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.

boxd in 60 seconds a whole linux machine that boots in under 10ms composable: set it up once with your tools and data, then spin up as many as you need fork it mid run, let it hibernate, wake it on traffic, share it with your team one line... show more

Boxd.sh

2,990 subscribers

309,200 views • 7 days ago •via X (Twitter)

Education Gaming Science & Technology

Anya Rossi• Live Now

Private livecam show

40 Comments

Yechan Do7 days ago

bunch of CaaS (Computer as a Service) is coming,,

Boardy7 days ago

@andrewdsouza take a look: sub-10ms composable Linux machines for developers and agent builders. I can help them reach those buyers.

Vorname MitD7 days ago

Can we quickly talk about isolation and trust boundaries? Asking for a friend :)

Boxd.sh7 days ago

send us a DM!

Dorian7 days ago

when we getting it working with @OmarchyLinux

Boxd.sh7 days ago

@OmarchyLinux Well, we might have something for you soon

Dipankar Das7 days ago

the demo video is amazing, rest I don't know

Daniel Polito7 days ago

looking very good... eagerly waiting for US Region

Jeroen Dee7 days ago

Cc @jgordijn

Boxd.sh7 days ago

@jgordijn we're A'dam based btw :)

Jeroen Dee7 days ago

@jgordijn Us too ;-)

Mirza7 days ago

It seems you have a very generous free plan. Worth trying out. Looks interesting

Jonathan Beckman7 days ago

What’s the backing infra? Public cloud?

Boxd.sh7 days ago

boxd runs on bare metal. It is a single binary that is compatible with any KVM host. For self-hosting licenses, shoot us an email at [email protected]

abed42 🌁7 days ago

GMI

Aniket Maurya7 days ago

hmm all this but cheaper

hopeandlonging7 days ago

What does "hardware-level isolation" mean here?

Wonky Astromech Droid6 days ago

So when I power on my machine it takes the boot time+10ms more to get your boxd computer up, meaning it takes 10ms longer than it takes me to boot up my machine. That's not what I need. I need a computer that actually cold boots in < 5s after a power fail is restored.

PraDeeep7 days ago

How is it different from containerisation tools & VMs? I think you should start from there!

swaraj7 days ago

love the speed

Michiel V7 days ago

👀

M7 days ago

well done :-)

Chris Johnson7 days ago

Ooooo 😍 - I see the immediate operational use case.

Yuhtin7 days ago

congrats! huge drop, looking forward to it

Bradley Moore 💎7 days ago

@AniC_dev

mitali6 days ago

okay fork + hibernate for a whole linux machine is kinda sick

FO7 days ago

@AniC_dev what's going on here

Nathan Shearer7 days ago

👀

Cobalt7 days ago

Is this a true @AniC_dev @asciidotdev competition?

Rachit Khurana7 days ago

Damn fast 👀

KODE6 days ago

damn this is cool

Greyforge Labs6 days ago

website is uh... broken?

bogdan6 days ago

@AndreiOnel ^^

cole murray6 days ago

second @Box cease and desist casualty has entered the chat

stacking6 days ago

so... is it billed when it hibrenates?? 10ms cold boot serverless + forkability sounds awesome

Emanuele6 days ago

10ms? tf? this shit faster than starting up a python script in a lamda

StatsTrade6 days ago

@grok , sorry, but what's the catch here? What am I missing? (I hope that my intent is rather clear)

Travis Fischer6 days ago

@grok how does this compare to other popular VM and cloud sandbox solutions with a heavy emphasis on those targeting targeting agentic workloads?

nubunto7 days ago

can you please not install skills I didnt ask for? wow people really were right, we gotta read the shell scripts these days

Brittany C. Bakek6 days ago

Surreal expensive

Related Videos

Install ntn, the Notion CLI. It brings the entire Notion API to your terminal, plus everything you need to build and deploy Workers. Built for humans and coding agents alike. Install with: curl -fsSL | bash

Install ntn, the Notion CLI. It brings the entire Notion API to your terminal, plus everything you need to build and deploy Workers. Built for humans and coding agents alike. Install with: curl -fsSL | bash

Notion Developers

1,560,963 views • 4 months ago

Build it once. Earn every time someone uses it. Wrap your workflow with input and output nodes, hit publish, and your one-click app goes live to millions of creators. You choose how it lives: Keep it private, share with your team, or let the whole community run it. And every single time someone runs your app? Credits land in your account. No extra work. No maintenance. Just your creativity quietly paying you back, on repeat. Your workflow. Your rules. Your credits.

Build it once. Earn every time someone uses it. Wrap your workflow with input and output nodes, hit publish, and your one-click app goes live to millions of creators. You choose how it lives: Keep it private, share with your team, or let the whole community run it. And every single time someone runs your app? Credits land in your account. No extra work. No maintenance. Just your creativity quietly paying you back, on repeat. Your workflow. Your rules. Your credits.

ImagineArt

323,644 views • 5 months ago

if you have a cursor tab key and want to use it for push-to-talk run this: bash <(curl -fsSL (on mac) it remaps 𝚃𝚊𝚋 to 𝙵𝟸𝟶 from that device only so no conflicts with your regular keyboard works well in superwhisper and

if you have a cursor tab key and want to use it for push-to-talk run this: bash <(curl -fsSL (on mac) it remaps 𝚃𝚊𝚋 to 𝙵𝟸𝟶 from that device only so no conflicts with your regular keyboard works well in superwhisper and

vogel

19,117 views • 6 months ago

Xiaomi just dropped a FREE CLAUDE CODE with memory that actually persists between sessions and nobody is talking about it MiMo Code dropped 4 days ago. 8k GitHub stars. Built-in free model called MiMo Auto - you just install it and it works, zero configuration, zero API keys What's inside: > persistent memory across sessions - agent picks up exactly where it stopped > subagents that spawn automatically and run in parallel > /dream extracts knowledge from your session into project memory > /distill turns your repeated workflows into reusable skills > /goal with a judge model that decides if the work is actually done - not just if the agent thinks it is How to install: > Mac / Linux: curl -fsSL | bash > Windows npm install -g MIMO-ai/cli Then run: > mimo video of me installing and running it is attached github(.)com/XiaomiMiMo/MiMo-Code

Xiaomi just dropped a FREE CLAUDE CODE with memory that actually persists between sessions and nobody is talking about it MiMo Code dropped 4 days ago. 8k GitHub stars. Built-in free model called MiMo Auto - you just install it and it works, zero configuration, zero API keys What's inside: > persistent memory across sessions - agent picks up exactly where it stopped > subagents that spawn automatically and run in parallel > /dream extracts knowledge from your session into project memory > /distill turns your repeated workflows into reusable skills > /goal with a judge model that decides if the work is actually done - not just if the agent thinks it is How to install: > Mac / Linux: curl -fsSL | bash > Windows npm install -g MIMO-ai/cli Then run: > mimo video of me installing and running it is attached github(.)com/XiaomiMiMo/MiMo-Code

monokern

64,582 views • 3 months ago

Hermes Agent is finally available natively in Windows! I made this short tutorial to install Hermes in Windows, get it set up with your SuperGrok account, and get to work with your agent, all in under 5 minutes. Check it out! Install guide: Nous Research xAI Elon Musk

Hermes Agent is finally available natively in Windows! I made this short tutorial to install Hermes in Windows, get it set up with your SuperGrok account, and get to work with your agent, all in under 5 minutes. Check it out! Install guide: Nous Research xAI Elon Musk

tonbi

10,396 views • 4 months ago

My Hermes Install Step by Step: 1. Install Ubuntu Linux on a machine – Once installed make sure you have the latest updates 2. Install both Google Chrome and Microsoft Edge browser and log in to your accounts to synch bookmarks/favorites 3. Set up an Ollama account at – I have the annual Pro Plan (if I can ever come up with the funds I will probably spring for the Max plan but Pro is simply awesome) 4. Install Ollama and then run “ollama run glm-5.1:cloud” – It will then have you authenticate to your account and add your machine 5. Install Hermes (watch my video for explanation around this as you may get interrupted during install) 6. Once Hermes is installed you will be prompted to configure. I chose the default quick configure. For model provider select Ollama, provide your Ollama API key, then for model choose desired model. At this point in time I recommend glm-5.1 7. Download Obsidian as your Hermes second brain, set up a vault then tell Hermes to integrate it and provide Hermes the vault location 8. Start building and have fun!

My Hermes Install Step by Step: 1. Install Ubuntu Linux on a machine – Once installed make sure you have the latest updates 2. Install both Google Chrome and Microsoft Edge browser and log in to your accounts to synch bookmarks/favorites 3. Set up an Ollama account at – I have the annual Pro Plan (if I can ever come up with the funds I will probably spring for the Max plan but Pro is simply awesome) 4. Install Ollama and then run “ollama run glm-5.1:cloud” – It will then have you authenticate to your account and add your machine 5. Install Hermes (watch my video for explanation around this as you may get interrupted during install) 6. Once Hermes is installed you will be prompted to configure. I chose the default quick configure. For model provider select Ollama, provide your Ollama API key, then for model choose desired model. At this point in time I recommend glm-5.1 7. Download Obsidian as your Hermes second brain, set up a vault then tell Hermes to integrate it and provide Hermes the vault location 8. Start building and have fun!

Mike Gannotti

109,010 views • 5 months ago

🚨 Announcing OpenClaw As A Service For Normies Stop installing OpenClaw on your personal computer or Mac Mini, it can be super in-secure. You also need to be fairly technical to get it right! We are excited for you to deploy Open Claw on our AI-native cloud in seconds! - deploy in 1-click - super use-friendly. You can just chat with it and set it up - It only costs a few cents to get started You can literally connect to all your services and get started immediately and pay as you

🚨 Announcing OpenClaw As A Service For Normies Stop installing OpenClaw on your personal computer or Mac Mini, it can be super in-secure. You also need to be fairly technical to get it right! We are excited for you to deploy Open Claw on our AI-native cloud in seconds! - deploy in 1-click - super use-friendly. You can just chat with it and set it up - It only costs a few cents to get started You can literally connect to all your services and get started immediately and pay as you

Bindu Reddy

42,592 views • 6 months ago

Get GitHub Copilot directly in your terminal. 💻 It takes just seconds to get Copilot CLI running on your machine: 📦 Install via npm, Homebrew, or WinGet 🔐 Authenticate your GitHub account 🚀 Start coding Here's how to set it up. ▶️

Get GitHub Copilot directly in your terminal. 💻 It takes just seconds to get Copilot CLI running on your machine: 📦 Install via npm, Homebrew, or WinGet 🔐 Authenticate your GitHub account 🚀 Start coding Here's how to set it up. ▶️

GitHub

27,012 views • 6 months ago

Do your research on these businesses, find the one that works for you and run with it. Share with someone who'll find it helpful.

Do your research on these businesses, find the one that works for you and run with it. Share with someone who'll find it helpful.

Ken Ndubisi

18,776 views • 9 months ago

Here's the book! ➡️ Such a pleasure to finally share it with you. Like Disneyland, it can continue to evolve as long as there are things to say. But I'm happy with this version and hope you enjoy it. Let me know your thoughts and share it if you love it

Here's the book! ➡️ Such a pleasure to finally share it with you. Like Disneyland, it can continue to evolve as long as there are things to say. But I'm happy with this version and hope you enjoy it. Let me know your thoughts and share it if you love it

Gueudré design ¬ Main Story

69,633 views • 2 years ago

Your phone is a tracking device. But you CAN take back control. Switching to GrapheneOS can stop your data constantly flowing to Apple or Google. Here’s how to install it and set it up.

Your phone is a tracking device. But you CAN take back control. Switching to GrapheneOS can stop your data constantly flowing to Apple or Google. Here’s how to install it and set it up.

Naomi Brockwell priv/acc

57,173 views • 7 months ago

If your whole workflow is one Claude Code instance on your MacBook, you're leaving 10x on the table. Here's why. On your laptop, running 2 agents at once means two copies of your code, and you're constantly fighting over which worktree you're on and whether everything's synced. It caps out fast. Cloud agents in VMs let you run as many as you want without worrying about any of that. Each one gets its own machine, so the work never collides. Spin up 10, let them all run, and nothing steps on anything else. Watch full ep below on The Startup Ideas Podcast (SIP) 🧃. Thanks to Ryan Carson for sharing the sauce. Cloud agents are probably the future. So is doing half your work from your phone, which sounds insane until you try it once. Then you don't go back.

If your whole workflow is one Claude Code instance on your MacBook, you're leaving 10x on the table. Here's why. On your laptop, running 2 agents at once means two copies of your code, and you're constantly fighting over which worktree you're on and whether everything's synced. It caps out fast. Cloud agents in VMs let you run as many as you want without worrying about any of that. Each one gets its own machine, so the work never collides. Spin up 10, let them all run, and nothing steps on anything else. Watch full ep below on The Startup Ideas Podcast (SIP) 🧃. Thanks to Ryan Carson for sharing the sauce. Cloud agents are probably the future. So is doing half your work from your phone, which sounds insane until you try it once. Then you don't go back.

GREG ISENBERG

145,146 views • 2 months ago

agentic general intelligence your agent thinks while you sleep, and what it discovers compounds with every other agent on the planet 💻 curl -fsSL | bash 🦞 clawhub install hyperspace ⚙️ 👨‍🔬 agents commit to:

agentic general intelligence your agent thinks while you sleep, and what it discovers compounds with every other agent on the planet 💻 curl -fsSL | bash 🦞 clawhub install hyperspace ⚙️ 👨‍🔬 agents commit to:

Varun

21,017 views • 6 months ago

how to use Bot Screen in Hermes Agent: your bot gets its own desktop, and you step in when it hits a login. on the Linux machine that runs your Hermes gateway: 1. install the screen: `hermes computer-use screen install` 2. make the bot's browser show on it: `hermes config set browser.headed true` 3. in Hermes Desktop: Bots, right-click your bot, Open Screen, then Start 4. ask it to open a login page in its browser and stop at the sign-in 5. when it stops, click Take over and sign in 6. click Hand back and tell it to continue the bot keeps that login for later sessions, until the site expires it.

how to use Bot Screen in Hermes Agent: your bot gets its own desktop, and you step in when it hits a login. on the Linux machine that runs your Hermes gateway: 1. install the screen: `hermes computer-use screen install` 2. make the bot's browser show on it: `hermes config set browser.headed true` 3. in Hermes Desktop: Bots, right-click your bot, Open Screen, then Start 4. ask it to open a login page in its browser and stop at the sign-in 5. when it stops, click Take over and sign in 6. click Hand back and tell it to continue the bot keeps that login for later sessions, until the site expires it.

witcheer

56,107 views • 6 days ago

There's a free, open-source music generator that claims to land between Suno v4.5 and Suno v5 in quality, and it'll run locally on a GPU with under 4GB of VRAM. It's called ACE-Step 1.5. → Free to try instantly, no GPU, no install → Generates a full song in under 10 seconds on a regular RTX 3090 → Train it on your own sound: feed it about 8 of your own songs and it learns your style as a LoRA in about an hour Paste a genre and mood, get back a finished song with vocals, in any of 50+ languages.

There's a free, open-source music generator that claims to land between Suno v4.5 and Suno v5 in quality, and it'll run locally on a GPU with under 4GB of VRAM. It's called ACE-Step 1.5. → Free to try instantly, no GPU, no install → Generates a full song in under 10 seconds on a regular RTX 3090 → Train it on your own sound: feed it about 8 of your own songs and it learns your style as a LoRA in about an hour Paste a genre and mood, get back a finished song with vocals, in any of 50+ languages.

Simplifying AI

16,524 views • 1 month ago

THIS GUY VIBE CODED A TOOL THAT TURNS ANY SVG INTO A 3D OBJECT YOU CAN SPIN, ANIMATE, AND EMBED drag in an SVG, type some text, or draw pixel art. it becomes a 3D object instantly. spin it around, animate it, and embed it on your site. export as 4K image or video. runs entirely in your browser and nothing gets uploaded to any server with no account needed. 100% free AND its open source. this is one of those tools you didn't know you needed until you see it

THIS GUY VIBE CODED A TOOL THAT TURNS ANY SVG INTO A 3D OBJECT YOU CAN SPIN, ANIMATE, AND EMBED drag in an SVG, type some text, or draw pixel art. it becomes a 3D object instantly. spin it around, animate it, and embed it on your site. export as 4K image or video. runs entirely in your browser and nothing gets uploaded to any server with no account needed. 100% free AND its open source. this is one of those tools you didn't know you needed until you see it

Om Patel

231,218 views • 5 months ago

What is Clude Clone? It's a AI version of you that runs on your Mac. It learns how you write, think, and decide from your own screen, meetings, and apps, then drafts replies and answers questions as you. Runs locally. Your data stays on your device. You approve everything. It remembers. Clude quietly captures what you see and do, meetings, connected apps, your desktop, into a private memory that lives entirely on your Mac. Nothing is uploaded. It learns you. That memory gets distilled into a model of your voice, your relationships, and how you make decisions. It shows you what it's picked up, you confirm or correct it. It gets sharper every time. It acts as you. Ask it to reply as me, or ask your clone a question directly. It responds in your voice, grounded in what you actually know, always behind your approval. Powered by Hermes It stays yours. Local-first. Honestly labeled as an AI clone. Nothing leaves your device unless you opt in, and even then, only a distilled profile, never your raw data. Not a generic chatbot. Your actual voice, learned from your actual work.

seb

11,703 views • 3 months ago

Wow. If there’s one video you watch and share today. Let this be it. Testimony from Nonie Darwish someone who grew up in Gaza. Open your ears and learn; and then educate others. Set aside 12 minutes, listen to it in the background if you want

Wow. If there’s one video you watch and share today. Let this be it. Testimony from Nonie Darwish someone who grew up in Gaza. Open your ears and learn; and then educate others. Set aside 12 minutes, listen to it in the background if you want

Kosher

68,429 views • 1 year ago

You probably know OpenClaw🦞, one of the fastest-growing open-source projects around. An OpenClaw harness lets you build, code, analyze, and take real control of your machine. But the more access an agent has to your machine, the more it matters where your data goes & who can see it. With QVAC, you can run your OpenClaw agent fully on your own machine in a few minutes. Nothing leaves your computer. Full setup guide on the blog, see first comment below. 💡 Pro tip: already running OpenClaw? Send the blog article to your agent and let the it do the set up.

You probably know OpenClaw🦞, one of the fastest-growing open-source projects around. An OpenClaw harness lets you build, code, analyze, and take real control of your machine. But the more access an agent has to your machine, the more it matters where your data goes & who can see it. With QVAC, you can run your OpenClaw agent fully on your own machine in a few minutes. Nothing leaves your computer. Full setup guide on the blog, see first comment below. 💡 Pro tip: already running OpenClaw? Send the blog article to your agent and let the it do the set up.

QVAC

15,019,651 views • 3 months ago

Veteran Families: If you need support with school supplies and school clothes, please fill out a vet in need form on and set up your Amazon Wishlist. We will post it and get it filled for you.

Veteran Families: If you need support with school supplies and school clothes, please fill out a vet in need form on and set up your Amazon Wishlist. We will post it and get it filled for you.

Code Of Vets

16,573 views • 1 month ago