And there it is. So, one of these probably this one. Yeah, this one is actually aperture. So, we can probably u rename it aperture. And this will handle all of our environment variables, secrets, API keys. So, we can safely and securely distribute them across multiple different agents on different VPSs. But what's more, we can do so quickly. Like, let's be honest, nobody wants to manage 10 different API keys across seven different agents. Just easier to have it in a single centralized location. All right, checking in on the progress of Codex here. It's doing stuff and we can see on the right pane it's installing the dependencies for Hermes agent and again I don't have to manage it you know I just have a powerful agent like Codex or cloud code and I trusted that it will do what I tked it to do so again the leverage on using AI agents if you have the right setup is really immense you can literally use one AI agent to help you set up another one right so on this VPS I would have to do this myself I would have to manage all these steps myself but since I have Codex already installed on my MacBook and since I CMAX installed on my MacBook. And since I gave Codex a skill on how to ma manage and use CMAX, all of this is just a walk in the park. It's super easy. And again, I literally open sourced all of my skills for free. It's going to be linked below the video. Just grab them. You can see there's a folder on agent orchestration, ops and setup, research and web, thinking docs, and skill offering. So, all of my skills, including the ones used here, like the CMAX skill and the VPS management skill, are completely open source now. Feel free to use them. Hermes installed. It asks um just go through the steps. Stop when it asks for open router API key. Okay, that's the only step I'm going to give it myself. All right. So, so back to CMAX here. As you can see, Codex went through all the steps. You click through it and now it's asking for the open router API key. So, I'm going to say instead of giving it directly, I want to use aperture. Let's make sure the Okay, that's good. Telescale to ensure to store all the API keys and then we give them to the different AI agents on the different VPS servers from there. How do we do it? Guide me through it. Be very concise. So since this is during the setup, I'm not sure how we can insert it there. So again, here is using another one of my skills. Setup help. And then using the API, I did a quick web search. I already have uh Aperture set up. I already added it to RTL scale network. What's next? Okay, so the voice transcription up here. So here I am in Aperture, but since honestly I'm pretty new to this, I just going to take a screenshot and get Codex to guide me. So paste that in and say guide me through the UI. Another op use case of using AI agents, sending it screenshots and helping you do the setup that the agent cannot do. Okay, go to providers in the API key section. All right. Here go to providers. Okay. Boom. Add a provider. Open router. Okay. And let's say like you know anytime you want more inputs just do another screen should say what now. And again it's following my setup help skill. That's why it's formatting the responses in this way. Current step past your opener API key into the API key field. Just going to create a new one here. Tail scale testing. Put some limit $10. It's fine. Create. Copy. Back to aperture. store it here. Uh uh uh models. We definitely want more models. So, let's go back to open router. Let's maybe add uh 5.6 soul. Why not replace the latest model for OpenAI? Boom. Enter. Okay. Why is there What the Nobody's using Llama 3.1. That is pretty sketchy selection here. Even these are outdated. Haiku. Nobody's using Haiku, guys. If you're using Haiku 4.5, please you need to renounce your sins. This crazy. Uh, this list is absolutely crazy. Uh, whatever. If anything, we want to use like communicated 7 code, right? If you want some fast, efficient models. Boom. We also would probably want GLM 5.2, you know, whatever. We can probably change this later as well. So, I'm going to screenshot this again. It should probably be all good, but let's confirm. All good now. All right. Let's add the provider. Create access for log. Okay. Can do a quick test here. It's going to test all three VPSs. Okay. Amazing. So, let's do a screenshot. What now? Agent config in the left sidebar. There we go. There's no Hermes agent here. There is no Hermes agent. So since Hermes needs a OpenAI compatible endpoint, I'm going to click on the Codex tab and I'm going to ask Codex if it has everything. Do you have everything to finish the Hermes agent setup? Yes or no? So get to work and finish it using tail scale and aperture to manage our open router API key. Get to work. The setup for Hermes agent is still in the CMAX pane. I would say the other CMAX pane. Boom. So now we provided codeex with the info that it was missing which namely is the opener API key and this is going to be stored securely on aperture now and by the way a bit more about aperture this is tail skills AI gateway so it also lets you run providers but we're using it to store API keys securely so it joins your tail net as a node so that agents can reach it privately over tail scale so your real API keys for openi enthropy google or custom endpoints live in one place never on individual machines it's securely stored in Aperture or let's check on the setup here. As you can see, CMAX I'm not doing anything. CMAX allows Codex to do all of the steps for the Hermes agent setup. So, this is crazy, right? Even the clicking like literally month or two ago, I would still be doing the clicking here, selecting the options, but we don't have to do any of that. We literally don't like we just tell the goal to codeex and because I have it set up in Cmax, I can just do these steps and I literally have my hands off the keyboard and it's able to progress through the setup, insert stuff, make selections, make decisions. It's really incredible. Okay, there we go. Seems like Hermes Asian installation is complete. I'm wiring its model provider to Aperture and testing it. So, one thing that I noticed with this generation of latest AI models like Fable and GBD 5.6 is that they do a lot more tests and you don't have to tell them this, right? So, anytime they do a change, if you use the previous generation, it will just make the change, right? Opus or GBD 5.5, they would do what you tell them, but they wouldn't really care about the results or the implications. Fable and GBD 5.6, they do care. They make a change and they figure out, okay, was this a breaking change? Is the performance good? You know, they run a few tests to see like does it work? Does it do the things that we wanted it to do? Does it have any side effects? These models are way way smarter and it's really incredible. And I do believe you can just build build anything if you have good product intuition and a good vision and good taste, you can build anything. People complain about slop, right? AI turning out slop. I completely disagree. I think 99% of slop is because of the humans. The humans don't know what to build. The humans using the AI have no taste. They have no experience of what it takes to make a great product. They don't have deep domain expertise to solve that very specific problem. And that's why they're churning out slop. It's because they're telling the AI to make slop, not because of the AI is not capable enough. If you're using Fable 5, if you're using GBD 5.6, these models are more than capable to build any piece of software you want. You just need to know what to build and have the work ethic to build it. All right. So now Codex is testing Hermes with aperture. We say aperture. Okay. All right. It says setup complete. Hermes agent V08 installed model GLM 5.2 request route through aperture over tail scale. Open our key is not stored on the VPS end to end test return. So now we can do Hermes can chat with it. Obviously you can connect it to discord telegram all of that. I've shown you that in many different videos. And let's do the test ourselves. Who are you? I'm Hermes agent AI assistant but news research. Amazing. So, I'm going to say, are we still connected to the VPS through tail scale? Just to confirm, I know the answer is yes. Now, I want you to change the model inside of Hermes agent to be GPT 5.6 Soul instead, not GLM 5.2. Do this change right now. Change the default model in Hermes. So, again, this would be something that you would have to do yourself. But with the scale you can, you know, anytime a new model comes out, let's say you have five different agents on five different VPSs or one of them is on a Mac studio, the other one is on a, you know, laptop, whatever. If you put all these devices on tail scale, all it takes is sending one prompt to your personal agent and it can update all of your agents to the latest and greatest model like by itself and you're saving 20, 30, 40 minutes easily. I mean the amount of times I spent 30 to 60 minutes just fixing some open claw issue is more than I would like to admit right and uh people know it and this is why people switch away from agents like open claw or hermes but uh with tail scale a lot of these issues disappear completely and again my hands are lifted guys I need to stress this I'm not doing this I just told it my goal update the default model to GBD 5.6 And it's doing that itself and end to end test passed. Okay, amazing. So, let's try it. So, it it did a test itself again, but now I can do a manual test myself. What model are you? We already see it here, but you know, I wanted to answer. Yeah, I'm running OpenAs GB 56 through Hermes agent. Amazing. And if you want to triple check this, we can literally go to open router logs and we should see boom, here we go. 5.6 Excel provider openai blah blah blah tokens per second right here and yeah it works. So we have set up brand new Hermes agent on a VPS. We have logged down the VPS making it completely secure only accessible via tail scale. We have used correct CLI to install everything and to set it up to change the model for us and we're securely storing the API keys on aperture. This already just the contents in this one video will already put you ahead of 99% of people in AI. Most of them have no idea what their scale is. Most of them are storing API keys insecurely. Most of them have VPS servers with open ports and you know disabled firewalls and all that stuff. If you actually do the steps and which I would highly recommend you go through it again and follow it, right? If you just watch this video and you didn't implement it, go through it again and follow all these steps yourself. Do it for your own servers. Do it for your own agents. If you don't have a VPS, I already showed you how to get one from Hostinger and how to set it up. Please do these steps yourself. The future is going to be full of agents. All of us are going to be running 10, 20, 30, 50, 100 agents doing all kinds of different things for us. All of us are going to be managing multiple different computers, multiple different VPSs. You need to get familiar with this technologies. Now, this is why I made this video about tail scale. And instead of, you know, talking about tail scale only, I made it specific to AI agents. How to use tail scale with a agents because this is only the beginning.