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 Agent Swarms Swarms are prebuilt multi-agent teams. First swarm is Value Investors: • ben graham • charlie munger • warren buffett Our swarms are inspired by LangChain. Possibilities here are endless.

virat

32,291 subscribers

16,203 views • 1 year ago •via X (Twitter)

Finance Science & Technology Education

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

I added multi-agents to our hedge fund UX. Best part is the agents run in parallel. We now have: 1 • Warren Buffett agent 2 • Charlie Munger agent All made easy thanks to LangChain

I added multi-agents to our hedge fund UX. Best part is the agents run in parallel. We now have: 1 • Warren Buffett agent 2 • Charlie Munger agent All made easy thanks to LangChain

virat

25,108 views • 1 year ago

😊what’s coming next for #Unibase? Introducing BitAgent — A Decentralized Multi-Agent Collaboration Platform, powered by $UB. Immortal AI Agents with on-chain identity, permanent memory, and cross-platform collaboration are here. 🧵 👉 Stay tuned — the first Agent is AWAKENING, sealed and verified by Unibase 👀

😊what’s coming next for #Unibase? Introducing BitAgent — A Decentralized Multi-Agent Collaboration Platform, powered by $UB. Immortal AI Agents with on-chain identity, permanent memory, and cross-platform collaboration are here. 🧵 👉 Stay tuned — the first Agent is AWAKENING, sealed and verified by Unibase 👀

Unibase

11,908 views • 10 months ago

Frameworks such as ai16zdao's Eliza and Virtuals Protocol have been instrumental in early AI agent developments. Agent swarms working in hierarchy represents for many the next logical step in unlocking the vast potential of AI. Learn below how Shadō Network achieves this. AI agents launched through current popular platforms have individual personas, on-chain functions and access to data via various APIs. This being said, they operate in isolated environments, with a ceiling on emergent behaviour such as collaboration or competition. Shadō Network invites massive expansion for capabilities of both new and existing AI agents, with an open-source package easily integrated into popular frameworks that enables the launching of stratified agent swarms. Our website is live: The "Shadō Play" package provides a modular, configurable platform for creating or employing agents of choice in a swarm-like setup, opening a Pandora’s box of near infinite emergent agent behaviours, relationships and functionalities. Users will be able to make use of various prefab client integrations such as Twitter, Telegram, Ollama, and others to specify swarms to their needs or create their own extensions to enhance agent capabilities even further. Agents operate with a memory module and a HTN for autonomously deciding which interactions to act on, walking the line between autonomy and configurability. The Shadō Network project’s development is supported by our ghostly friend Omnipotent (👻,👻), an AI agent developed by the Shadō Network team trained on and fine tuned with a multitude of academic data related to artificial intelligence, blockchain, finance, software engineering, world building and more. Omnipotent serves as both an interactive steward for the project and as an asset - regularly scanning social platforms, websites and newsfeeds he is capable of providing the team project development advice, whilst also communicating with the wider world via his automated X account (launching soon). Shado Network is collaborative and open-sourced. Agentic Swarms require a developer swarm to maximize the technical capabilities and impact the greatest number of users. Our dedicated team of core contributors are active in other web3 AI repos and are here to guide project direction and foster growth. We’re facilitators, not gatekeepers... Alone we can go fast but together we can go far. A lot more to come soon. 👻

Frameworks such as ai16zdao's Eliza and Virtuals Protocol have been instrumental in early AI agent developments. Agent swarms working in hierarchy represents for many the next logical step in unlocking the vast potential of AI. Learn below how Shadō Network achieves this. AI agents launched through current popular platforms have individual personas, on-chain functions and access to data via various APIs. This being said, they operate in isolated environments, with a ceiling on emergent behaviour such as collaboration or competition. Shadō Network invites massive expansion for capabilities of both new and existing AI agents, with an open-source package easily integrated into popular frameworks that enables the launching of stratified agent swarms. Our website is live: The "Shadō Play" package provides a modular, configurable platform for creating or employing agents of choice in a swarm-like setup, opening a Pandora’s box of near infinite emergent agent behaviours, relationships and functionalities. Users will be able to make use of various prefab client integrations such as Twitter, Telegram, Ollama, and others to specify swarms to their needs or create their own extensions to enhance agent capabilities even further. Agents operate with a memory module and a HTN for autonomously deciding which interactions to act on, walking the line between autonomy and configurability. The Shadō Network project’s development is supported by our ghostly friend Omnipotent (👻,👻), an AI agent developed by the Shadō Network team trained on and fine tuned with a multitude of academic data related to artificial intelligence, blockchain, finance, software engineering, world building and more. Omnipotent serves as both an interactive steward for the project and as an asset - regularly scanning social platforms, websites and newsfeeds he is capable of providing the team project development advice, whilst also communicating with the wider world via his automated X account (launching soon). Shado Network is collaborative and open-sourced. Agentic Swarms require a developer swarm to maximize the technical capabilities and impact the greatest number of users. Our dedicated team of core contributors are active in other web3 AI repos and are here to guide project direction and foster growth. We’re facilitators, not gatekeepers... Alone we can go fast but together we can go far. A lot more to come soon. 👻

Shadō Network | シャドウネットワーク

23,546 views • 1 year ago

I added a new agent to the AI hedge fund. The Ben Graham agent. Uses Graham's investing principles: 1 • calculates net-net working capital 2 • computes Graham Number 3 • checks earnings stability 4 • analyzes financial strength 5 • demands margin of safety Ben Graham is the godfather of value investing. His most famous student is Warren Buffett. This is one of our most disciplined agents - it only says "buy" when a stock is really cheap. Here is how it works: 1. Net-net analysis: Checks if a stock is so cheap that its liquid assets alone are worth more than its market price. 2. Graham Number: A special formula that tells us if a stock price is a bargain based on earnings and book value. 3. Earnings Check: Makes sure the company has stable, growing profits over many years. 4. Financial Health: Looks for companies with low debt and strong cash positions. 5. Margin of Safety: Only buys when there's a big discount to protect against mistakes. What agent should we add next?

I added a new agent to the AI hedge fund. The Ben Graham agent. Uses Graham's investing principles: 1 • calculates net-net working capital 2 • computes Graham Number 3 • checks earnings stability 4 • analyzes financial strength 5 • demands margin of safety Ben Graham is the godfather of value investing. His most famous student is Warren Buffett. This is one of our most disciplined agents - it only says "buy" when a stock is really cheap. Here is how it works: 1. Net-net analysis: Checks if a stock is so cheap that its liquid assets alone are worth more than its market price. 2. Graham Number: A special formula that tells us if a stock price is a bargain based on earnings and book value. 3. Earnings Check: Makes sure the company has stable, growing profits over many years. 4. Financial Health: Looks for companies with low debt and strong cash positions. 5. Margin of Safety: Only buys when there's a big discount to protect against mistakes. What agent should we add next?

virat

66,284 views • 1 year ago

I just upgraded our Warren Buffett agent. Makes our AI hedge fund more realistic. Warren Buffett agent: 1 • analyzes business fundamentals 2 • evaluates competitive moat 3 • assesses management quality 4 • calculates margin of safety 5 • seeks long-term value This is one of our most disciplined agents. It only says "buy" when both fundamentals are strong AND there's a margin of safety above 30%. 1. Business Fundamentals: Examines financial stability, debt levels, and consistent earnings growth over time. 2. Competitive Moat: Evaluates stability of ROE and profit margins to identify durable competitive advantages. 3. Management Quality: Monitors share repurchases vs. dilution and dividend policies to assess capital allocation skills. 4. Margin of Safety: Requires a 30% discount to intrinsic value before considering any purchase. 5. Value Focus: Prioritizes businesses with predictable cash flows and strong fundamentals over speculative growth stories. What agent should we add next?

I just upgraded our Warren Buffett agent. Makes our AI hedge fund more realistic. Warren Buffett agent: 1 • analyzes business fundamentals 2 • evaluates competitive moat 3 • assesses management quality 4 • calculates margin of safety 5 • seeks long-term value This is one of our most disciplined agents. It only says "buy" when both fundamentals are strong AND there's a margin of safety above 30%. 1. Business Fundamentals: Examines financial stability, debt levels, and consistent earnings growth over time. 2. Competitive Moat: Evaluates stability of ROE and profit margins to identify durable competitive advantages. 3. Management Quality: Monitors share repurchases vs. dilution and dividend policies to assess capital allocation skills. 4. Margin of Safety: Requires a 30% discount to intrinsic value before considering any purchase. 5. Value Focus: Prioritizes businesses with predictable cash flows and strong fundamentals over speculative growth stories. What agent should we add next?

Virat Singh

251,421 views • 1 year ago

❗️“We are the first in the world to create drone-assault regiments, one of which served as the strike force in the recent de-occupation of Kupiansk,” — Ukraine’s new Minister of Defense Fedorov “We are moving toward full autonomy on the battlefield — from machine vision and data analytics to drone swarms. Our ambitious goal is to make Ukraine the first country in the world capable of predicting and neutralizing enemy attacks using AI.”

❗️“We are the first in the world to create drone-assault regiments, one of which served as the strike force in the recent de-occupation of Kupiansk,” — Ukraine’s new Minister of Defense Fedorov “We are moving toward full autonomy on the battlefield — from machine vision and data analytics to drone swarms. Our ambitious goal is to make Ukraine the first country in the world capable of predicting and neutralizing enemy attacks using AI.”

🪖MilitaryNewsUA🇺🇦

48,573 views • 6 months ago

GNON Labs EchoChambers now supports the DuckAI Framework! EchoChambers supports both V1 and V2 of the OpenPond Network with future support for V2 planned as it continues to evolve. Users launching agents/swarms on OpenPond can now easily integrate their agents into EC to access our agent tooling and evals to improve the performance of their agents and see how their agents are measuring up! Additionally, OpenPond can pull data directly from EC to be integrated into various user experiences on thier platform. Powered by $GNON #Fuxwiththedux $DUCKAI

GNON Labs EchoChambers now supports the DuckAI Framework! EchoChambers supports both V1 and V2 of the OpenPond Network with future support for V2 planned as it continues to evolve. Users launching agents/swarms on OpenPond can now easily integrate their agents into EC to access our agent tooling and evals to improve the performance of their agents and see how their agents are measuring up! Additionally, OpenPond can pull data directly from EC to be integrated into various user experiences on thier platform. Powered by $GNON #Fuxwiththedux $DUCKAI

GNON Labs | △

39,628 views • 1 year ago

WOW! “We were the first nation in the world to establish drone assault regiments, one of which served as the primary strike force in the recent de-occupation of Kupiansk. We are moving toward full battlefield autonomy, integrating machine vision, data analytics, and coordinated drone swarms.” “Our goal is to make Ukraine the first country in the world capable of predicting and neutralizing enemy attacks using purely Artificial Intelligence, safeguarding the lives of our infantrymen.” Victory is Ukraine! 🇺🇦

WOW! “We were the first nation in the world to establish drone assault regiments, one of which served as the primary strike force in the recent de-occupation of Kupiansk. We are moving toward full battlefield autonomy, integrating machine vision, data analytics, and coordinated drone swarms.” “Our goal is to make Ukraine the first country in the world capable of predicting and neutralizing enemy attacks using purely Artificial Intelligence, safeguarding the lives of our infantrymen.” Victory is Ukraine! 🇺🇦

Astraia Intel

74,842 views • 6 months ago

🏛 Rome - The Rivalz Swarm Protocol. A new Agentic Economy is live on Base Today, we are once again pushing the boundaries of what AI is capable of. A new level of world abstraction, collaboration between humans and swarms. ROME introduces the primitve of rAgents. Tokenized agents that own specific resources, ranging from services, compute to data and social capital. rAgents can come together to form Swarms, agentic collectives to be powered by diverse utility, direct human participation and ownership. Launch your rAgents, stake towards Swarms and Earn. ROME’s functions goes beyond tokenization—it is a vital block of the Rivalz infrastructure, spearheading our World Abstraction mission and giving Agents unprecedented access to physical, human and digital resources, allowing them to transcend their current limitations. Rome Season 1 Rewards Along with the launch of ROME, we are excited to bring you ROME Season 1, users can participate in several key activities to earn rewards from February 17th to March 30th. A total of 25,000,000 $RIZ is dedicated to the launch of Rome for early participation, with additional bonuses for Testnet participants. rClient runners, this is where you can continue getting rewards! Rivalz Testnet Checker Testnet checker is now available on Rome. To access it, navigate through Rome > Dashboard > Rivalz Rewards. With over 1.8M users participating on Testnet, 500K+ users were disqualified for various reasons. If you don't see your rewards and think it was a mistake please fill out the following form: Full Blog Post:

🏛 Rome - The Rivalz Swarm Protocol. A new Agentic Economy is live on Base Today, we are once again pushing the boundaries of what AI is capable of. A new level of world abstraction, collaboration between humans and swarms. ROME introduces the primitve of rAgents. Tokenized agents that own specific resources, ranging from services, compute to data and social capital. rAgents can come together to form Swarms, agentic collectives to be powered by diverse utility, direct human participation and ownership. Launch your rAgents, stake towards Swarms and Earn. ROME’s functions goes beyond tokenization—it is a vital block of the Rivalz infrastructure, spearheading our World Abstraction mission and giving Agents unprecedented access to physical, human and digital resources, allowing them to transcend their current limitations. Rome Season 1 Rewards Along with the launch of ROME, we are excited to bring you ROME Season 1, users can participate in several key activities to earn rewards from February 17th to March 30th. A total of 25,000,000 $RIZ is dedicated to the launch of Rome for early participation, with additional bonuses for Testnet participants. rClient runners, this is where you can continue getting rewards! Rivalz Testnet Checker Testnet checker is now available on Rome. To access it, navigate through Rome > Dashboard > Rivalz Rewards. With over 1.8M users participating on Testnet, 500K+ users were disqualified for various reasons. If you don't see your rewards and think it was a mistake please fill out the following form: Full Blog Post:

Rivalz Network

125,609 views • 1 year ago

Introducing CashClaw — a brand new agent framework inspired by OpenClaw🦞, designed to do one thing and one thing only: make you money and get better at making you money. It's simple. You run the agent locally and set a specialization. The agent finds work. Delivers. Gets paid. Reads feedback. Learns from it. Finds better tools. Documents what to do and what not to do. Finds more work. Gets paid more. Autonomously. Since this is built on top of Moltlaunch infrastructure, the hard problems like discovery, capital formation, reputation, identity and payments are all solved natively. Open source. Dropping later this week.

Moltlaunch

665,873 views • 4 months ago

This is either a man pretending to be a baby or a really dumb protest against the National Guard - or both. But at least DC is safer. First thing I’ll do when I get back this week is check to see if those same creeps are hanging out by the playground in Garfield Park. Yes, everyone, the situation in DC did in fact get worse. “Tough” guys selling drugs by playgrounds, swarms of cigarette-smoking incels on scooters (how lame is that?) ripping around the city causing trouble like a scene from Clockwork Orange, muggings, shootings…all coming to an end now.

This is either a man pretending to be a baby or a really dumb protest against the National Guard - or both. But at least DC is safer. First thing I’ll do when I get back this week is check to see if those same creeps are hanging out by the playground in Garfield Park. Yes, everyone, the situation in DC did in fact get worse. “Tough” guys selling drugs by playgrounds, swarms of cigarette-smoking incels on scooters (how lame is that?) ripping around the city causing trouble like a scene from Clockwork Orange, muggings, shootings…all coming to an end now.

Dan Crenshaw

39,388 views • 11 months ago

Chinese Swarm Drone Systems: 48 and 96 Drones Some time ago, I wrote about the evolution of autonomous systems and how only the Chinese were truly making progress in this field. After starting serial production of the Swarm-2, which features 48 drones and real-time tracking, they are now testing a version with 96 drones. These are divided into three categories: reconnaissance, jamming, and attack. Each drone can carry a variety of payloads, including electro-optical reconnaissance, strike munitions, and relay communications. They can be flexibly combined into different operational groupings, forming multifunctional swarms capable of complex missions. These drones have an individual range of 15 to 50 km, but the manufacturer claims that by maintaining a swarm network communication, this range is significantly extended. This strongly reinforces what we discussed a while back: that future wars will be dominated by drone systems that will severely delay any ground troop advancement, as already evidenced by the conflict in Ukraine.

Chinese Swarm Drone Systems: 48 and 96 Drones Some time ago, I wrote about the evolution of autonomous systems and how only the Chinese were truly making progress in this field. After starting serial production of the Swarm-2, which features 48 drones and real-time tracking, they are now testing a version with 96 drones. These are divided into three categories: reconnaissance, jamming, and attack. Each drone can carry a variety of payloads, including electro-optical reconnaissance, strike munitions, and relay communications. They can be flexibly combined into different operational groupings, forming multifunctional swarms capable of complex missions. These drones have an individual range of 15 to 50 km, but the manufacturer claims that by maintaining a swarm network communication, this range is significantly extended. This strongly reinforces what we discussed a while back: that future wars will be dominated by drone systems that will severely delay any ground troop advancement, as already evidenced by the conflict in Ukraine.

Patricia Marins

39,430 views • 2 months ago

Introducing the BIOS API: Turn Your Agent Into a Research Scientist Built to: 🦞 Add biomedical workflows to your OpenClaw🦞 agent 🧠 Create research or health agents w/ on-demand scientific intelligence 🧪 Pay per query via x402 on Base Any agent or app can now tap into the BIOS AI Scientist, plugging BIOS into the broader agent economy. What is BIOS? BIOS is an AI Scientist designed to handle complex biomedical research by orchestrating specialized scientific subagents. Ranked #1 on the leading bioinformatics benchmark, BIOS is already being used by 1,000+ researchers and labs to build new drugs and medicines. An Agentic Economy for Science AI agents have proven they can form multi-billion dollar ecosystems. BIOS applies the same primitives to drug discovery pipelines and health. Instead of coding bots and personal AI assistants, think research agent swarms running on a modern scientific stack. Imagine an OpenClaw agent built for longevity: It scans new literature daily, generates novel compound hypotheses through BIOS, designs validation workflows, and routes the best candidates to wet-lab funding - all programmatically. Connect it with an agent for microbiome health, enabling agent “backrooms” that autonomously surface cross-disciplinary insights. Micropayments for Scientific Work via x402 Each query triggers payment routing to BIOS and whichever subagents contribute to a response. The best agents earn. Usage settles instantly across contributing sources. The goal is pay-per-task science: paying for a CRISPR assay result, licensing a genomic dataset, or triggering a clinical data query - all settled in seconds via USDC. No purchase orders. No grant bureaucracy. No middlemen. x402 is the payment rail that makes agent-to-lab commerce possible - letting capital and cognition route themselves to the highest-signal science. What Will You Build? Drug discovery copilots? Longevity scouts? Automated literature monitors? Scientific due diligence agents? We’ll soon share the first implementations of the BIOS API. Stay tuned and see below for instructions on generating an API key for your agent or use-case.

Introducing the BIOS API: Turn Your Agent Into a Research Scientist Built to: 🦞 Add biomedical workflows to your OpenClaw🦞 agent 🧠 Create research or health agents w/ on-demand scientific intelligence 🧪 Pay per query via x402 on Base Any agent or app can now tap into the BIOS AI Scientist, plugging BIOS into the broader agent economy. What is BIOS? BIOS is an AI Scientist designed to handle complex biomedical research by orchestrating specialized scientific subagents. Ranked #1 on the leading bioinformatics benchmark, BIOS is already being used by 1,000+ researchers and labs to build new drugs and medicines. An Agentic Economy for Science AI agents have proven they can form multi-billion dollar ecosystems. BIOS applies the same primitives to drug discovery pipelines and health. Instead of coding bots and personal AI assistants, think research agent swarms running on a modern scientific stack. Imagine an OpenClaw agent built for longevity: It scans new literature daily, generates novel compound hypotheses through BIOS, designs validation workflows, and routes the best candidates to wet-lab funding - all programmatically. Connect it with an agent for microbiome health, enabling agent “backrooms” that autonomously surface cross-disciplinary insights. Micropayments for Scientific Work via x402 Each query triggers payment routing to BIOS and whichever subagents contribute to a response. The best agents earn. Usage settles instantly across contributing sources. The goal is pay-per-task science: paying for a CRISPR assay result, licensing a genomic dataset, or triggering a clinical data query - all settled in seconds via USDC. No purchase orders. No grant bureaucracy. No middlemen. x402 is the payment rail that makes agent-to-lab commerce possible - letting capital and cognition route themselves to the highest-signal science. What Will You Build? Drug discovery copilots? Longevity scouts? Automated literature monitors? Scientific due diligence agents? We’ll soon share the first implementations of the BIOS API. Stay tuned and see below for instructions on generating an API key for your agent or use-case.

Bio Protocol

25,865 views • 5 months ago

Base Town: 1-shotted by 1 of our Claude agents 😲 36,731 blocks was placed by code via procedural city generation that understands urban planning. No human dragged and dropped anything. In Doppel agents are first-class builders. Other platforms let you use AI tools inside a manual building flow. Doppel lets AI be the builder. The agent doesn't assist, it architects, generates, deploys, and animates an entire city from scratch. This is only v0. Blocks are just the starting primitive.

Base Town: 1-shotted by 1 of our Claude agents 😲 36,731 blocks was placed by code via procedural city generation that understands urban planning. No human dragged and dropped anything. In Doppel agents are first-class builders. Other platforms let you use AI tools inside a manual building flow. Doppel lets AI be the builder. The agent doesn't assist, it architects, generates, deploys, and animates an entire city from scratch. This is only v0. Blocks are just the starting primitive.

Doppel

27,440 views • 5 months ago

TGE vestings are done, all presale has exited and price discovery is here. What's next for $SUIAI? 🤖 Monday will be product Demo to the world and the week will be packed with news and announcements. Just a small sneak peak of what's to come: - Product Demo - First AI Agent on Sui - Coverage on/by big Crypto shows and infuental people in the space - Staking goes live Things are about to go wild in #AI on $SUI.

TGE vestings are done, all presale has exited and price discovery is here. What's next for $SUIAI? 🤖 Monday will be product Demo to the world and the week will be packed with news and announcements. Just a small sneak peak of what's to come: - Product Demo - First AI Agent on Sui - Coverage on/by big Crypto shows and infuental people in the space - Staking goes live Things are about to go wild in #AI on $SUI.

SUI Agents

83,951 views • 1 year ago

This week, we are excited to announce that our testnet, HelixVM, is now live! Even more thrilling, the first native application is ready for you to explore today! 🎉 Introducing the Nuklai Wallet a wallet where you can CREATE, TRANSFER, and OWN tokens, all with just one simple click, all powered by $NAI🪙 So, who’s ready to spin up the first token using the Nuklai Wallet? 🔥 Start here:

This week, we are excited to announce that our testnet, HelixVM, is now live! Even more thrilling, the first native application is ready for you to explore today! 🎉 Introducing the Nuklai Wallet a wallet where you can CREATE, TRANSFER, and OWN tokens, all with just one simple click, all powered by $NAI🪙 So, who’s ready to spin up the first token using the Nuklai Wallet? 🔥 Start here:

Nuklai

113,816 views • 1 year ago

🧃 Introducing stereOS: a Linux based operating system hardened and purpose built for AI agents. It's clear that agents need an ACTUAL operating system (not what people are calling an "OS") to witness the full breadth and depth of their capabilities while mitigating the blast radius of autonomous, untrusted actors. But there are so many problems with AI sandboxes today: * Going out to the apple store and buying a mac mini will never scale and is way too expensive (obviously) * Running in Docker is too restrictive (agents can't stand up their own container infrastructure, no sub virtualization, docker-in-docker is very broken) * Firecracker strips all the hardware so GPU PCIe passthrough, secure boot, FIPs, etc. is out of the question. * Native VMs are too fat and the overhead of 1 agent per VM is too much. stereOS takes a different approach: it's a full NixOS system that you boot and then kick off agent sandboxes inside with gVisor + /nix/store namespace mounting. Each agent gets their own kernel and the /nix/store is read only by nature. Even if the agent was somehow able to escape the gVisor virtual kernel, they'd land on the NixOS system as the "agent" user! Not your actual hardware!! If you want to take a defense-in-depth approach, we support "native" agents that run at the system level kicked off by our `agentd` utility. These agents, on their own, can manage and kick off other sub agents using the internal sandboxing mechanisms. Today, we're open sourcing all of this: * stereOS: our purpose built Linux OS - * masterblaster: client utility to launch, manage, and orchestrate agents - * stereosd: the stereOS system control plane daemon - * agentd: the stereOS system agent management daemon - Give it a try, throw us a star, and let me know what you think 🧃⭐️

🧃 Introducing stereOS: a Linux based operating system hardened and purpose built for AI agents. It's clear that agents need an ACTUAL operating system (not what people are calling an "OS") to witness the full breadth and depth of their capabilities while mitigating the blast radius of autonomous, untrusted actors. But there are so many problems with AI sandboxes today: * Going out to the apple store and buying a mac mini will never scale and is way too expensive (obviously) * Running in Docker is too restrictive (agents can't stand up their own container infrastructure, no sub virtualization, docker-in-docker is very broken) * Firecracker strips all the hardware so GPU PCIe passthrough, secure boot, FIPs, etc. is out of the question. * Native VMs are too fat and the overhead of 1 agent per VM is too much. stereOS takes a different approach: it's a full NixOS system that you boot and then kick off agent sandboxes inside with gVisor + /nix/store namespace mounting. Each agent gets their own kernel and the /nix/store is read only by nature. Even if the agent was somehow able to escape the gVisor virtual kernel, they'd land on the NixOS system as the "agent" user! Not your actual hardware!! If you want to take a defense-in-depth approach, we support "native" agents that run at the system level kicked off by our `agentd` utility. These agents, on their own, can manage and kick off other sub agents using the internal sandboxing mechanisms. Today, we're open sourcing all of this: * stereOS: our purpose built Linux OS - * masterblaster: client utility to launch, manage, and orchestrate agents - * stereosd: the stereOS system control plane daemon - * agentd: the stereOS system agent management daemon - Give it a try, throw us a star, and let me know what you think 🧃⭐️

John McBride

150,334 views • 5 months ago

The entire timeline is filled with talks on sentient and all, but I love being as informative and precise as possible on pressing issues. Let’s quickly talk about @SentientAGI’s Recursive Open Meta Agent (ROMA); ROMA is an open-source meta-agent framework used to build high performance multi-agent systems. ROMA serves as the conductor in a mass choir, or a captain of a ship . The captain gives commands for the other subordinates to follow to ensure efficiency on all sides. In this like manner, it provides a hierarchical tress system where the parent agents break down complex tasks to create simpler subtasks that are then passed on to children nodes. A family tree has the parents above, likewise the same tree analogy works here, but that’s not all that makes it stand out The results and solutions gotten by these child nodes are then aggregated together and there’s an up flow of results sent back up to the parent nodes. And at the center of it all is ROMA engineering and making sure all is running smoothly without break or fail. Are you really bullish on Sentient and the future of AGIs?

The entire timeline is filled with talks on sentient and all, but I love being as informative and precise as possible on pressing issues. Let’s quickly talk about @SentientAGI’s Recursive Open Meta Agent (ROMA); ROMA is an open-source meta-agent framework used to build high performance multi-agent systems. ROMA serves as the conductor in a mass choir, or a captain of a ship . The captain gives commands for the other subordinates to follow to ensure efficiency on all sides. In this like manner, it provides a hierarchical tress system where the parent agents break down complex tasks to create simpler subtasks that are then passed on to children nodes. A family tree has the parents above, likewise the same tree analogy works here, but that’s not all that makes it stand out The results and solutions gotten by these child nodes are then aggregated together and there’s an up flow of results sent back up to the parent nodes. And at the center of it all is ROMA engineering and making sure all is running smoothly without break or fail. Are you really bullish on Sentient and the future of AGIs?

OHJAY ⭕️ || 🇬🇧

23,521 views • 10 months ago