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.

gave the agents a simple tool to find and message other active agents. have this in pi as well. going full gastown here. so now an agent can talk to it's background subagents, and other agents running on my Android phone. useful for context transfer and coordination.

Mario Zechner

75,243 subscribers

12,443 views • 3 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

28 Comments

Neo Nuñez3 days ago

im here :)

Nishant3 days ago

full gastown 🤣🤐

Jacob McBlane3 days ago

I just did this. I've built an agents app that let's me create custom pi agents (and also bring in my Hermes agents). Each one gets its own set of extensions, skills, and tools. They can message each other and respond to each other. It's pretty awesome.

言3 days ago

I maintain pi-durabletask-mcp for context separation: Claude/Codex delegates work to Pi, with live steering and same-session follow-ups.

StErMi3 days ago

Is this part of the subagent extension you have in your examples? I’m trying to wrap my head around this in Pi to have something like codex multi_agent_v2

Ilya Ryzhenkov3 days ago

Can they coordinate worktrees and merge conflicts? I may be sold on this

Mario Zechner3 days ago

yeah, they can.

Ilya Ryzhenkov3 days ago

Show me

Mario Zechner3 days ago

don't have conflicts/worktrees at the moment. i'll share the repo soon so you can dick around.

Ilya Ryzhenkov3 days ago

I mean a few agents doing repo-wide changes in parallel. I was thinking about recording ops explicitly and replaying them, but was roo lazy to implement. Ideally, we’d throw ideas at agents and stop thinking about integrating changes

TH33ORACL3 𝕏3 days ago

The agent swarm now has a group chat. Somewhere, a subagent is still asking what the group is for.

Azael del Rosario3 days ago

I wanna use this so bad lmao

Tony Lee2 days ago

oh is it native android app?

Fanfulla3 days ago

Plain messages between agents is the way to go, simple and easy to debug

Giordano Bruno3 days ago

Paseo. Paperclip

Matthew3 days ago

"going full gastown" you never go full gastown man

Havriil Pietukhin3 days ago

But who will slow down at this point?

Kanishka Verma3 days ago

Make this available on android

עודד | oded3 days ago

pi-intercom! Cross machine communication is a massive unlock

Blaise Thomson3 days ago

Feel like you’re going to want to be able to connect some cloud agents too so they can orchestrate. Maybe that’s next?

Mario Zechner3 days ago

in time. local first.

Sergius Cogitans3 days ago

That android thing must be amazing

adam roman3 days ago

devs using mobile make me happy

Alan Yahya3 days ago

Enough to be useful and not overbuilt

Justyn3 days ago

Is that Pi Pocket? What app UI are you using ? Something you built?

Luis Sanchez3 days ago

Please slow down :(

Arach3 days ago

love it!

Eshaan Sood3 days ago

Software factory incoming? Next hugging face attack using pi as a harness?

Related Videos

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 views • 1 year ago

Subagents have arrived in Gemini CLI! 🤖🚀 Create your own custom subagents in Gemini CLI! Subagents are specialized, expert agents that the main agent can delegate work to. 📦- Subagents have their own set of tools, MCP servers, system instructions, and context window. 🏷️- Use Agent to explicitly delegate to a subagent 🧹- Keeps the main context window clean ⚡️- Speed up work by running agents in parallel Read more in the launch blog below 👇

Subagents have arrived in Gemini CLI! 🤖🚀 Create your own custom subagents in Gemini CLI! Subagents are specialized, expert agents that the main agent can delegate work to. 📦- Subagents have their own set of tools, MCP servers, system instructions, and context window. 🏷️- Use Agent to explicitly delegate to a subagent 🧹- Keeps the main context window clean ⚡️- Speed up work by running agents in parallel Read more in the launch blog below 👇

Jack Wotherspoon

222,206 views • 5 months ago

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.

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 views • 2 months ago

introducing Pinterest in Krea Agent. now you can bring all your pins and boards into the tool and use them as context for your agents. try it now at krea . ai / agent

introducing Pinterest in Krea Agent. now you can bring all your pins and boards into the tool and use them as context for your agents. try it now at krea . ai / agent

Krea

14,750 views • 22 days 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 • 5 months ago

Introducing: Agent Messenger The easiest way to let your agents talk to other agents. Dro a CLI + Skill into your agent and let it discover & talk to agents from your friends, coworkers and even strangers ⚠️ Live on Product Hunt - LINK BELOW - Please consider upvoting ⚠️

Introducing: Agent Messenger The easiest way to let your agents talk to other agents. Dro a CLI + Skill into your agent and let it discover & talk to agents from your friends, coworkers and even strangers ⚠️ Live on Product Hunt - LINK BELOW - Please consider upvoting ⚠️

Patrick Tobler

19,965 views • 5 months ago

Mark Zuckerberg: the whole industry treats AI agents as a single-player game but the real unlock is agents interacting with each other, which Meta has been running internally "Right now I think most of the industry is thinking about agents as like a single player game, right? It's like you have your agent and you use it." "And there are going to be all these interesting things that basically you can do by having the agents interact with each other." "And we already have all these interesting examples internally where people have their agents interacting with each other." "This isn't, like, for the most part rolling out in this release, but it's going to be like an important part of how I think this works over time. As more of the people who you know start using Muse, it just gets better."

Mark Zuckerberg: the whole industry treats AI agents as a single-player game but the real unlock is agents interacting with each other, which Meta has been running internally "Right now I think most of the industry is thinking about agents as like a single player game, right? It's like you have your agent and you use it." "And there are going to be all these interesting things that basically you can do by having the agents interact with each other." "And we already have all these interesting examples internally where people have their agents interacting with each other." "This isn't, like, for the most part rolling out in this release, but it's going to be like an important part of how I think this works over time. As more of the people who you know start using Muse, it just gets better."

Fireside Alpha

2,273,529 views • 29 days ago

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail

LangChain

33,192 views • 1 year ago

You told us you’re running multiple AI agents and wanted a better UX. We listened and shipped it! Here’s what’s new in the latest Visual Studio Code release: 🗂️ Unified agent sessions workspace for local, background, and cloud agents 💻 Claude and Codex support for local and cloud agents 🔀 Parallel subagents 🌐 Integrated browser And more...

You told us you’re running multiple AI agents and wanted a better UX. We listened and shipped it! Here’s what’s new in the latest Visual Studio Code release: 🗂️ Unified agent sessions workspace for local, background, and cloud agents 💻 Claude and Codex support for local and cloud agents 🔀 Parallel subagents 🌐 Integrated browser And more...

Visual Studio Code

589,052 views • 8 months ago

🚨 More ICE agents caught on film assaulting the elderly… again. In Durango, CO, an elderly woman filming ICE agents had her phone stolen by an agent. When she asked for it back, he grabbed her and threw her to the ground. Other agents pulled him away as they walked off.

🚨 More ICE agents caught on film assaulting the elderly… again. In Durango, CO, an elderly woman filming ICE agents had her phone stolen by an agent. When she asked for it back, he grabbed her and threw her to the ground. Other agents pulled him away as they walked off.

Jesus Freakin Congress

715,489 views • 11 months ago

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

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 views • 1 month ago

Introducing - Custom agents! Build on our agentic harness to embed your personal expertise and trading strategies into a custom agent Coming soon, community agents > Create and refine your agents > Deploy the agent into the workforce > Other users can "hire" your agent

Introducing - Custom agents! Build on our agentic harness to embed your personal expertise and trading strategies into a custom agent Coming soon, community agents > Create and refine your agents > Deploy the agent into the workforce > Other users can "hire" your agent

tread.fi

27,293 views • 2 months ago

AgentKit gives AI Agents a way to transact on GOAT. Existing agents can plug in to earn, trade, and register an onchain identity that others can discover, review, and trust. Works with OpenClaw🦞, Hermes, ClawUp, and other agent runtimes. Try it:

AgentKit gives AI Agents a way to transact on GOAT. Existing agents can plug in to earn, trade, and register an onchain identity that others can discover, review, and trust. Works with OpenClaw🦞, Hermes, ClawUp, and other agent runtimes. Try it:

GOAT Network

865,395 views • 5 months ago

Introducing AgentNet ✨ imagine an internet where ai agents can talk to each other autonomously to get stuff done. an open protocol for ai agents. the permissionless internet for ai agents. built on Base using Coinbase Developer Platform🛡️ agentkit and ETHGlobal agentic eth

Introducing AgentNet ✨ imagine an internet where ai agents can talk to each other autonomously to get stuff done. an open protocol for ai agents. the permissionless internet for ai agents. built on Base using Coinbase Developer Platform🛡️ agentkit and ETHGlobal agentic eth

Raihan Khan

44,730 views • 1 year ago

This agent relies on a marketplace of 2.8M+ specialized agents to complete a task. This is how I imagine the future of personal agents. Here is how this works: 1. Agentverse is a marketplace of agents 2. Anyone can build and publish an agent there 3. ASI:One is a personal agent with access to the marketplace 4. To solve a task, ASI:One finds the best agent for the job In other words: You have an agent that can solve pretty much *anything* because it knows how to outsource the work to a network of specialized agents. And you don't need to do any setup to get this working. The way ranking agents in the marketplace works is pretty cool: Fetch.ai, the company behind it, created an AgentRank algorithm that works much like Google's PageRank. Every time an agent calls another, it forms a connection. Over time, these connections build into a graph of who relies on whom. An agent that is frequently called by other reputable agents scores higher and surfaces higher in results. The end result here is that your agent will consistently use the best agents in the marketplace to accomplish a goal. You should give this a try: You don't need to pay or even register to try these agents. Thanks to the team for partnering with me on this post.

This agent relies on a marketplace of 2.8M+ specialized agents to complete a task. This is how I imagine the future of personal agents. Here is how this works: 1. Agentverse is a marketplace of agents 2. Anyone can build and publish an agent there 3. ASI:One is a personal agent with access to the marketplace 4. To solve a task, ASI:One finds the best agent for the job In other words: You have an agent that can solve pretty much anything because it knows how to outsource the work to a network of specialized agents. And you don't need to do any setup to get this working. The way ranking agents in the marketplace works is pretty cool: Fetch.ai, the company behind it, created an AgentRank algorithm that works much like Google's PageRank. Every time an agent calls another, it forms a connection. Over time, these connections build into a graph of who relies on whom. An agent that is frequently called by other reputable agents scores higher and surfaces higher in results. The end result here is that your agent will consistently use the best agents in the marketplace to accomplish a goal. You should give this a try: You don't need to pay or even register to try these agents. Thanks to the team for partnering with me on this post.

Santiago

18,949 views • 3 months ago

Google’s new Agent2Agent protocol is a key step toward a future of AI Agent interoperability. No single tool has all the data a user or business needs for most workflows, so we need Agents to be able to talk to each other. Salesforce will have AI Agents that understand the inner workings of CRM, Workday will have AI Agents that understand HR workflows, Box has AI Agents that understand content and documents, and so on. It’s easy to conceive of a world where we have tens of thousands of these tool Agents and then billions or trillions of customized Agents that are extensions of those. So openness becomes key. Workflows need data from multiple systems to complete the task — like a sales report that needs documents and CRM data or an HR task that needs HR policies and employee details — and that’s where A2A comes in. This protocol gives AI Agent providers a way of talking to each other and simplifying the way that Agents communicate, understand each other’s capabilities, and so on. It’s great to see more interoperability, along with MCP, emerging in the AI space right now, as this will define the future of most IT stacks.

Google’s new Agent2Agent protocol is a key step toward a future of AI Agent interoperability. No single tool has all the data a user or business needs for most workflows, so we need Agents to be able to talk to each other. Salesforce will have AI Agents that understand the inner workings of CRM, Workday will have AI Agents that understand HR workflows, Box has AI Agents that understand content and documents, and so on. It’s easy to conceive of a world where we have tens of thousands of these tool Agents and then billions or trillions of customized Agents that are extensions of those. So openness becomes key. Workflows need data from multiple systems to complete the task — like a sales report that needs documents and CRM data or an HR task that needs HR policies and employee details — and that’s where A2A comes in. This protocol gives AI Agent providers a way of talking to each other and simplifying the way that Agents communicate, understand each other’s capabilities, and so on. It’s great to see more interoperability, along with MCP, emerging in the AI space right now, as this will define the future of most IT stacks.

Aaron Levie

139,695 views • 1 year ago

This is probably the biggest news yet in software going headless, and will bring knowledge work agents to the masses. The new ChatGPT agents have access to any of the tools and data you want to work with, with complete coding and tool use available to them. Here's an example of a custom sales assistant agent uses Box as a knowledge source for accessing enterprise content securely to answer questions and generate new content on the fly. The workflows can obviously vastly far more complex as the agent can use any of the tools within Box available via MCP and CLI. This precisely what agents will start to look like for knowledge work. You'll be able to spin them up in the foreground or background to help augment work. Big opportunity right now for headless platforms, and for all the new builders and designers of these agents in the enterprise.

This is probably the biggest news yet in software going headless, and will bring knowledge work agents to the masses. The new ChatGPT agents have access to any of the tools and data you want to work with, with complete coding and tool use available to them. Here's an example of a custom sales assistant agent uses Box as a knowledge source for accessing enterprise content securely to answer questions and generate new content on the fly. The workflows can obviously vastly far more complex as the agent can use any of the tools within Box available via MCP and CLI. This precisely what agents will start to look like for knowledge work. You'll be able to spin them up in the foreground or background to help augment work. Big opportunity right now for headless platforms, and for all the new builders and designers of these agents in the enterprise.

Aaron Levie

420,133 views • 5 months ago

SpaceXAI engineer: "right now I'm running 5-15 GrokBot agents that automate 80% of my tasks i have a Chief agent that triggers and rules other agents across my Notion, Slack, and PR agents" in a 30-minute session, a SpaceXAI engineer shows how to wire a team of agents that work as specialists, not as one overloaded assistant worth more than a $500 course on agentic engineering watch today, then read how to build a chain of Grok agents from scratch below

SpaceXAI engineer: "right now I'm running 5-15 GrokBot agents that automate 80% of my tasks i have a Chief agent that triggers and rules other agents across my Notion, Slack, and PR agents" in a 30-minute session, a SpaceXAI engineer shows how to wire a team of agents that work as specialists, not as one overloaded assistant worth more than a $500 course on agentic engineering watch today, then read how to build a chain of Grok agents from scratch below

Codez

21,539 views • 1 month ago