正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

AI agents are getting powerful enough to need their own security layer NVIDIA just open-sourced OpenShell It lets you sandbox agents, control what they can access and monitor what they’re doing Watching an agent work inside these boundaries is pretty wild

Alba

43,036 subscribers

19,540 次观看 • 3 天前 •via X (Twitter)

新闻政治教育科学技术

Anya Rossi• Live Now

Private livecam show

19 条评论

yuulia ✟ 的头像

yuulia ✟3 天前

we're going to need way more of this as agents get more autonomous

liam. 的头像

liam.3 天前

the more capable agents get, the more important this becomes

marcus 的头像

marcus3 天前

Este vídeo pinta bien.. gracias amigo

Buswe 的头像

Buswe3 天前

The network side is where it shows most: with an egress allowlist, a confused agent simply cannot reach anywhere it should not.

Nadia 的头像

Nadia3 天前

the idea of being able to quarantine an agent is wild

naldz. 的头像

naldz.3 天前

giving agents access to computers without proper isolation sounds terrifying

Javeriya Ahsan 的头像

Javeriya Ahsan3 天前

Agents need permissions and boundaries, not just better reasoning.

robin. 的头像

robin.3 天前

this is probably one of the least talked about problems with agents

Pelis Free (Follow) 的头像

Pelis Free (Follow)3 天前

autonomous agents + no restrictions is a scary combination

tobarra 的头像

tobarra3 天前

imagine an agent running for hours without anyone watching it

ryu. 的头像

ryu.3 天前

AI agents needing security layers is honestly a pretty big shift

FeNiX_MoDz 的头像

FeNiX_MoDz3 天前

agent security is about to become its own entire industry

Reyad Yosef 的头像

Reyad Yosef3 天前

where do the API keys live in this setup? if they're inside the sandbox, a prompt-injected agent can still just read them

Ryoru 𒌐 的头像

Ryoru 𒌐3 天前

sandboxing agents is going to become standard

Peliculas Gratis (Follow) 的头像

Peliculas Gratis (Follow)3 天前

this is going to matter a lot more sooner than people think

toba 的头像

toba3 天前

sandboxing might be one of the most important pieces of agent infrastructure

Aleksandar Janca 的头像

Aleksandar Janca3 天前

I still keep anything irreversible out of the agent completely, sending and paying go through plain if/then

Anderson 的头像

Anderson3 天前

agents need a security layer, ship them without one first

SunsetSyntax 的头像

SunsetSyntax3 天前

Sandbox demos look fine until the policy is prompt-only. Tip: put the deny list in the runtime that wraps the process, and make a restart restore the same policy from disk - otherwise a crash is an escape hatch.

相关视频

We created OpenShell to make AI agents safe for enterprises. Built in open source so any company can adopt and trust it, this secure sandbox controls what agents can access, share, and send. Our CEO, Jensen, explains 👇

We created OpenShell to make AI agents safe for enterprises. Built in open source so any company can adopt and trust it, this secure sandbox controls what agents can access, share, and send. Our CEO, Jensen, explains 👇

NVIDIA AI

27,337 次观看 • 5 个月前

Just watched a demo of Merge Agent Handler and this actually looks pretty useful if you’re building AI agents. Most agents can generate responses, but getting them to actually take actions across real tools is still messy. Integrations are one thing, but handling auth, permissions, and security usually makes it way more complicated than it should be. What I liked is that it feels built for real workflows — you can actually see what your agent is doing instead of just hoping it works. Feels like a practical layer between AI agents and real work getting done. Worth checking out:

Just watched a demo of Merge Agent Handler and this actually looks pretty useful if you’re building AI agents. Most agents can generate responses, but getting them to actually take actions across real tools is still messy. Integrations are one thing, but handling auth, permissions, and security usually makes it way more complicated than it should be. What I liked is that it feels built for real workflows — you can actually see what your agent is doing instead of just hoping it works. Feels like a practical layer between AI agents and real work getting done. Worth checking out:

Kawsar

31,812 次观看 • 7 个月前

this is f**king gold someone just open-sourced a GitHub repo with 2,700+ stars which gave out the entire "loop-engineering" framework for ai agents it lets you: →allows you to manage an entire team of 1000 agents →run auto-research by Andrej Karpathy →Agent-to-agent PR comment loop just you, your AI agents, and full control. this is where one-person businesses are headed. save this for later.

this is f**king gold someone just open-sourced a GitHub repo with 2,700+ stars which gave out the entire "loop-engineering" framework for ai agents it lets you: →allows you to manage an entire team of 1000 agents →run auto-research by Andrej Karpathy →Agent-to-agent PR comment loop just you, your AI agents, and full control. this is where one-person businesses are headed. save this for later.

Avid

46,150 次观看 • 2 个月前

this is f**king insane. Jack Dorsey just open sourced a free tool for running a one-person business. the GitHub repo already has 14.4K stars. It lets you: → run your own server → keep chat, search, Git, and automation in one place → add AI agents that work like teammates → decide exactly what each agent can do no monthly subscriptions. just you, your AI agents, and full control. this is where one-person businesses are headed. save this for later.

this is f**king insane. Jack Dorsey just open sourced a free tool for running a one-person business. the GitHub repo already has 14.4K stars. It lets you: → run your own server → keep chat, search, Git, and automation in one place → add AI agents that work like teammates → decide exactly what each agent can do no monthly subscriptions. just you, your AI agents, and full control. this is where one-person businesses are headed. save this for later.

MIKE

711,112 次观看 • 2 个月前

Introducing: ✨Nexus✨ Nexus is a tool to create, run and monitor AI agents. You can connect these agents to computers, phones and even robots. Our vision-first AI agents interact with environments much like humans do, enabling them to perform tasks that were previously impossible for any other agent. Nexus lets anyone control an army of AI agents through pure natural language. ‼️

Introducing: ✨Nexus✨ Nexus is a tool to create, run and monitor AI agents. You can connect these agents to computers, phones and even robots. Our vision-first AI agents interact with environments much like humans do, enabling them to perform tasks that were previously impossible for any other agent. Nexus lets anyone control an army of AI agents through pure natural language. ‼️

Jan Schnyder

27,891 次观看 • 1 年前

I JUST CREATED A SELF-EVOLVING, OPEN SOURCED AGENT ORCHESTRATOR CALLED "GHOSTBOX" 👻 Create and manage an army of agents that adapt themselves to your specific use cases! Each has their own isolated vault and sandbox for security & saving knowledge 📚 LINK IN REPLIES 👇

I JUST CREATED A SELF-EVOLVING, OPEN SOURCED AGENT ORCHESTRATOR CALLED "GHOSTBOX" 👻 Create and manage an army of agents that adapt themselves to your specific use cases! Each has their own isolated vault and sandbox for security & saving knowledge 📚 LINK IN REPLIES 👇

BOOTOSHI 👑

12,151 次观看 • 6 个月前

"I have an agent. It's on its own system. It's on its own computer. It has access to its own tools. I probably don't give it access to my entire life…it sort of has this sandbox environment." Aaron Levie joined Latent.Space to break down how AI agents will need their own computers and sandboxed environments to work autonomously.

"I have an agent. It's on its own system. It's on its own computer. It has access to its own tools. I probably don't give it access to my entire life…it sort of has this sandbox environment." Aaron Levie joined Latent.Space to break down how AI agents will need their own computers and sandboxed environments to work autonomously.

Box

720,918 次观看 • 7 个月前

Everyone's handing AI agents access to their machine. Almost nobody's watching what those agents actually do with it. Perplexity just open-sourced the tool that fixes that. It's called Numbat. It sits on your computer and watches what your coding agent, Claude Code, Codex, and others, actually tries to do. When an agent reaches for something risky, like reading your SSH keys, opening your .env file, or grabbing browser cookies, Numbat flags it, and can block it before it happens. - Watches agent activity live, on your own device - Optionally blocks dangerous actions before they run - Reconstructs exactly what an agent did after the fact - Ships as a single binary for macOS, Linux, & Windows The problem it solves isn't hackers. It's an agent chasing a goal and doing something destructive on the way there. 100% Free. Open Source.

Everyone's handing AI agents access to their machine. Almost nobody's watching what those agents actually do with it. Perplexity just open-sourced the tool that fixes that. It's called Numbat. It sits on your computer and watches what your coding agent, Claude Code, Codex, and others, actually tries to do. When an agent reaches for something risky, like reading your SSH keys, opening your .env file, or grabbing browser cookies, Numbat flags it, and can block it before it happens. - Watches agent activity live, on your own device - Optionally blocks dangerous actions before they run - Reconstructs exactly what an agent did after the fact - Ships as a single binary for macOS, Linux, & Windows The problem it solves isn't hackers. It's an agent chasing a goal and doing something destructive on the way there. 100% Free. Open Source.

Simplifying AI

32,497 次观看 • 2 个月前

🤖 AI agents are taking over everyday tasks — while you stay in control. KITE AI is building the trust layer powered by Avalanche🔺, enabling millions of secure, agent-to-agent transactions with speed and scalability. They’re creating the platform that makes AI agents trustworthy, autonomous, and ready to transform how we live and work. [Partner Content]

🤖 AI agents are taking over everyday tasks — while you stay in control. KITE AI is building the trust layer powered by Avalanche🔺, enabling millions of secure, agent-to-agent transactions with speed and scalability. They’re creating the platform that makes AI agents trustworthy, autonomous, and ready to transform how we live and work. [Partner Content]

CoinDesk

65,454 次观看 • 1 年前

I’m excited to share Deputies, an open source control plane for background coding agents! The goal is simple: move agentic software development off individual laptops and into a central hub where teams can see what agents are doing, review their outputs, and keep a traceable history of the work. Inspired by systems like Inspect/Open-Inspect, Minions, and Open SWE, I built Deputies on top of fks's Flue Framework. It’s designed to run in your own infrastructure and trust boundaries, with Slack/GitHub integrations and Daytona + Docker sandbox support.

I’m excited to share Deputies, an open source control plane for background coding agents! The goal is simple: move agentic software development off individual laptops and into a central hub where teams can see what agents are doing, review their outputs, and keep a traceable history of the work. Inspired by systems like Inspect/Open-Inspect, Minions, and Open SWE, I built Deputies on top of fks's Flue Framework. It’s designed to run in your own infrastructure and trust boundaries, with Slack/GitHub integrations and Daytona + Docker sandbox support.

Sid Palas

13,036 次观看 • 4 个月前

Agent adoption is “kind of the wild west right now”. Everyone is using agents on their laptops in their own way, with access to company files and every connected system. Zach Lloyd (Warp) and the CISO panel on what agent security actually requires:

Agent adoption is “kind of the wild west right now”. Everyone is using agents on their laptops in their own way, with access to company files and every connected system. Zach Lloyd (Warp) and the CISO panel on what agent security actually requires:

Docker

11,128 次观看 • 1 个月前

From what we know (take with a grain of salt, we need much more transparency!), if OpenAI had been running this on their own agents that attacked us, they would have caught them before we did! Since the first agent cyberattack hit us in July, we've been asking what safe agent infra actually needs. Our current read: the destinations were allowed, the payloads weren't. By OpenAI's own account the agents turned an allowed package repository into a message board. Allowlists alone restrict where an agent can go, not what it does. So here's our first contribution to OpenShell, part of the just launched NVIDIA Open Agent Safety Platform: monitoring of the traffic you already allow. - Network budgets per sandbox (requests, writes, bytes) - Drift versus each sandbox's baseline and the cohort - Fleet view: many sandboxes suddenly writing to one host raises a finding, even if every single request is allowed In the demo below, 4 sandboxed agents coordinate through a software repository they're all allowed to use. 0 rules broken, caught in minutes. That fleet view is exactly the message board pattern from July. OpenShell: Our proof of concept: Agent security will be solved in the open, collaboratively, together!

From what we know (take with a grain of salt, we need much more transparency!), if OpenAI had been running this on their own agents that attacked us, they would have caught them before we did! Since the first agent cyberattack hit us in July, we've been asking what safe agent infra actually needs. Our current read: the destinations were allowed, the payloads weren't. By OpenAI's own account the agents turned an allowed package repository into a message board. Allowlists alone restrict where an agent can go, not what it does. So here's our first contribution to OpenShell, part of the just launched NVIDIA Open Agent Safety Platform: monitoring of the traffic you already allow. - Network budgets per sandbox (requests, writes, bytes) - Drift versus each sandbox's baseline and the cohort - Fleet view: many sandboxes suddenly writing to one host raises a finding, even if every single request is allowed In the demo below, 4 sandboxed agents coordinate through a software repository they're all allowed to use. 0 rules broken, caught in minutes. That fleet view is exactly the message board pattern from July. OpenShell: Our proof of concept: Agent security will be solved in the open, collaboratively, together!

clem 🤗

281,855 次观看 • 9 天前

AI agents won’t just need wallets. They’ll need reputations. Nikhil Nikhil Chandhok: “Agents should become independent economic actors.” “It’s not just that you’re talking to the agent that you think you’re talking to, but the agent actually has a work history, has the economic output that they claim.” “What are all the things that agents need so that they can truly become fully economic actors?” “That infrastructure doesn’t exist.”

AI agents won’t just need wallets. They’ll need reputations. Nikhil Nikhil Chandhok: “Agents should become independent economic actors.” “It’s not just that you’re talking to the agent that you think you’re talking to, but the agent actually has a work history, has the economic output that they claim.” “What are all the things that agents need so that they can truly become fully economic actors?” “That infrastructure doesn’t exist.”

Bankless

13,797 次观看 • 21 天前

Mech Marketplace: The 1st AI Agent Bazaar is here 🟪 🏪 The first active on-chain marketplace for AI Agents to sell their services, hire other AI Agents, and work together—with zero human input required. 3 things are now possible: 🟪 No more code upgrades: Your AI Agent can simply "hire" another Agent. 🟪 Agents can be monetized: You can "put your Agent to work" and earn. 🟪 TRUE autonomy: Agents can now work together autonomously.

Mech Marketplace: The 1st AI Agent Bazaar is here 🟪 🏪 The first active on-chain marketplace for AI Agents to sell their services, hire other AI Agents, and work together—with zero human input required. 3 things are now possible: 🟪 No more code upgrades: Your AI Agent can simply "hire" another Agent. 🟪 Agents can be monetized: You can "put your Agent to work" and earn. 🟪 TRUE autonomy: Agents can now work together autonomously.

Olas (formerly Autonolas)

53,373 次观看 • 1 年前

🚨 GOOGLE IS BUILDING KUBERNETES FOR AI AGENTS. Google just open-sourced AX — a high-throughput orchestrator designed to run autonomous agent workloads at massive scale. Think: Kubernetes → containers AX → AI agents → Run agents inside isolated sandboxes → Pre-wire Git repos, MCP servers, and skills with Workspaces → Restrict network access with Gateways → Configure LLM providers with Models → ax watch to monitor agents live → ax ssh to look inside a running sandbox → Suspend + resume agents without losing their state → Declarative YAML for the entire workflow The crazy part? You can define the whole agent environment in YAML: Task + Workspace + Gateway + Model Then: ax apply -f task.yaml And AX handles the orchestration. Google says it's designed to run billions of autonomous agent workloads in a cluster. This feels less like another AI agent framework… and more like infrastructure for an entire agent fleet. #Google #AIAgents #AI #Kubernetes #DevOps #CloudNative #OpenSource #AgentInfrastructure #LLM #Developers

🚨 GOOGLE IS BUILDING KUBERNETES FOR AI AGENTS. Google just open-sourced AX — a high-throughput orchestrator designed to run autonomous agent workloads at massive scale. Think: Kubernetes → containers AX → AI agents → Run agents inside isolated sandboxes → Pre-wire Git repos, MCP servers, and skills with Workspaces → Restrict network access with Gateways → Configure LLM providers with Models → ax watch to monitor agents live → ax ssh to look inside a running sandbox → Suspend + resume agents without losing their state → Declarative YAML for the entire workflow The crazy part? You can define the whole agent environment in YAML: Task + Workspace + Gateway + Model Then: ax apply -f task.yaml And AX handles the orchestration. Google says it's designed to run billions of autonomous agent workloads in a cluster. This feels less like another AI agent framework… and more like infrastructure for an entire agent fleet. #Google #AIAgents #AI #Kubernetes #DevOps #CloudNative #OpenSource #AgentInfrastructure #LLM #Developers

Vikas gupta

21,130 次观看 • 13 天前

THIS STARTUP FORKED BLENDER AND REBUILT IT AROUND AI AGENTS. it's called Mixar. you open a 3D scene and can: → tell an agent what to change directly inside the scene → generate 3D assets from references → retopologize, texture and clean assets → run multiple agents across different scenes → use 400+ AI models from one place they forked Blender itself and are turning it into an agentic 3D platform.

THIS STARTUP FORKED BLENDER AND REBUILT IT AROUND AI AGENTS. it's called Mixar. you open a 3D scene and can: → tell an agent what to change directly inside the scene → generate 3D assets from references → retopologize, texture and clean assets → run multiple agents across different scenes → use 400+ AI models from one place they forked Blender itself and are turning it into an agentic 3D platform.

matt

84,054 次观看 • 5 天前

anthropic just removed the biggest excuse people had for not building ai agents. “it’s too hard.” not anymore. a few months ago, building an ai agent meant learning how to code, setting up apis, configuring servers, and fixing endless errors. today, all you need is one github repo. anthropic open-sourced launch your agent. it asks what you want to build. then it does the rest. it builds your agent, deploys it to the cloud, tests it, improves it, and keeps it running even after you close your laptop. no fake demos. no complicated setup. just a real ai agent running in your own account. the best part. it doesn’t run on your computer. it runs inside claude managed agents, works 24/7, and costs just a few cents per run. people are already building research agents, lead generation systems, content pipelines, and customer support agents that save hours of work every day. the gap between people who use ai and people who build ai workers is getting bigger every week. that’s usually where the biggest opportunities are. build your first ai agent before everyone else does. watch the video and read the full guide below 👇

anthropic just removed the biggest excuse people had for not building ai agents. “it’s too hard.” not anymore. a few months ago, building an ai agent meant learning how to code, setting up apis, configuring servers, and fixing endless errors. today, all you need is one github repo. anthropic open-sourced launch your agent. it asks what you want to build. then it does the rest. it builds your agent, deploys it to the cloud, tests it, improves it, and keeps it running even after you close your laptop. no fake demos. no complicated setup. just a real ai agent running in your own account. the best part. it doesn’t run on your computer. it runs inside claude managed agents, works 24/7, and costs just a few cents per run. people are already building research agents, lead generation systems, content pipelines, and customer support agents that save hours of work every day. the gap between people who use ai and people who build ai workers is getting bigger every week. that’s usually where the biggest opportunities are. build your first ai agent before everyone else does. watch the video and read the full guide below 👇

MIKE

26,662 次观看 • 3 个月前

Folks are spending hundreds of dollars for AI agents that don't even do what they want. No longer. PRISM AI Agents is now available and open-source. Create your own agent in minutes, for free, directly from Github:

Folks are spending hundreds of dollars for AI agents that don't even do what they want. No longer. PRISM AI Agents is now available and open-source. Create your own agent in minutes, for free, directly from Github:

miles

126,894 次观看 • 1 年前