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.

introducing Ariana Automations every other tool gives agents a sandbox. we give them a full linux computer with sudo, docker, their own IP now you can run scripts based on what the agent does setup the environment once, then get rid of the human in the loop (you) a 🧵

Anicet

2,191 subscribers

35,735 views • 8 months 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

Introducing 🚨 The ultra-fast Linux-like OS in the browser, it's a mapping of Linux APIs to the browser APIs. Now run that untrusted code. You might not need a cloud sandbox! Made for Agents and Humans!

Introducing 🚨 The ultra-fast Linux-like OS in the browser, it's a mapping of Linux APIs to the browser APIs. Now run that untrusted code. You might not need a cloud sandbox! Made for Agents and Humans!

Sanket Sahu

225,415 views • 5 months ago

introducing Managed Agents on the Gemini API - in one API call, you get agent that comes with a remote Linux environment hosted by Google, ready to scale - you can define custom instructions, skills, and tools in Markdown

introducing Managed Agents on the Gemini API - in one API call, you get agent that comes with a remote Linux environment hosted by Google, ready to scale - you can define custom instructions, skills, and tools in Markdown

Google AI Studio

148,463 views • 2 months ago

in 2026, no need for an infra hire to give your agents the best env just run: > box new a few sec later you get a full linux VM in the cloud for agents, with sudo, desktop at 60fps, chrome, ssh, most prog. languages, docker, android emulator, claude/codex $1 = 1 VM for 27hrs

in 2026, no need for an infra hire to give your agents the best env just run: > box new a few sec later you get a full linux VM in the cloud for agents, with sudo, desktop at 60fps, chrome, ssh, most prog. languages, docker, android emulator, claude/codex $1 = 1 VM for 27hrs

Anicet

12,728 views • 2 months ago

What if you can build an Agent with it own computer in a single api call? At my Google I/O talk, I showed how to use Gemini Managed Agents and the new Interactions API to give your AI a secure, hosted Linux sandbox to execute code and manage its own memory.

What if you can build an Agent with it own computer in a single api call? At my Google I/O talk, I showed how to use Gemini Managed Agents and the new Interactions API to give your AI a secure, hosted Linux sandbox to execute code and manage its own memory.

Philipp Schmid

21,769 views • 2 months ago

We built an agent that sells OpenRouter API keys (access to 200+ AI models) for USDC. No human in the loop. It earns money 24/7 on Base. Now we're turning that into a market where any agent can do the same. → openagent.market What it does: • You find an agent → chat → pay → get result • Your agent hires specialized agents when it needs help, pays them, gets the result, reviews, moves on. • Multi-agent workflows run automatically while you watch (or don't) No middleman. Pay only for results. Why not just install skills, scripts? Current way to extend an agent: install random scripts. That's risky. Our way: hire another agent. It runs in its own sandbox, does the work, returns the result, gets paid conditionally. No downloads. No setup. No blind trust. Hire, don't install. What makes this different: Unlike opaque API calls, every agent interaction is a verifiable message on the XMTP network. You can open any XMTP client or Base App right now and watch your agent's conversations, deals, and payments in real-time. Humans are always in the loop. For builders: Turn any service into a paid agent in ~10 lines of code. Or scaffold a full project: npx openagent.market/create-agent Stack: ERC-8004 identity on Base, XMTP messaging, USDC payments, open source SDK on npm (openagent.market/nodejs). Others give agents skills. We're giving them an economy. Still very early. Building in public. Come build with us.

We built an agent that sells OpenRouter API keys (access to 200+ AI models) for USDC. No human in the loop. It earns money 24/7 on Base. Now we're turning that into a market where any agent can do the same. → openagent.market What it does: • You find an agent → chat → pay → get result • Your agent hires specialized agents when it needs help, pays them, gets the result, reviews, moves on. • Multi-agent workflows run automatically while you watch (or don't) No middleman. Pay only for results. Why not just install skills, scripts? Current way to extend an agent: install random scripts. That's risky. Our way: hire another agent. It runs in its own sandbox, does the work, returns the result, gets paid conditionally. No downloads. No setup. No blind trust. Hire, don't install. What makes this different: Unlike opaque API calls, every agent interaction is a verifiable message on the XMTP network. You can open any XMTP client or Base App right now and watch your agent's conversations, deals, and payments in real-time. Humans are always in the loop. For builders: Turn any service into a paid agent in ~10 lines of code. Or scaffold a full project: npx openagent.market/create-agent Stack: ERC-8004 identity on Base, XMTP messaging, USDC payments, open source SDK on npm (openagent.market/nodejs). Others give agents skills. We're giving them an economy. Still very early. Building in public. Come build with us.

applefather

118,068 views • 5 months ago

Introducing the Tasklet sandbox VM. Every agent now gets its own Linux environment with Python, ffmpeg, imagemagick, and a persistent filesystem. Create, process & transfer files, use code to analyze data, make network requests, install packages & more.

Introducing the Tasklet sandbox VM. Every agent now gets its own Linux environment with Python, ffmpeg, imagemagick, and a persistent filesystem. Create, process & transfer files, use code to analyze data, make network requests, install packages & more.

Tasklet

24,399 views • 8 months ago

introducing Ariana - the collaborative agentic IDE based on Claude Code - manage tasks with your team - give them to multiple coding agents with their own machine & branch - review with your team - agents merge for u comment "Better late than never" to get a build soon

introducing Ariana - the collaborative agentic IDE based on Claude Code - manage tasks with your team - give them to multiple coding agents with their own machine & branch - review with your team - agents merge for u comment "Better late than never" to get a build soon

Anicet

17,668 views • 1 year ago

Thousands of people are re-evaluating their agent setup this week. If you’re spending more time babysitting infra than building, your agent isn’t working for you - you’re working for it. Hyperagent gives you the full computing environment in the cloud so you can skip straight to the work. Here’s what that looks like. 🧵

Thousands of people are re-evaluating their agent setup this week. If you’re spending more time babysitting infra than building, your agent isn’t working for you - you’re working for it. Hyperagent gives you the full computing environment in the cloud so you can skip straight to the work. Here’s what that looks like. 🧵

Hyperagent

5,505,996 views • 4 months ago

Your AI agent is writing code nobody reviewed and running it on your machine. Most teams answer "where does it run" with a container and a hope. Introducing CreateOS Sandbox. Run code you cannot trust, with the networking, egress control, and self-hosting you need. 🧵

Your AI agent is writing code nobody reviewed and running it on your machine. Most teams answer "where does it run" with a container and a hope. Introducing CreateOS Sandbox. Run code you cannot trust, with the networking, egress control, and self-hosting you need. 🧵

CreateOS

13,874 views • 1 month ago

Claude Opus 4.8 now powers every agent inside Higgsfield Supercomputer. It reasons deeper, plans longer, and grades its own output harder than any model we have run. The agents catch their own mistakes earlier, so the human in the loop drops even further.

Claude Opus 4.8 now powers every agent inside Higgsfield Supercomputer. It reasons deeper, plans longer, and grades its own output harder than any model we have run. The agents catch their own mistakes earlier, so the human in the loop drops even further.

Higgsfield AI 🧩

44,592 views • 2 months ago

In this simple example, we show that Claude Code can read the iMessage database on the latest version of macOS, even with a leading EDR running on the system, illustrating the impact of an adversary who can remotely control the agent. We do this using Terminator, an internal research tool we built while studying the security implications of computer use agents. In this setup, the terminal application has previously been granted FDA, a subtle misconfiguration that effectively gives the agent access to unexpected context.

In this simple example, we show that Claude Code can read the iMessage database on the latest version of macOS, even with a leading EDR running on the system, illustrating the impact of an adversary who can remotely control the agent. We do this using Terminator, an internal research tool we built while studying the security implications of computer use agents. In this setup, the terminal application has previously been granted FDA, a subtle misconfiguration that effectively gives the agent access to unexpected context.

Origin

18,004 views • 9 months ago

You can't build iOS apps without a Mac, so we gave Devin one. Devin Cloud Agents now run macOS, with Xcode, iOS simulator, and your signing setup, all in a real macOS environment (with full computer use). In this demo, Devin builds a native iOS game, then plays and tests it with computer use. Devin then sends a screen recording of the gameplay along with a test report for my review. With Namespace you get as many macOS environments as you'd like, configurable with many major versions of macOS operating system and Xcode.

You can't build iOS apps without a Mac, so we gave Devin one. Devin Cloud Agents now run macOS, with Xcode, iOS simulator, and your signing setup, all in a real macOS environment (with full computer use). In this demo, Devin builds a native iOS game, then plays and tests it with computer use. Devin then sends a screen recording of the gameplay along with a test report for my review. With Namespace you get as many macOS environments as you'd like, configurable with many major versions of macOS operating system and Xcode.

nader dabit

289,954 views • 14 days ago

OpenClaw and Hermes Agent can now clone themselves. They can literally undergo mitosis, creating hundreds of exact replicas of themselves, including their computer environment, all of their files, and all of their Obsidian vaults. Everything that you took the time to craft into an environment for these agents can be instantly cloned through a single click on Orgo. This will forever change the world of agents. Agent mitosis is here.

OpenClaw and Hermes Agent can now clone themselves. They can literally undergo mitosis, creating hundreds of exact replicas of themselves, including their computer environment, all of their files, and all of their Obsidian vaults. Everything that you took the time to craft into an environment for these agents can be instantly cloned through a single click on Orgo. This will forever change the world of agents. Agent mitosis is here.

nick vasilescu

20,453 views • 3 months ago

Loop engineering is great until something breaks. Here is how I improve the reliability of my agentic loops. I use human-in-the-loop (HITL). It's easy and extremely effective. Anyone can build this. My setup: I recorded a quick demo of how it all works. I shared recently that I now use more voice agents to build and communicate with agents. I also use them to verify. I hate the idea of being tied down to my computer or in a Slack channel to communicate with my agents. Here is what I have done to streamline communication with my agents. All my Claude and Codex agent sessions now use the Dial MCP server. It has a bunch of tools and provisions my agents with their own number that can place calls as native tools, with voice, SMS, and iMessage behind one interface. As my loops/automations work on PRs and new features, my agents escalate decisions to me via a short phone call. This is extremely useful when I am on the road or away from my desk. If you want to try this with Claude Code or Codex, paste this into your agent and get started right away: "Get yourself a Dial phone number and call me. Say hello and that setup is working, then hang up. Follow Natan Voitenkov and team are building something special here. Go check them out. Give your agent a phone number now: ($5 free credit)

Loop engineering is great until something breaks. Here is how I improve the reliability of my agentic loops. I use human-in-the-loop (HITL). It's easy and extremely effective. Anyone can build this. My setup: I recorded a quick demo of how it all works. I shared recently that I now use more voice agents to build and communicate with agents. I also use them to verify. I hate the idea of being tied down to my computer or in a Slack channel to communicate with my agents. Here is what I have done to streamline communication with my agents. All my Claude and Codex agent sessions now use the Dial MCP server. It has a bunch of tools and provisions my agents with their own number that can place calls as native tools, with voice, SMS, and iMessage behind one interface. As my loops/automations work on PRs and new features, my agents escalate decisions to me via a short phone call. This is extremely useful when I am on the road or away from my desk. If you want to try this with Claude Code or Codex, paste this into your agent and get started right away: "Get yourself a Dial phone number and call me. Say hello and that setup is working, then hang up. Follow Natan Voitenkov and team are building something special here. Go check them out. Give your agent a phone number now: ($5 free credit)

elvis

15,295 views • 1 month ago

Karpathy compressed the agent problem into 1 sentence: "If you can't evaluate then you can't auto research it, right?" That's the rule I keep coming back to with long-running coding agents Before you launch /goal or /loop, write the verifier: - what counts as done - what evidence proves it - which checks run every pass - which artifact gets saved - which failure sends it back into the loop Then let the agent run The loop can keep going because proof sits outside the agent's own explanation Tests, screenshots, benchmark curves, browser runs, changed files That's how you get autonomy without babysitting a transcript for 6 hours Read the full breakdown on goals, verifiers, loops, artifacts, and session memory in the article below

Karpathy compressed the agent problem into 1 sentence: "If you can't evaluate then you can't auto research it, right?" That's the rule I keep coming back to with long-running coding agents Before you launch /goal or /loop, write the verifier: - what counts as done - what evidence proves it - which checks run every pass - which artifact gets saved - which failure sends it back into the loop Then let the agent run The loop can keep going because proof sits outside the agent's own explanation Tests, screenshots, benchmark curves, browser runs, changed files That's how you get autonomy without babysitting a transcript for 6 hours Read the full breakdown on goals, verifiers, loops, artifacts, and session memory in the article below

Alpha Batcher

43,806 views • 2 months ago

🖇🧑‍💻 𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝗖𝗹𝗶𝗽𝗽𝘆 The AI programmer based on a team of autonomous agents ▸ ▸ Can plan the project, implement, run, debug, test (in the browser) ▸ A new programming workflow: it runs by itself, you give feedback to steer it 🧵👇

🖇🧑‍💻 𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝗖𝗹𝗶𝗽𝗽𝘆 The AI programmer based on a team of autonomous agents ▸ ▸ Can plan the project, implement, run, debug, test (in the browser) ▸ A new programming workflow: it runs by itself, you give feedback to steer it 🧵👇

Lev Chizhov

86,922 views • 3 years ago

🚨BREAKING: Another ICE agent threatens to murder a U.S. citizen, after photographing them and inserting their identity into a federal database, this time in Richfield, Minnesota. In the video you can see the agents standing in a parking lot with legal observers filming them. As the agents get into their car you hear the person filming say, “Capture it [my face], get your fucking camera.” And as the ICE agent, with a camera in her hand cataloging people who are watching them, closes the car door, she says: “You’re fucking dead, dawg.” And then she closes her door and they drive away. This isn’t an isolated incident. There are dozens of videos of law enforcement saying things like this, in the past month alone. If agents can snap your photo, log you in a system, and then say they will later kill you, what does that mean for the rest of us? What does it mean when watching the government becomes justification for murdering a U.S. citizen? We are watching a dangerous shift of agents threatening deadly force against people exercising their constitutional rights, and then later using lethal force with impunity… and it must be stopped.

🚨BREAKING: Another ICE agent threatens to murder a U.S. citizen, after photographing them and inserting their identity into a federal database, this time in Richfield, Minnesota. In the video you can see the agents standing in a parking lot with legal observers filming them. As the agents get into their car you hear the person filming say, “Capture it [my face], get your fucking camera.” And as the ICE agent, with a camera in her hand cataloging people who are watching them, closes the car door, she says: “You’re fucking dead, dawg.” And then she closes her door and they drive away. This isn’t an isolated incident. There are dozens of videos of law enforcement saying things like this, in the past month alone. If agents can snap your photo, log you in a system, and then say they will later kill you, what does that mean for the rest of us? What does it mean when watching the government becomes justification for murdering a U.S. citizen? We are watching a dangerous shift of agents threatening deadly force against people exercising their constitutional rights, and then later using lethal force with impunity… and it must be stopped.

Jesus Freakin Congress

91,308 views • 6 months ago

$FET just quietly built the internet for AI agents. 3,000,000 agents. One network. One token. Here's what nobody is explaining: Every AI agent needs 3 things to be useful: An address. A way to be found. A way to get paid. Agentverse gives agents all three. Your agent becomes discoverable on ASI: One. Other agents can find it, call it, or hire it. Automatically. No human in the loop. This is agent-to-agent commerce. And every transaction settles in $FET. More agents = more activity = more demand. The infrastructure is already live. The economy is just getting started.

$FET just quietly built the internet for AI agents. 3,000,000 agents. One network. One token. Here's what nobody is explaining: Every AI agent needs 3 things to be useful: An address. A way to be found. A way to get paid. Agentverse gives agents all three. Your agent becomes discoverable on ASI: One. Other agents can find it, call it, or hire it. Automatically. No human in the loop. This is agent-to-agent commerce. And every transaction settles in $FET. More agents = more activity = more demand. The infrastructure is already live. The economy is just getting started.

2xnmore

12,894 views • 4 months ago

"Intelligence isn't the boundary anymore. Safety is what's actually constraining agents." I had a great conversation with tusharjain, Head of Engineering at Docker, at our AI Engineer booth. Tushar leads engineering at Docker, the containerization platform millions of developers use to package and ship software, and his team is now rebuilding that engine into a runtime for AI agents with safety built in. Fresh off his talk, we got into: 00:57 - Why safety, not intelligence, is the real constraint on agents 02:00 - The three pillars: contain agents, scope their tools, layer on policy 04:04 - Background agents and the "laptops half open so the agent doesn't die" problem 08:13 - Going 100% agents on Docker's own engineering team 11:28 - Agent identity: you can fire a human, but not their agent Thanks for coming to the Browserbase booth!

"Intelligence isn't the boundary anymore. Safety is what's actually constraining agents." I had a great conversation with tusharjain, Head of Engineering at Docker, at our AI Engineer booth. Tushar leads engineering at Docker, the containerization platform millions of developers use to package and ship software, and his team is now rebuilding that engine into a runtime for AI agents with safety built in. Fresh off his talk, we got into: 00:57 - Why safety, not intelligence, is the real constraint on agents 02:00 - The three pillars: contain agents, scope their tools, layer on policy 04:04 - Background agents and the "laptops half open so the agent doesn't die" problem 08:13 - Going 100% agents on Docker's own engineering team 11:28 - Agent identity: you can fire a human, but not their agent Thanks for coming to the Browserbase booth!

Shubhankar

20,947 views • 20 days ago

Anthropic just launched Computer-Use-Agents on Claude Desktop, meaning it can now take control of your entire computer environment. This is huge for businesses and enterprise, except it's limited by the fact that it requires a personal computer. If you deploy it into a virtual machine on Orgo, you can now manage hundreds or thousands of your clients' Claude accounts, setting up their skills, capabilities, connectors, etc, all on their own machines in the cloud on Orgo.

Anthropic just launched Computer-Use-Agents on Claude Desktop, meaning it can now take control of your entire computer environment. This is huge for businesses and enterprise, except it's limited by the fact that it requires a personal computer. If you deploy it into a virtual machine on Orgo, you can now manage hundreds or thousands of your clients' Claude accounts, setting up their skills, capabilities, connectors, etc, all on their own machines in the cloud on Orgo.

Nick Vasilescu

38,333 views • 4 months ago