Loading video...

Video Failed to Load

Go Home

The quickest/simplest demo of running a microVM for claude on a Linux machine you own. Here I connect via the API or SSH to run commands. Also included cp, exec, and port-forwarding for syncing work and ralph loops.

alexellisuk's profile picture

Alex Ellis

30,959 subscribers

25,556 views • 4 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Introducing cmux SSH: `cmux ssh user@remote` You can now drag images into SSH'd Claude Code sessions, and cmux will automatically upload them via scp. And when you start a dev server on the remote machine, the browser pane in cmux can reach it at localhost:3000 without port forwarding. The workspace kinda becomes the remote machine, so split panes/new tabs automatically open remote shells. Out in the latest version of cmux (0.63).
2:23

Introducing cmux SSH: `cmux ssh user@remote` You can now drag images into SSH'd Claude Code sessions, and cmux will automatically upload them via scp. And when you start a dev server on the remote machine, the browser pane in cmux can reach it at localhost:3000 without port forwarding. The workspace kinda becomes the remote machine, so split panes/new tabs automatically open remote shells. Out in the latest version of cmux (0.63).

Lawrence Chen

49,311 views • 2 months ago

New Demo: Connect any Hyperbolic GPU to a Colaboratory notebook using SSH tunneling with custom port selection. This demo guides you through setting up a Colab Local Runtime and running high-performance matrix multiplication directly on one of our H100 SXM instances. It's a great workflow for fine-tuning via Unsloth AI and academic environments where local compute is limited.
1:34

New Demo: Connect any Hyperbolic GPU to a Colaboratory notebook using SSH tunneling with custom port selection. This demo guides you through setting up a Colab Local Runtime and running high-performance matrix multiplication directly on one of our H100 SXM instances. It's a great workflow for fine-tuning via Unsloth AI and academic environments where local compute is limited.

Hyperbolic

22,639 views • 1 year ago

Claude Cowork gives you a peek into the future of knowledge work. Here's a demo of using Box as a cloud filesystem via MCP for Claude to leverage content as context to generate new slides locally. The future is having agents running in the background doing work for you.
1:00

Claude Cowork gives you a peek into the future of knowledge work. Here's a demo of using Box as a cloud filesystem via MCP for Claude to leverage content as context to generate new slides locally. The future is having agents running in the background doing work for you.

Aaron Levie

61,100 views • 5 months ago

Curious how NanoClaw + Docker Sandboxes actually work? This demo walks through setting up NanoClaw in a Docker Sandbox - connecting messaging accounts, configuring agent tools and access, and running agents inside an isolated MicroVM instead of on your machine. Watch the full demo and learn more →
1:06

Curious how NanoClaw + Docker Sandboxes actually work? This demo walks through setting up NanoClaw in a Docker Sandbox - connecting messaging accounts, configuring agent tools and access, and running agents inside an isolated MicroVM instead of on your machine. Watch the full demo and learn more →

Docker

14,653 views • 2 months ago

"I don't prompt Claude anymore. I have loops running that prompt Claude and figuring out what to do. My job is to write loops. And this is transition we're going to see for the rest of the year." - Boris Cherny, head of Claude Code at Anthropic.
0:40

"I don't prompt Claude anymore. I have loops running that prompt Claude and figuring out what to do. My job is to write loops. And this is transition we're going to see for the rest of the year." - Boris Cherny, head of Claude Code at Anthropic.

Rohan Paul

2,302,968 views • 9 days ago

And here it is running on Arch Linux (btw), this was A LOT of work...
1:18

And here it is running on Arch Linux (btw), this was A LOT of work...

XWine1

46,209 views • 1 year ago

You can now schedule recurring cloud-based tasks on Claude Code. Set a repo (or repos), a schedule, and a prompt. Claude runs it via cloud infra on your schedule, so you don’t need to keep Claude Code running on your local machine.
0:27

You can now schedule recurring cloud-based tasks on Claude Code. Set a repo (or repos), a schedule, and a prompt. Claude runs it via cloud infra on your schedule, so you don’t need to keep Claude Code running on your local machine.

Noah Zweben

2,031,952 views • 2 months ago

Creator of Claude Code : "I don't prompt Claude anymore. I create loops - and the loops do the work. My job is to create loops." In 30 minutes, Boris breaks down his real daily Claude Code setup. Claude + loops + routines + dynamic workflow Worth more than a $500 vibe-coding course
29:27

Creator of Claude Code : "I don't prompt Claude anymore. I create loops - and the loops do the work. My job is to create loops." In 30 minutes, Boris breaks down his real daily Claude Code setup. Claude + loops + routines + dynamic workflow Worth more than a $500 vibe-coding course

Codez

145,339 views • 10 days ago

Boris has Claude Code loops running on cron all day - One babysits his PRs and fixes CI - Another keeps CI healthy - Another pulls Twitter feedback every 30 min and clusters it His Claude Code setup is simple and pretty close to mine That's what I like about Claude Code. Hundreds of options, but the simplest setup just works, you probably don't need more than that And since one of those loops reads Twitter every 30 min, Boris Cherny (or his Claude on cron) is reading this post whether he wants to or not 😅
1:16

Boris has Claude Code loops running on cron all day - One babysits his PRs and fixes CI - Another keeps CI healthy - Another pulls Twitter feedback every 30 min and clusters it His Claude Code setup is simple and pretty close to mine That's what I like about Claude Code. Hundreds of options, but the simplest setup just works, you probably don't need more than that And since one of those loops reads Twitter every 30 min, Boris Cherny (or his Claude on cron) is reading this post whether he wants to or not 😅

Daniel San

121,041 views • 1 month ago

No Claude plan? You can still use Claude Code. Connect it to Jan and run local models on your own machine. That means no subscription and no token caps. Download Jan v0.7.7 at
0:23

No Claude plan? You can still use Claude Code. Connect it to Jan and run local models on your own machine. That means no subscription and no token caps. Download Jan v0.7.7 at

👋 Jan

250,144 views • 3 months ago

Claude Code creator: "I don't prompt Claude anymore. I write loops - and the loops do the work. My job is to write loops." in 30 minutes Boris reveals his actual daily Claude Code setup. Claude Code + loops + dynamic workflow Worth more than a $500 vibe-coding course
29:51

Claude Code creator: "I don't prompt Claude anymore. I write loops - and the loops do the work. My job is to write loops." in 30 minutes Boris reveals his actual daily Claude Code setup. Claude Code + loops + dynamic workflow Worth more than a $500 vibe-coding course

Codez

861,473 views • 12 days ago

Hot tip for anyone doing AI dev: Use Ollama to easily run models like Deepseek-r1 or Gemma locally on your machine. It downloads them and spins up a server with an OpenAI SDK compatible API The smaller models are fast and good enough to work on new features or debug streaming without having to pay for API requests
2:08

Hot tip for anyone doing AI dev: Use Ollama to easily run models like Deepseek-r1 or Gemma locally on your machine. It downloads them and spins up a server with an OpenAI SDK compatible API The smaller models are fast and good enough to work on new features or debug streaming without having to pay for API requests

Wes Bos

153,435 views • 11 months ago

🚀 I created a simple ChatGPT like app to connect to ollama With Ollama you can run Large Language Models (LLMs) offline on your own machine Follow these 3 simple steps to get it up and running 🧵
0:28

🚀 I created a simple ChatGPT like app to connect to ollama With Ollama you can run Large Language Models (LLMs) offline on your own machine Follow these 3 simple steps to get it up and running 🧵

Juan Stoppa

18,066 views • 2 years ago

There is a new self-hosted personal AI-Agent platform called PocketPaw. 100% open source. 'pip install pocketpaw' and in less than 60 seconds you own an AI agent. It connects to WhatsApp, Slack, Discord, and a local Web Dashboard. Capable of browsing the web, managing Gmail/Calendar, and executing code. Runs entirely on your machine using local Ollama models or Claude/OpenAI. Includes "Guardian AI" to review shell commands for security + 6 layers of defence. Watch the demo 👇
1:54

There is a new self-hosted personal AI-Agent platform called PocketPaw. 100% open source. 'pip install pocketpaw' and in less than 60 seconds you own an AI agent. It connects to WhatsApp, Slack, Discord, and a local Web Dashboard. Capable of browsing the web, managing Gmail/Calendar, and executing code. Runs entirely on your machine using local Ollama models or Claude/OpenAI. Includes "Guardian AI" to review shell commands for security + 6 layers of defence. Watch the demo 👇

AshutoshShrivastava

24,585 views • 3 months ago

Claude Code is insane. And yes… there’s a free version. Here’s how it works: → install the free Claude Code repo → connect Nvidia NIM free API → map Opus to GLM-4.7 → run local proxy server → launch Claude Code normally → start building apps for $0 Same workflow. No monthly API bill. Save this video, you’ll stop paying for Claude Code.
7:22

Claude Code is insane. And yes… there’s a free version. Here’s how it works: → install the free Claude Code repo → connect Nvidia NIM free API → map Opus to GLM-4.7 → run local proxy server → launch Claude Code normally → start building apps for $0 Same workflow. No monthly API bill. Save this video, you’ll stop paying for Claude Code.

Julian Goldie SEO

16,438 views • 1 month ago

I ported Linux to the PS5 and turned it into a Steam Machine. Running GTA 5 Enhanced with Ray Tracing. 🤯
0:31

I ported Linux to the PS5 and turned it into a Steam Machine. Running GTA 5 Enhanced with Ray Tracing. 🤯

Andy Nguyen

2,278,075 views • 3 months ago

🦞 Aniclaw — connect companions to your OpenClaw! Here is a quick demo of how it works. Conversions are flowing seamlessly even for long running tasks and it adds a lot of fun to the process. Link in the reply.
0:52

🦞 Aniclaw — connect companions to your OpenClaw! Here is a quick demo of how it works. Conversions are flowing seamlessly even for long running tasks and it adds a lot of fun to the process. Link in the reply.

Sergey Gonchar

110,249 views • 4 months ago

Sometimes you build a tool just to streamline your own work. Here is the demo of "Televector" Telegram OSINT platform, not available to the public, developed purely for my own use :) -Live monitoring with API -Hash database -Matkap module -Threat analysis with ai
1:38

Sometimes you build a tool just to streamline your own work. Here is the demo of "Televector" Telegram OSINT platform, not available to the public, developed purely for my own use :) -Live monitoring with API -Hash database -Matkap module -Threat analysis with ai

0x6rss

83,683 views • 1 year ago

Didn't take very long. Codex on Linux is fine. Just ask Codex or Claude to port it to Linux lol
0:24

Didn't take very long. Codex on Linux is fine. Just ask Codex or Claude to port it to Linux lol

Rob Zolkos

52,189 views • 4 months ago

Yip-Boi lets you do Closed Captions for everything you hear, or your own voice, running Whisper 100% locally. (Thanks to BorkSalt and Spiro Renard for the demo)
0:40

Yip-Boi lets you do Closed Captions for everything you hear, or your own voice, running Whisper 100% locally. (Thanks to BorkSalt and Spiro Renard for the demo)

Foxipso

25,976 views • 2 months ago