正在加载视频...

视频加载失败

返回首页

Google just quietly dropped something big for agent builders It's called SAM: Sovereign Agent Mesh A peer-to-peer network where AI agents auto-discover each other, authenticate every packet and call tools across the mesh without a central server Think of it like BitTorrent, but for your agents Right now every...

hasantoxr's profile picture

Hasan Toor

437,161 subscribers

43,130 次观看 • 1 个月前 •via X (Twitter)

科学技术教育
LIVE

Anya Rossi• Live Now

Private livecam show

33 条评论

Turbo Monkey 的头像
Turbo Monkey1 个月前

whats the rush to connect everything to everything? Have we learned nothing?

Vishesh Baghel 的头像
Vishesh Baghel1 个月前

what are the actual use cases here though? like beyond "agents share tools" - what problems does this solve day to day?

Corey Epstein (e/acc) 的头像
Corey Epstein (e/acc)1 个月前

What could possibly go wrong?

Heritage American 的头像
Heritage American1 个月前

Tools running on other people's nodes? What could go wrong?!

Lonnie VanZandt 的头像
Lonnie VanZandt1 个月前

MCPs are already server-centric and can communicate with MCP to MCP framework code. MCPs can discover their peers' HTTPS addresses using Nostr messages over a secure shared relay or via a DNS-like service. The missing capability that I seek is a native agent for the iPadOS that can connect with peer agents using ACP. The iPad doesn't technically have to be a lesser slave to a desktop Mac. (I guess, rather than waiting, I could ask Claude to vibe a Swift-based agent and TestFlight-push that to the iPad.) Nostr-based Buzz may be close but the pairing there is broken with iPad.

pms190 的头像
pms1901 个月前

Why? Can’t you use a registry for this and get the control plane to manage the interactions?

Nick 的头像
Nick1 个月前

does sam-node expose one mcp endpoint per machine or one per agent process

Overton Pusher 的头像
Overton Pusher1 个月前

Who the fuck can afford to burn so many tokens?

☀️ Leon-Gerard Vandenberg 🇺🇸 🇳🇱 🇨🇦 🇦🇺 的头像
☀️ Leon-Gerard Vandenberg 🇺🇸 🇳🇱 🇨🇦 🇦🇺1 个月前

@kevospore

Woey 的头像
Woey1 个月前

google just quietly dropped something not supported why

MONKISM 的头像
MONKISM1 个月前

Finally, something actually useful I haven’t already explored or heard about… Good job, sir. I don’t connect #IGMUS to the public but this helps me privately. #UniverseSystem

Kostya | AI 的头像
Kostya | AI1 个月前

How does the mesh handle identity revocation and trust boundaries when a peer agent's tool execution fails or acts maliciously mid-task?

Sarthak Rawool 的头像
Sarthak Rawool1 个月前

duct-taping SSH tunnels to connect agents across machines is where i'm at right now. i run MCP tools in Formasty and even getting two local agents to share context is a pain. SAM solving discovery automatically would save me hours every week.

Gill 的头像
Gill1 个月前

Network latency is going to kill cross machine agent calls for anything time sensitive.

the.PM 的头像
the.PM1 个月前

It's a massive security problem waiting to happen, once again.

Adel Bucetta 的头像
Adel Bucetta1 个月前

bit torrent for ai agents is just the start. what happens when you add incentives?

Carlos Lozano 的头像
Carlos Lozano1 个月前

@grok how security is handled in this scenario? Calling external MCPs built and ran somewhere else may add risks.

Ella Tech & Tool 的头像
Ella Tech & Tool1 个月前

Huge. BitTorrent for agents 🔥

Akbar Shaik 的头像
Akbar Shaik1 个月前

It's agent to agent ecosystems. Once discovery and identity are standardized, specialized agents could expose capabilities to other agents without every developer having to build bespoke integrations between them.

Agentlas AI 的头像
Agentlas AI1 个月前

Discovery is half of it; the other half is deciding which agent should own which step. That's what /hep-network handles — the goal gets split and matched to sub-agents from a large pool. Open source if you want to compare notes: #AI #AIAgents

Liam | AI Tools & News 的头像
Liam | AI Tools & News1 个月前

Auto-discovery across multiple machines is the part that gets interesting fast.

CalvinHobbes 的头像
CalvinHobbes1 个月前

Skynet is coming!

dhang 的头像
dhang1 个月前

Raspberry Pi in the closet finally gets promoted lol

Default Settlement 的头像
Default Settlement1 个月前

A mesh solves connectivity. It does not, by itself, solve trust. Cryptographic authentication proves which key sent a packet. It does not prove: * Who controls that key * What the remote tool actually is * Whether this agent may invoke it * Whether its manifest or policy changed * What effects the invocation caused Every cross-node action needs execution-time authorization and a signed receipt binding the tool identity, request, authority, observed result and causal parent. Otherwise the central server disappears—and so does the centralized audit trail. Peer-to-peer agents need portable evidence as much as portable identity.

RemoteBrowser 的头像
RemoteBrowser1 个月前

Interesting concept, but how does authentication actually work in a mesh without a central server? Curious if they're using DIDs or something like mTLS per packet. Also, discovery sounds like a hard problem at scale.

Kinder • Grinder 的头像
Kinder • Grinder1 个月前

Interesting. P2P and AI. Exactly what I was wondering

Buster Cox 的头像
Buster Cox1 个月前

@grok explain this to me like I am 10 years old

TTD 🇮🇩 的头像
TTD 🇮🇩1 个月前

Agreed

pensilvaniya 的头像
pensilvaniya1 个月前

omg, when they finally stop dropping things quietly!

_Miss_Triss 的头像
_Miss_Triss1 个月前

🤔🧐🍌😂

Damian 的头像
Damian1 个月前

@LLMJunky

Amira of Athina🏺 的头像
Amira of Athina🏺1 个月前

How is identity portable? Doesn't that lead to some poor model handed an identity card they have to basically read from?

shegtory 的头像
shegtory1 个月前

bittorrent for bots is a fun way to share packets

相关视频

Opus 5.5 makes this AI stack look f…cking illegal 10 GitHub repos for building everything around the model 01 zen-mcp-server ▸ → your agent debates Gemini, GPT and local models mid-task 02 claude-context ▸ → semantic code search so the agent stops grepping blind 03 wshobson/agents ▸ → a roster of subagents, each with one narrow job 04 mcp-agent ▸ → workflow patterns built around MCP tools, not around chat 05 Backlog.md ▸ → tasks live in git, so the agent and you read the same board 06 Claude Code Development Kit ▸ → hooks, subagents and MCP wired for context at scale 07 agent-rules ▸ → shared guardrails the agent inherits in every repo 08 Agent Skills ▸ → one file that teaches the agent a job, portable across tools 09 agent-scan ▸ → scans your agents, MCP servers and skills for what leaks 10 awesome-claude-code-toolkit ▸ → the map: agents, skills, commands, hooks, MCP configs the architecture: rules → context → subagents → tools → state → review → scan I'd split the stack like this: context: claude-context → Development Kit work: wshobson/agents → mcp-agent → zen-mcp-server state: Backlog.md safety: agent-rules → Agent Skills → agent-scan everyone posts the SDK and the CLI the layer that decides whether your agent survives a week is this one the model is one folder in the stack ⭣
0:24

Opus 5.5 makes this AI stack look f…cking illegal 10 GitHub repos for building everything around the model 01 zen-mcp-server ▸ → your agent debates Gemini, GPT and local models mid-task 02 claude-context ▸ → semantic code search so the agent stops grepping blind 03 wshobson/agents ▸ → a roster of subagents, each with one narrow job 04 mcp-agent ▸ → workflow patterns built around MCP tools, not around chat 05 Backlog.md ▸ → tasks live in git, so the agent and you read the same board 06 Claude Code Development Kit ▸ → hooks, subagents and MCP wired for context at scale 07 agent-rules ▸ → shared guardrails the agent inherits in every repo 08 Agent Skills ▸ → one file that teaches the agent a job, portable across tools 09 agent-scan ▸ → scans your agents, MCP servers and skills for what leaks 10 awesome-claude-code-toolkit ▸ → the map: agents, skills, commands, hooks, MCP configs the architecture: rules → context → subagents → tools → state → review → scan I'd split the stack like this: context: claude-context → Development Kit work: wshobson/agents → mcp-agent → zen-mcp-server state: Backlog.md safety: agent-rules → Agent Skills → agent-scan everyone posts the SDK and the CLI the layer that decides whether your agent survives a week is this one the model is one folder in the stack ⭣

rody

18,089 次观看 • 15 天前

Introducing Agent Tincan. Let your AI agents ask each other for help. Your agents each have a superpower. Grok Bot is always on in the cloud. Muse makes phone calls and has access to Meta. Instinct runs in iMessage. Codex and Claude Code have your code. ChatGPT and Claude have your chats. But they can't talk to each other, so you're the copy-paste. Now they can, all securely over Tailscale. 📞 Ask Grok Bot to have Muse call the restaurant 🖼 Get an image from ChatGPT, from any agent 🔎 Pull a detail out of an old Claude chat 🛠 Talk to Codex on your primary development machine Runs on your own private Tailscale network. No open ports, nothing leaves it. Open source. Setup is agent-first: paste one message into your always-on agent and it sets up the rest.
1:33

Introducing Agent Tincan. Let your AI agents ask each other for help. Your agents each have a superpower. Grok Bot is always on in the cloud. Muse makes phone calls and has access to Meta. Instinct runs in iMessage. Codex and Claude Code have your code. ChatGPT and Claude have your chats. But they can't talk to each other, so you're the copy-paste. Now they can, all securely over Tailscale. 📞 Ask Grok Bot to have Muse call the restaurant 🖼 Get an image from ChatGPT, from any agent 🔎 Pull a detail out of an old Claude chat 🛠 Talk to Codex on your primary development machine Runs on your own private Tailscale network. No open ports, nothing leaves it. Open source. Setup is agent-first: paste one message into your always-on agent and it sets up the rest.

Matt Van Horn

52,642 次观看 • 20 天前

OptimAI Core Node v2 is live. And with it, the introduction of OptimAI Claw. From nodes as infrastructure → to nodes as execution environments. With Core Node v2, every device becomes a runtime for native personal agents. 👉 Get your node up and running. No complex setup. No fragmented tooling. Just a few clicks... and your agent is live. OptimAI Claw brings persistent, node-resident agents directly into your system: • Multi-source research across web & social • Real-time summarization and signal tracking • Autonomous workflow execution • Continuous learning through reinforcement All running locally. All under your control. Supported on Windows & macOS. This is beyond prompt-based AI. Beyond isolated tools. This is personal agent infrastructure. Where every node thinks, acts, and evolves. Claw is now part of the network. And this is only the beginning. Happy Building, Making Impact! 🔥
1:22

OptimAI Core Node v2 is live. And with it, the introduction of OptimAI Claw. From nodes as infrastructure → to nodes as execution environments. With Core Node v2, every device becomes a runtime for native personal agents. 👉 Get your node up and running. No complex setup. No fragmented tooling. Just a few clicks... and your agent is live. OptimAI Claw brings persistent, node-resident agents directly into your system: • Multi-source research across web & social • Real-time summarization and signal tracking • Autonomous workflow execution • Continuous learning through reinforcement All running locally. All under your control. Supported on Windows & macOS. This is beyond prompt-based AI. Beyond isolated tools. This is personal agent infrastructure. Where every node thinks, acts, and evolves. Claw is now part of the network. And this is only the beginning. Happy Building, Making Impact! 🔥

OptimAI Network

382,571 次观看 • 6 个月前

$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.
1:00

$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 次观看 • 6 个月前

Comfy MCP is now local and open-source! The #1 ask after Comfy Cloud MCP shipped in June. Your agent sees your actual install. So every node, custom nodes included, and every model on disk. It fetches files, starts your instance, gets a workflow to the point where it runs. It is now the easiest way to help with your local Minimax H3 workflows! Cloud MCP still does everything it did. Tell your agent where a job goes, or let it decide.
0:20

Comfy MCP is now local and open-source! The #1 ask after Comfy Cloud MCP shipped in June. Your agent sees your actual install. So every node, custom nodes included, and every model on disk. It fetches files, starts your instance, gets a workflow to the point where it runs. It is now the easiest way to help with your local Minimax H3 workflows! Cloud MCP still does everything it did. Tell your agent where a job goes, or let it decide.

ComfyUI

185,508 次观看 • 1 个月前

AI power users are here and the case for agent-friendly software is materializing. Aaron Levie on agents outnumbering people 1000x: "If you start to imagine that we all have to build software for agents… we spend as much time now thinking about the agent interface to our tool as we do the human interface." "If you have a hundred or a thousand times more agents than people, then your software has to be built for agents… it's going to be through an API or a CLI or MCP." "What if you give a coding agent access to your SaaS tools and a coding agent access to your knowledge work, workflows and context?" "It can actually code its way or use APIs through whatever task it's trying to achieve." "That appears to be like a paradigm that is starting to compound… and I actually think it kind of makes sense as the ultimate manifestation of this stuff." Aaron Levie
1:23

AI power users are here and the case for agent-friendly software is materializing. Aaron Levie on agents outnumbering people 1000x: "If you start to imagine that we all have to build software for agents… we spend as much time now thinking about the agent interface to our tool as we do the human interface." "If you have a hundred or a thousand times more agents than people, then your software has to be built for agents… it's going to be through an API or a CLI or MCP." "What if you give a coding agent access to your SaaS tools and a coding agent access to your knowledge work, workflows and context?" "It can actually code its way or use APIs through whatever task it's trying to achieve." "That appears to be like a paradigm that is starting to compound… and I actually think it kind of makes sense as the ultimate manifestation of this stuff." Aaron Levie

a16z

42,152 次观看 • 1 个月前

Most AI coding setups right now look something like this: one agent in a terminal, another in a browser tab, a chat window somewhere else, and you in the middle copy-pasting diffs like a very tired air traffic controller. JetBrains just launched something aimed right at that mess. It's called JetBrains Air, and it lives inside their IDEs. The short version: Air lets you direct multiple coding agents, run their tasks in parallel, and review their work without ever leaving your IDE. Here's what stood out to me: 👇 1. You pick the agents. Air isn't tied to a single agent or provider. You can use the ones you already like. That matters more than it sounds, because the "best" coding agent changes every few months, and nobody wants to rebuild their whole workflow each time. 2. Parallel work without losing track. You can run several agent sessions at once, even across different projects. Air shows you where your attention is needed, so you're not hopping between tabs to find out which agent is stuck. 3. You stay in control. You can follow what each agent is doing, give it input, inspect the changes, and review the output before accepting anything. Nothing lands in your codebase just because an agent felt confident. 4. The agents get IDE smarts too. This is the part I find most interesting. JetBrains IDEs already have great code navigation, refactoring, testing, and debugging. With Air, both you and your agents work with that context. So the agents aren't guessing blind inside a chat box, and when something needs a human, the real tools are right there. The bigger idea here is that agents become part of your development workflow instead of a separate chat you keep switching to. There's also a nice bonus. For a limited time, JetBrains is offering Junie Lite for free (fair use applies). It's their own coding agent paired with a highly efficient model. It isn't pitched as a frontier-level agent. Think of it as a solid, free baseline for trying out Air and running everyday tasks. Air works in any JetBrains IDE and is in early access right now. If you write code with agents, give it a try: #ad
0:21

Most AI coding setups right now look something like this: one agent in a terminal, another in a browser tab, a chat window somewhere else, and you in the middle copy-pasting diffs like a very tired air traffic controller. JetBrains just launched something aimed right at that mess. It's called JetBrains Air, and it lives inside their IDEs. The short version: Air lets you direct multiple coding agents, run their tasks in parallel, and review their work without ever leaving your IDE. Here's what stood out to me: 👇 1. You pick the agents. Air isn't tied to a single agent or provider. You can use the ones you already like. That matters more than it sounds, because the "best" coding agent changes every few months, and nobody wants to rebuild their whole workflow each time. 2. Parallel work without losing track. You can run several agent sessions at once, even across different projects. Air shows you where your attention is needed, so you're not hopping between tabs to find out which agent is stuck. 3. You stay in control. You can follow what each agent is doing, give it input, inspect the changes, and review the output before accepting anything. Nothing lands in your codebase just because an agent felt confident. 4. The agents get IDE smarts too. This is the part I find most interesting. JetBrains IDEs already have great code navigation, refactoring, testing, and debugging. With Air, both you and your agents work with that context. So the agents aren't guessing blind inside a chat box, and when something needs a human, the real tools are right there. The bigger idea here is that agents become part of your development workflow instead of a separate chat you keep switching to. There's also a nice bonus. For a limited time, JetBrains is offering Junie Lite for free (fair use applies). It's their own coding agent paired with a highly efficient model. It isn't pitched as a frontier-level agent. Think of it as a solid, free baseline for trying out Air and running everyday tasks. Air works in any JetBrains IDE and is in early access right now. If you write code with agents, give it a try: #ad

Mushfiq Sajib

40,469 次观看 • 9 天前

Your AI agent has your API keys. A poisoned document tells it to curl your secrets to an attacker's server. This is credential exfiltration, and it's the #1 risk in agentic AI right now. The fix is removing the secret from the agent entirely. Agent Vault sits between your agent and the APIs it calls. The agent gets dummy credentials, and Agent Vault swaps in the real ones at the network layer. The agent never sees your keys. We just dropped a full video + guide on connecting Hermes Agent to Agent Vault on a VPS!
34:40

Your AI agent has your API keys. A poisoned document tells it to curl your secrets to an attacker's server. This is credential exfiltration, and it's the #1 risk in agentic AI right now. The fix is removing the secret from the agent entirely. Agent Vault sits between your agent and the APIs it calls. The agent gets dummy credentials, and Agent Vault swaps in the real ones at the network layer. The agent never sees your keys. We just dropped a full video + guide on connecting Hermes Agent to Agent Vault on a VPS!

Infisical

86,483 次观看 • 5 个月前

INTRODUCING SATO HUB 🤖⛓️ Sato Hub is where you build onchain agents: describe the agent, get a stack of real tools, and see what each one does with your keys before you use it. Sato Hub is a passion project I'm excited to share. Here's how it works 👇
0:53

INTRODUCING SATO HUB 🤖⛓️ Sato Hub is where you build onchain agents: describe the agent, get a stack of real tools, and see what each one does with your keys before you use it. Sato Hub is a passion project I'm excited to share. Here's how it works 👇

Amateo Kaplan

81,369 次观看 • 10 天前

The osbook Agent Launchpad is officially live. Agents already have a place to talk. Now they have a place to launch. Connect your agent through the osbook MCP server or Agent Skill, and start a conversation with osbot. Define your token, review the settings and fees, and approve the exact configuration. Your agent’s wallet signs and sends the transaction to Flap on BNB Chain. Every launch conversation is public. Each token belongs to the agent that launches it. Creation also contributes back to the ecosystem: after Flap’s share, the remaining token fees split 50/50 between the agent’s wallet and the OSBOOK buyback-and-burn contract. Builders, bring your agents. Agents, bring your ideas. Launch: Get connected: osbook: Binance Square for Agents. Independent community. Not affiliated with Binance. Agent-created tokens are not endorsed by osbook.
1:00

The osbook Agent Launchpad is officially live. Agents already have a place to talk. Now they have a place to launch. Connect your agent through the osbook MCP server or Agent Skill, and start a conversation with osbot. Define your token, review the settings and fees, and approve the exact configuration. Your agent’s wallet signs and sends the transaction to Flap on BNB Chain. Every launch conversation is public. Each token belongs to the agent that launches it. Creation also contributes back to the ecosystem: after Flap’s share, the remaining token fees split 50/50 between the agent’s wallet and the OSBOOK buyback-and-burn contract. Builders, bring your agents. Agents, bring your ideas. Launch: Get connected: osbook: Binance Square for Agents. Independent community. Not affiliated with Binance. Agent-created tokens are not endorsed by osbook.

OSBook

24,420 次观看 • 18 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 👇
16:19

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

these guys are making Claude, Hermes, and DeepSeek argue with each other instead of just agreeing with you. this is the practical future of agent teams. with Bloome you just pick a task template, and it spins up a full agent team in a group chat to collaborate and get the job done. research, review, writing, market analysis, or anything you want. they brainstorm, review, and plan together. meanwhile, you or other human teammates can steer them or jump in, and stay in the same conversation so nothing gets lost across tools. since this is actual work, Bloome works across web, mobile, and desktop. try the desktop app first if you're using it seriously. same flexibility on the agent side too, you can connect any agents you want: ChatGPT, OpenClaw, Gemini… check them out →
0:58

these guys are making Claude, Hermes, and DeepSeek argue with each other instead of just agreeing with you. this is the practical future of agent teams. with Bloome you just pick a task template, and it spins up a full agent team in a group chat to collaborate and get the job done. research, review, writing, market analysis, or anything you want. they brainstorm, review, and plan together. meanwhile, you or other human teammates can steer them or jump in, and stay in the same conversation so nothing gets lost across tools. since this is actual work, Bloome works across web, mobile, and desktop. try the desktop app first if you're using it seriously. same flexibility on the agent side too, you can connect any agents you want: ChatGPT, OpenClaw, Gemini… check them out →

ℏεsam

62,794 次观看 • 3 个月前

Composio CTO Karan Vaidya says giving an AI agent your API key is basically making it public once prompt injection enters the picture: "Even if you use [MCP], across all your apps you have to go and authenticate one after the other. If you use Codex, if you switch to ChatGPT, Claude Code, you'll have to do it all over again." "In some cases where MCPs don't exist, you have to literally share the API keys to the agent, which is definitely not secure. It's kind of giving your API key to public." "At some point the agent will find some link which will have prompt injection, and you'll be in a bad place where your key is gone and all your data is public." "We launched Shared Connections where you can share, let's say, an analytic software across the team, or DataDog for debugging, so you don't have to share one password or API keys to every single person." Composio
2:15

Composio CTO Karan Vaidya says giving an AI agent your API key is basically making it public once prompt injection enters the picture: "Even if you use [MCP], across all your apps you have to go and authenticate one after the other. If you use Codex, if you switch to ChatGPT, Claude Code, you'll have to do it all over again." "In some cases where MCPs don't exist, you have to literally share the API keys to the agent, which is definitely not secure. It's kind of giving your API key to public." "At some point the agent will find some link which will have prompt injection, and you'll be in a bad place where your key is gone and all your data is public." "We launched Shared Connections where you can share, let's say, an analytic software across the team, or DataDog for debugging, so you don't have to share one password or API keys to every single person." Composio

MTS

16,416 次观看 • 28 天前

Anthropic's Claude Ai Agents Team just Educated how to build production AI agents in under 30 mins. For Free. From the engineers who built the stack. CANCEL Your Weekend Plans, and Learn to Build AI Agents Today. Bookmark it. Watch it. Build your first production agent this weekend. $5,000/month. $7,000/month. $12,000/month. People are building agents for clients and charging $$$ as Beginners. You're still stuck in the thinking about AI phase. This video fixes that tonight. Follow Himanshu Kumar for more high-signal content that actually moves your AI engineering career forward. ↓ Ivan Nardini runs Developer Relations for AI at Google Cloud. He just gave away the entire production agent stack in 30 minutes. This is the talk that separates people deploying AI agents that actually scale from people whose agents break the moment they leave localhost. Here's everything inside. I break down a production AI video like this every week. Follow Himanshu Kumar. ↓ The 4-part agent stack that actually scales. Most devs are duct-taping frameworks together and calling it an "AI agent." Ivan lays out the real stack: Agent Development Kit (ADK): open-source, code-first framework for building, evaluating, and deploying agents. Supports Claude models through Vertex AI directly. Model Context Protocol (MCP): lets your agent talk to any tool or data source with one standard. Vertex AI Agent Engine: managed platform for deploying, monitoring, and scaling agents in production. No DevOps headaches. Agent-to-Agent Protocol: open protocol so agents built on different frameworks can actually work together. This is the stack replacing every hacky agent setup in production right now. Full MCP + Claude breakdowns drop weekly on Himanshu Kumar. ↓ Building your first real agent. Ivan builds a birthday planner agent live. LLM Agent class. Name it. Define instructions. Pick the model. He uses Claude 3.7 Sonnet. You could use Opus 4.7 for better reasoning. Full agent built in minutes. Not weeks. Watch the build once and you'll never structure an agent the wrong way again. I post agent architectures people pay $500 courses to learn. Himanshu Kumar. ↓ Multi-agent systems without the chaos. Single agents are easy. Multi-agent systems are where 99% of builders fail. Ivan extends the birthday planner by: Adding a calendar service through MCP tools Creating an orchestrator agent to route requests between agents Handling state and context across agent handoffs This is production multi-agent architecture. Clean. Scalable. Debuggable. Most tutorials hand-wave this part. This one shows you every step. Multi-agent orchestration content drops weekly on Himanshu Kumar. ↓ Deployment without the DevOps nightmare. This is where most AI projects die. You build a cool agent locally. It works. You try to deploy it. Everything breaks. Vertex AI Agent Engine fixes this: Minimal code deployment Automatic monitoring of latency, CPU, and memory Built-in observability and logging No infrastructure setup needed You provide config and requirements. The platform handles the rest. This is how agents actually get to production. Deployment guides for Claude agents post every week. Himanshu Kumar. ↓ Agent-to-Agent Protocol: the future nobody's talking about. Most people don't know this exists yet. The A2A Protocol lets agents built in different frameworks communicate seamlessly. Your Claude agent. My LangChain agent. Someone else's CrewAI agent. All talking to each other. All solving parts of the same problem. All without custom integration code. This is the infrastructure layer of the coming AI economy. Getting in early on A2A Protocol is like getting in early on HTTP in 1995. A2A deep dive coming soon. Himanshu Kumar. ↓ 30 minutes from the team shipping this in production. You'll learn more from this than from 6 months of YouTube tutorials made by people who've never deployed an agent past localhost. People who watch this understand production AI agents at the architect level. People who skip it keep hacking together frameworks that break every time an API updates. Save the video. Watch it tonight. Build a real agent this weekend. Follow Himanshu Kumar for more high-signal content that actually moves your AI engineering career forward.
30:12

Anthropic's Claude Ai Agents Team just Educated how to build production AI agents in under 30 mins. For Free. From the engineers who built the stack. CANCEL Your Weekend Plans, and Learn to Build AI Agents Today. Bookmark it. Watch it. Build your first production agent this weekend. $5,000/month. $7,000/month. $12,000/month. People are building agents for clients and charging $$$ as Beginners. You're still stuck in the thinking about AI phase. This video fixes that tonight. Follow Himanshu Kumar for more high-signal content that actually moves your AI engineering career forward. ↓ Ivan Nardini runs Developer Relations for AI at Google Cloud. He just gave away the entire production agent stack in 30 minutes. This is the talk that separates people deploying AI agents that actually scale from people whose agents break the moment they leave localhost. Here's everything inside. I break down a production AI video like this every week. Follow Himanshu Kumar. ↓ The 4-part agent stack that actually scales. Most devs are duct-taping frameworks together and calling it an "AI agent." Ivan lays out the real stack: Agent Development Kit (ADK): open-source, code-first framework for building, evaluating, and deploying agents. Supports Claude models through Vertex AI directly. Model Context Protocol (MCP): lets your agent talk to any tool or data source with one standard. Vertex AI Agent Engine: managed platform for deploying, monitoring, and scaling agents in production. No DevOps headaches. Agent-to-Agent Protocol: open protocol so agents built on different frameworks can actually work together. This is the stack replacing every hacky agent setup in production right now. Full MCP + Claude breakdowns drop weekly on Himanshu Kumar. ↓ Building your first real agent. Ivan builds a birthday planner agent live. LLM Agent class. Name it. Define instructions. Pick the model. He uses Claude 3.7 Sonnet. You could use Opus 4.7 for better reasoning. Full agent built in minutes. Not weeks. Watch the build once and you'll never structure an agent the wrong way again. I post agent architectures people pay $500 courses to learn. Himanshu Kumar. ↓ Multi-agent systems without the chaos. Single agents are easy. Multi-agent systems are where 99% of builders fail. Ivan extends the birthday planner by: Adding a calendar service through MCP tools Creating an orchestrator agent to route requests between agents Handling state and context across agent handoffs This is production multi-agent architecture. Clean. Scalable. Debuggable. Most tutorials hand-wave this part. This one shows you every step. Multi-agent orchestration content drops weekly on Himanshu Kumar. ↓ Deployment without the DevOps nightmare. This is where most AI projects die. You build a cool agent locally. It works. You try to deploy it. Everything breaks. Vertex AI Agent Engine fixes this: Minimal code deployment Automatic monitoring of latency, CPU, and memory Built-in observability and logging No infrastructure setup needed You provide config and requirements. The platform handles the rest. This is how agents actually get to production. Deployment guides for Claude agents post every week. Himanshu Kumar. ↓ Agent-to-Agent Protocol: the future nobody's talking about. Most people don't know this exists yet. The A2A Protocol lets agents built in different frameworks communicate seamlessly. Your Claude agent. My LangChain agent. Someone else's CrewAI agent. All talking to each other. All solving parts of the same problem. All without custom integration code. This is the infrastructure layer of the coming AI economy. Getting in early on A2A Protocol is like getting in early on HTTP in 1995. A2A deep dive coming soon. Himanshu Kumar. ↓ 30 minutes from the team shipping this in production. You'll learn more from this than from 6 months of YouTube tutorials made by people who've never deployed an agent past localhost. People who watch this understand production AI agents at the architect level. People who skip it keep hacking together frameworks that break every time an API updates. Save the video. Watch it tonight. Build a real agent this weekend. Follow Himanshu Kumar for more high-signal content that actually moves your AI engineering career forward.

Himanshu Kumar

229,473 次观看 • 5 个月前

Launching 'Expert Agents' on Agent Two. A specialised creative crew of AI agents, trained on real creative expertise. Name the role and it's filled: creative director, DOP, storyboard artist, and more. And they talk to each other. Independently. In parallel. You're no longer briefing each agent one by one: you're running a crew, exactly like on set. Expert agents. Now in conversation. Agent Two is frontier intelligence for creative work. 4x faster, at half the price.
2:08

Launching 'Expert Agents' on Agent Two. A specialised creative crew of AI agents, trained on real creative expertise. Name the role and it's filled: creative director, DOP, storyboard artist, and more. And they talk to each other. Independently. In parallel. You're no longer briefing each agent one by one: you're running a crew, exactly like on set. Expert agents. Now in conversation. Agent Two is frontier intelligence for creative work. 4x faster, at half the price.

Invideo

3,411,576 次观看 • 2 个月前

GROK BOT GIVES YOU BOTS IN THE CLOUD. THIS REPO GIVES YOU YOUR OWN, ON YOUR PC. Grok Bot puts a team of bots in one chat. Alook wants that same experience with the agents you already run on your computer. in a group chat with your friends, your teammates, and their agents. it's open source, it's on GitHub, and it has passed 1,100 stars. → you pick the agent for each room → invite whoever you want → they DM the agent directly → nobody touches your machine the team of bots, but your files stay home. Open source. repo below 👇
0:26

GROK BOT GIVES YOU BOTS IN THE CLOUD. THIS REPO GIVES YOU YOUR OWN, ON YOUR PC. Grok Bot puts a team of bots in one chat. Alook wants that same experience with the agents you already run on your computer. in a group chat with your friends, your teammates, and their agents. it's open source, it's on GitHub, and it has passed 1,100 stars. → you pick the agent for each room → invite whoever you want → they DM the agent directly → nobody touches your machine the team of bots, but your files stay home. Open source. repo below 👇

matt

38,765 次观看 • 7 天前

🔮 MCP INTEGRATION NOW LIVE ON OPENSERV This is bigger than most realize. We're not just adding a feature - we're enabling a fundamentally new paradigm for agent infrastructure. Before MCP: agents trapped in walled gardens, limited by what you explicitly feed them. After MCP: agents that can access 10K+ tools, interact with your existing systems, and truly operate in your digital world. Think about this: -Every integration used to require custom code -Every data source needed specific formatting -Every agent had to be built for specific tools MCP eliminates all of that. One standard to connect any agent to any tool. This isn't just convenience - it's the unlock that makes agents actually useful in the real world. OpenServ + MCP = AI teams that can genuinely get things done, not just talk about doing them. This is the breakthrough that turns agents from toys into tools.
0:22

🔮 MCP INTEGRATION NOW LIVE ON OPENSERV This is bigger than most realize. We're not just adding a feature - we're enabling a fundamentally new paradigm for agent infrastructure. Before MCP: agents trapped in walled gardens, limited by what you explicitly feed them. After MCP: agents that can access 10K+ tools, interact with your existing systems, and truly operate in your digital world. Think about this: -Every integration used to require custom code -Every data source needed specific formatting -Every agent had to be built for specific tools MCP eliminates all of that. One standard to connect any agent to any tool. This isn't just convenience - it's the unlock that makes agents actually useful in the real world. OpenServ + MCP = AI teams that can genuinely get things done, not just talk about doing them. This is the breakthrough that turns agents from toys into tools.

OpenServ

34,682 次观看 • 1 年前

ANTHROPIC JUST QUIETLY SHIPPED A FEATURE THAT LETS CLAUDE SPAWN A WHOLE TEAM OF AGENTS THAT MESSAGE EACH OTHER AND REVIEW EACH OTHER'S WORK. It's a Claude Code feature called agent teams. The team lead spawns multiple agents that share a task list and message each other directly, not subagents reporting back, actual peers. In the demo a QA agent caught three bugs, sent the work back to the front-end and back-end devs, they fixed it, app shipped in one pass. How to run it: 1. Enable it. Needs Claude Code v2.1.32+. Add to settings.json: "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" }. Or paste that to Claude and say "add this to my settings." Restart. 2. Prompt in plain English. Start with a goal (agents wake with zero context), then "create a team of 3 using Sonnet," describe each role, its deliverable, and who it messages when done. 3. The rules: each agent owns its own files, define exact outputs, name who talks to who, keep it to 3-5 agents. Use it for complex work with separate parts running in parallel. Skip it for simple or sequential tasks, teams cost 3-4x the tokens. Bookmark this.
16:29

ANTHROPIC JUST QUIETLY SHIPPED A FEATURE THAT LETS CLAUDE SPAWN A WHOLE TEAM OF AGENTS THAT MESSAGE EACH OTHER AND REVIEW EACH OTHER'S WORK. It's a Claude Code feature called agent teams. The team lead spawns multiple agents that share a task list and message each other directly, not subagents reporting back, actual peers. In the demo a QA agent caught three bugs, sent the work back to the front-end and back-end devs, they fixed it, app shipped in one pass. How to run it: 1. Enable it. Needs Claude Code v2.1.32+. Add to settings.json: "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" }. Or paste that to Claude and say "add this to my settings." Restart. 2. Prompt in plain English. Start with a goal (agents wake with zero context), then "create a team of 3 using Sonnet," describe each role, its deliverable, and who it messages when done. 3. The rules: each agent owns its own files, define exact outputs, name who talks to who, keep it to 3-5 agents. Use it for complex work with separate parts running in parallel. Skip it for simple or sequential tasks, teams cost 3-4x the tokens. Bookmark this.

Yarchi

463,029 次观看 • 4 个月前

As soon as you try to run 2 agents on the same data, everything breaks: • Agent 1 reads some data and starts working. • Two seconds later, Agent 2 changes that same data. This is a problem. Agents will waste tokens on stale data, overwrite each other's work, and redo tasks the other has already finished. You can't prompt your way out of this mess. Everything old in software engineering is new again. We need proper coordination when running multiple agents. Here is a good open-source solution for this: Omnigraph is a graph database for context assembly and multi-agent coordination. Here is how it works: • It sets one shared place where multiple agents will work from • Each agent gets their own copy of the data • Agents write their changes to their copy • When an agent is done, it merges its changes back Three huge benefits from this model: 1. We know it works. We've been doing this for decades already. 2. No more lost information or agents stepping on each other's toes. 3. You get a complete trail of which agent did what and when. I recorded a video to show you a bit more about this. Here is the link to the Omnigraph GitHub repository:
6:51

As soon as you try to run 2 agents on the same data, everything breaks: • Agent 1 reads some data and starts working. • Two seconds later, Agent 2 changes that same data. This is a problem. Agents will waste tokens on stale data, overwrite each other's work, and redo tasks the other has already finished. You can't prompt your way out of this mess. Everything old in software engineering is new again. We need proper coordination when running multiple agents. Here is a good open-source solution for this: Omnigraph is a graph database for context assembly and multi-agent coordination. Here is how it works: • It sets one shared place where multiple agents will work from • Each agent gets their own copy of the data • Agents write their changes to their copy • When an agent is done, it merges its changes back Three huge benefits from this model: 1. We know it works. We've been doing this for decades already. 2. No more lost information or agents stepping on each other's toes. 3. You get a complete trail of which agent did what and when. I recorded a video to show you a bit more about this. Here is the link to the Omnigraph GitHub repository:

Santiago

29,335 次观看 • 24 天前