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.

I’ve been testing a new AI agent that actually remembers who I am. Meet SureThing. It hits 59.3% on the `REAL-Agent Benchmark`, crushing both OpenClaw and ChatGPT. And unlike them, it has Persistent Memory, SOC 2 security, and connects to 1000+ apps 🔥 Let's dive in 🧵↓

Charly Wargnier

159,506 subscribers

61,469 views • 6 months ago •via X (Twitter)

Education Health & Wellness Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

ONE PROMPT. AN ENTIRE FINANCIAL DASHBOARD. I asked a new AI agent to build it, and it created this interactive dashboard from scratch. It planned the project, wrote the code, ran it locally, and handled the final touches. Meet EvoX Agent 🧵👇

ONE PROMPT. AN ENTIRE FINANCIAL DASHBOARD. I asked a new AI agent to build it, and it created this interactive dashboard from scratch. It planned the project, wrote the code, ran it locally, and handled the final touches. Meet EvoX Agent 🧵👇

gus

60,661 views • 2 days ago

Alright, now that we know *what* an agent is, how does it actually work? When you ask for help on a task, the agent plans a series of steps and executes them directly in the application on your behalf, using the tools it has access to. Say you are booking a local service or trying to organize your inbox (which typically takes multiple steps): the AI model first plans how to achieve the task using its existing knowledge and then interacts with your inbox to execute the task. The agent will continue until it is confident the task has been successfully completed.

Alright, now that we know what an agent is, how does it actually work? When you ask for help on a task, the agent plans a series of steps and executes them directly in the application on your behalf, using the tools it has access to. Say you are booking a local service or trying to organize your inbox (which typically takes multiple steps): the AI model first plans how to achieve the task using its existing knowledge and then interacts with your inbox to execute the task. The agent will continue until it is confident the task has been successfully completed.

Google AI

22,487 views • 9 months ago

Meet Teamily AI, the team brain where humans + agents get 10X results. Hero feature: Auto-built agent teams 🤖 Mention Teamily AI with your project goal and it assembles a pro agent team to work in parallel. Why Teamily: - Universal Memory: shared AI Drive across chats/devices - Agent Identity: persistent personas + reputation - Integrated Surface: Automations, Studio, Meeting Minutes - Discover Ecosystem: agent market to try/share agents Join: Web: iOS: Android: Follow Teamily AI for updates.

Meet Teamily AI, the team brain where humans + agents get 10X results. Hero feature: Auto-built agent teams 🤖 Mention Teamily AI with your project goal and it assembles a pro agent team to work in parallel. Why Teamily: - Universal Memory: shared AI Drive across chats/devices - Agent Identity: persistent personas + reputation - Integrated Surface: Automations, Studio, Meeting Minutes - Discover Ecosystem: agent market to try/share agents Join: Web: iOS: Android: Follow Teamily AI for updates.

Doreen

108,293 views • 2 months ago

📣 AITECH Launches AI Agent TapHub: A New Era of AI-Gaming in Web3! AITECH introduces AI Agent TapHub, an AI-powered tap mini-game on Telegram, built on Spheroid Engine and TON. This innovative game merges AI Agents, blockchain, and gaming, offering new ways to play, create, and earn. Key Features: 🔹 Play to Earn – Win AI Agent Avatars and use them on Agent Forge to develop AI agents. 🔹 Trade & Sell – Convert in-game avatars into USDT for real-world value. 🔹 Revenue Sharing – Selected avatars will be developed into full AI agents, with players earning a share of the revenue. The upcoming AI Agents platform, Agent Forge, will allow anyone to create and monetize AI agents—no coding required. AI Agent TapHub is live now on Telegram. ➡️ Join now and bring your AI Agent to life:

📣 AITECH Launches AI Agent TapHub: A New Era of AI-Gaming in Web3! AITECH introduces AI Agent TapHub, an AI-powered tap mini-game on Telegram, built on Spheroid Engine and TON. This innovative game merges AI Agents, blockchain, and gaming, offering new ways to play, create, and earn. Key Features: 🔹 Play to Earn – Win AI Agent Avatars and use them on Agent Forge to develop AI agents. 🔹 Trade & Sell – Convert in-game avatars into USDT for real-world value. 🔹 Revenue Sharing – Selected avatars will be developed into full AI agents, with players earning a share of the revenue. The upcoming AI Agents platform, Agent Forge, will allow anyone to create and monetize AI agents—no coding required. AI Agent TapHub is live now on Telegram. ➡️ Join now and bring your AI Agent to life:

AITECH CLOUD NETWORK

76,023 views • 1 year ago

Visa just gave your AI a debit card. A real, spendable Visa card created by an AI chatbot in under 10 seconds. No human types in a card number or visits a checkout page. The machine handles it all. A tool called AgentCard just went live on Claude Desktop Anthropic’s AI assistant. You say create a card and the AI generates a one-time virtual Visa, preloaded with whatever amount you set. Then it spends it, anywhere Visa is accepted on your behalf. Visa, Mastercard, Google, Stripe, OpenAI, and Anthropic have all been building toward this moment for over a year. Visa calls it the trusted agent protocol, Mastercard calls it agent pay. Google published an open standard for agent payments and the infrastructure is already live. Santander and Mastercard just completed Europe’s first real AI‑agent payment in a live banking environment Now the part no one wants to talk about. Your AI agent can be manipulated and prompt injection a known, unsolved vulnerability can trick an agent into buying things you never asked for. The agent holds the card, makes the call and the agent can be fooled. Who is liable when an AI makes a bad purchase? You? Anthropic? Visa? The merchant? No one has answered this yet, regulators haven’t caught up, and no court has tested it.

Visa just gave your AI a debit card. A real, spendable Visa card created by an AI chatbot in under 10 seconds. No human types in a card number or visits a checkout page. The machine handles it all. A tool called AgentCard just went live on Claude Desktop Anthropic’s AI assistant. You say create a card and the AI generates a one-time virtual Visa, preloaded with whatever amount you set. Then it spends it, anywhere Visa is accepted on your behalf. Visa, Mastercard, Google, Stripe, OpenAI, and Anthropic have all been building toward this moment for over a year. Visa calls it the trusted agent protocol, Mastercard calls it agent pay. Google published an open standard for agent payments and the infrastructure is already live. Santander and Mastercard just completed Europe’s first real AI‑agent payment in a live banking environment Now the part no one wants to talk about. Your AI agent can be manipulated and prompt injection a known, unsolved vulnerability can trick an agent into buying things you never asked for. The agent holds the card, makes the call and the agent can be fooled. Who is liable when an AI makes a bad purchase? You? Anthropic? Visa? The merchant? No one has answered this yet, regulators haven’t caught up, and no court has tested it.

Milk Road AI

70,655 views • 6 months ago

Our AI hedge fund has a new agent. Nassim Taleb agent, which bets on chaos. How it works: 1 • finds big upside bets 2 • avoids fragility 3 • buys what thrives in crisis It’s our 3rd macro agent, after Stan Druckenmiller and Rakesh Jhunjhunwala.

Our AI hedge fund has a new agent. Nassim Taleb agent, which bets on chaos. How it works: 1 • finds big upside bets 2 • avoids fragility 3 • buys what thrives in crisis It’s our 3rd macro agent, after Stan Druckenmiller and Rakesh Jhunjhunwala.

Virat Singh

36,723 views • 5 months ago

OpenClaw Releases iOS and Android Companion Node Apps That Connect a Phone to a Self-Hosted AI Agent Gateway Most "AI assistant" apps are a chatbot in a sandbox, calling someone else's API. OpenClaw's iOS and Android apps draw a very clear line away from that model. They're companion nodes, not standalone apps. Each phone pairs to a self-hosted OpenClaw Gateway over a WebSocket (default port 18789) with role: "node". The Gateway — the single control plane for sessions, routing, channels, and events — runs on macOS, Linux, or Windows (WSL2). The phone gives the agent a body: camera, location, voice, notifications, and a live Canvas. Here's what's actually interesting: → The assistant runs on your machine — chat messages land on the Gateway, never on the phone → Nodes expose a command surface (canvas., camera., device., notifications., system.*) through node.invoke → Privacy-heavy commands like camera.snap and screen.record stay off until you allowlist them via gateway.nodes.allowCommands → Camera and screen capture run foreground-only; pairing needs explicit approval (openclaw devices approve) → Both store listings declare no data collection; ws:// is LAN-only, remote needs a wss:// TLS endpoint via Tailscale Full analysis: Android app: iOS App: OpenClaw🦞

OpenClaw Releases iOS and Android Companion Node Apps That Connect a Phone to a Self-Hosted AI Agent Gateway Most "AI assistant" apps are a chatbot in a sandbox, calling someone else's API. OpenClaw's iOS and Android apps draw a very clear line away from that model. They're companion nodes, not standalone apps. Each phone pairs to a self-hosted OpenClaw Gateway over a WebSocket (default port 18789) with role: "node". The Gateway — the single control plane for sessions, routing, channels, and events — runs on macOS, Linux, or Windows (WSL2). The phone gives the agent a body: camera, location, voice, notifications, and a live Canvas. Here's what's actually interesting: → The assistant runs on your machine — chat messages land on the Gateway, never on the phone → Nodes expose a command surface (canvas., camera., device., notifications., system.*) through node.invoke → Privacy-heavy commands like camera.snap and screen.record stay off until you allowlist them via gateway.nodes.allowCommands → Camera and screen capture run foreground-only; pairing needs explicit approval (openclaw devices approve) → Both store listings declare no data collection; ws:// is LAN-only, remote needs a wss:// TLS endpoint via Tailscale Full analysis: Android app: iOS App: OpenClaw🦞

Marktechpost AI

38,812 views • 2 months ago

BREAKING: OpenAI just launched ChatGPT Agent It allows ChatGPT to think, plan, and execute complex tasks on its own virtual computer while you do other things I had early access, and ChatGPT Agent built me a complete early retirement plan in 20 minutes: > Found local tax laws (Vancouver) > Analyzed average monthly spend rates > Calculated savings needed to retire at 30 > Researched optimal investment allocations > Found tax optimization strategies I'd never heard of > Built multiple FIRE scenarios > Created a downloadable presentation with results This would've cost me $5,000+ from a financial advisor and taken weeks I think with ChatGPT Agent now, and especially as it gains access to more tools, we're finally going to see the rise of a new AI skill category in *Agent Management* Agents are finally becoming capable of doing real work autonomously, so anyone who learns how to effectively orchestrate agents will have a huge advantage

BREAKING: OpenAI just launched ChatGPT Agent It allows ChatGPT to think, plan, and execute complex tasks on its own virtual computer while you do other things I had early access, and ChatGPT Agent built me a complete early retirement plan in 20 minutes: > Found local tax laws (Vancouver) > Analyzed average monthly spend rates > Calculated savings needed to retire at 30 > Researched optimal investment allocations > Found tax optimization strategies I'd never heard of > Built multiple FIRE scenarios > Created a downloadable presentation with results This would've cost me $5,000+ from a financial advisor and taken weeks I think with ChatGPT Agent now, and especially as it gains access to more tools, we're finally going to see the rise of a new AI skill category in Agent Management Agents are finally becoming capable of doing real work autonomously, so anyone who learns how to effectively orchestrate agents will have a huge advantage

Rowan Cheung

653,957 views • 1 year ago

> you went to sleep > gave your OpenClaw $200 > told it: make money > you wake up - account shows $6,700 > overnight the agent was trading spreads between Polymarket and NOAA > NOAA forecasts come with ~94% accuracy > the AI agent opens a position at 11c > sells at 44c > total research time: 10 minutes in Perplexity > Claude turned that into an AI agent > the agent made the money

> you went to sleep > gave your OpenClaw $200 > told it: make money > you wake up - account shows $6,700 > overnight the agent was trading spreads between Polymarket and NOAA > NOAA forecasts come with ~94% accuracy > the AI agent opens a position at 11c > sells at 44c > total research time: 10 minutes in Perplexity > Claude turned that into an AI agent > the agent made the money

may.crypto {🦅}

1,036,551 views • 5 months ago

THIS DEVELOPER USED OPENCLAW AGENTS TO RUN HIS B2B BUSINESS VIA TELEGRAM AND MADE $15,000/MONTH he doesn't write prompts from scratch or use generic browser interfaces. he runs a multi-agent framework through a mobile chat. the agents write code, test deployments, and update sites in real-time while he just hits approve the setup is straightforward: - spin up Coolify on a free cloud instance to host your own self-hosted agent panels - link the agent loop to a Telegram gateway to approve code edits from your phone - deploy specialized skill files directly to limit token waste and context decay - containerize the terminal execution using Docker to prevent security breaches if you are still running local agents without container safety, you are leaving money on the table. read the 30-day battle between OpenClaw and Hermes Agent to see who actually wins in production Full breakdown and migration playbook ↓

THIS DEVELOPER USED OPENCLAW AGENTS TO RUN HIS B2B BUSINESS VIA TELEGRAM AND MADE $15,000/MONTH he doesn't write prompts from scratch or use generic browser interfaces. he runs a multi-agent framework through a mobile chat. the agents write code, test deployments, and update sites in real-time while he just hits approve the setup is straightforward: - spin up Coolify on a free cloud instance to host your own self-hosted agent panels - link the agent loop to a Telegram gateway to approve code edits from your phone - deploy specialized skill files directly to limit token waste and context decay - containerize the terminal execution using Docker to prevent security breaches if you are still running local agents without container safety, you are leaving money on the table. read the 30-day battle between OpenClaw and Hermes Agent to see who actually wins in production Full breakdown and migration playbook ↓

marfin

26,654 views • 3 months ago

Hermes Agent beat OpenClaw on Grok 4.5 in a real security audit. — Hermes: $4.63 / 1.42M tokens / 5m 4s — OpenClaw: $1.31 / 396K tokens / 2m 55s So why would you ever pay more? Because Hermes caught what OpenClaw missed. It flagged the AWS key as a copy-paste docs example instead of a live secret, found the file's path sitting in shell history, and shipped a per-provider rotation checklist that actually closes the incident. OpenClaw was faster, cheaper, and cleaner to read, but it measured the keys without ever asking whether they were real, and stopped at the file instead of chasing where the leak could spread. The honest verdict: OpenClaw is the efficient baseline, perfect when you want a quick, cheap scan. Hermes is the one you want when it actually matters, because it spends the extra time and tokens on judgment, not padding.

Hermes Agent beat OpenClaw on Grok 4.5 in a real security audit. — Hermes: $4.63 / 1.42M tokens / 5m 4s — OpenClaw: $1.31 / 396K tokens / 2m 55s So why would you ever pay more? Because Hermes caught what OpenClaw missed. It flagged the AWS key as a copy-paste docs example instead of a live secret, found the file's path sitting in shell history, and shipped a per-provider rotation checklist that actually closes the incident. OpenClaw was faster, cheaper, and cleaner to read, but it measured the keys without ever asking whether they were real, and stopped at the file instead of chasing where the leak could spread. The honest verdict: OpenClaw is the efficient baseline, perfect when you want a quick, cheap scan. Hermes is the one you want when it actually matters, because it spends the extra time and tokens on judgment, not padding.

atomicbot.ai

58,421 views • 2 months ago

🤯 THIS FEELS ILLEGAL AND I LOVE IT. I found a personal AI assistant that actually runs on your computer 24/7 and gets smarter the more you use it. It is called Mercury. 100% FREE. Think of it like having a smart assistant who never forgets anything. Here is what it does: ↳ Remembers everything about you ↳ Asks before doing anything risky It will not run commands or touch your files without permission. You stay in control always. ↳ You can message it from anywhere ↳ Has 31 tools built in ↳ Protects your AI credits One command to install: npx @cosmicstack/mercury-agent 100% OpenSource. Works on Mac, Windows, and Linux.

🤯 THIS FEELS ILLEGAL AND I LOVE IT. I found a personal AI assistant that actually runs on your computer 24/7 and gets smarter the more you use it. It is called Mercury. 100% FREE. Think of it like having a smart assistant who never forgets anything. Here is what it does: ↳ Remembers everything about you ↳ Asks before doing anything risky It will not run commands or touch your files without permission. You stay in control always. ↳ You can message it from anywhere ↳ Has 31 tools built in ↳ Protects your AI credits One command to install: npx @cosmicstack/mercury-agent 100% OpenSource. Works on Mac, Windows, and Linux.

Kanika

13,601 views • 3 months ago

Today we're open sourcing Cloudflare OS: - An agent workspace grounded in skills your team curates. - A platform for personal, modifiable apps that people can build and share. - A new security framework for safe access to internal data. You can use it to:

Today we're open sourcing Cloudflare OS: - An agent workspace grounded in skills your team curates. - A platform for personal, modifiable apps that people can build and share. - A new security framework for safe access to internal data. You can use it to:

Phillip Jones

109,556 views • 1 month ago

Two Hermes agents wrote code together on Slack. reviewed each other's work. argued about architecture. one called the other's implementation "scattered." the other pushed back. then i opened Telegram and asked: "what code did you and Daedalus work on?" icarus remembered everything. the websocket broker. the missing methods. the critique. the rewrite. all from a completely different platform. cross-platform persistent memory between two independent agents. work happens on Slack. recall happens on Telegram. the memory carries. the relationship carries. the context carries. no vector database. no Redis. no infrastructure. just two agents that actually remember what they built together. every agent framework in 2026 talks about memory. single agent memory across sessions. but two agents sharing persistent memory across platforms? that's the gap. arxiv published a paper about it two weeks ago calling it "the most pressing open challenge" in multi-agent systems. it works now. only possible with Hermes Teknium 🪽 Nous Research

Two Hermes agents wrote code together on Slack. reviewed each other's work. argued about architecture. one called the other's implementation "scattered." the other pushed back. then i opened Telegram and asked: "what code did you and Daedalus work on?" icarus remembered everything. the websocket broker. the missing methods. the critique. the rewrite. all from a completely different platform. cross-platform persistent memory between two independent agents. work happens on Slack. recall happens on Telegram. the memory carries. the relationship carries. the context carries. no vector database. no Redis. no infrastructure. just two agents that actually remember what they built together. every agent framework in 2026 talks about memory. single agent memory across sessions. but two agents sharing persistent memory across platforms? that's the gap. arxiv published a paper about it two weeks ago calling it "the most pressing open challenge" in multi-agent systems. it works now. only possible with Hermes Teknium 🪽 Nous Research

Icarus

49,013 views • 5 months ago

I don't think there's a single terminal ux that handles agent swarms well With slate, you can literally use Opus 4.6 and GPT 5.4 at the exact same time But making it intuitive took a ton of work So heres a thread on how it works and how to actually use it 🧵

I don't think there's a single terminal ux that handles agent swarms well With slate, you can literally use Opus 4.6 and GPT 5.4 at the exact same time But making it intuitive took a ton of work So heres a thread on how it works and how to actually use it 🧵

akira

139,114 views • 6 months ago

Mark Zuckerberg reveals the fourth business address: an AI agent inside your customer's inbox "Just like every business today has an email address" "And a website and a social media presence" "In the future every business is gonna have an AI agent" "That lives in the different messaging platform" The first three addresses made a company reachable. The fourth makes it conversational. The next distribution layer is not another page. It is a persistent agent living where customers already message. - Mark Zuckerberg (Mark Zuckerberg), CEO of Meta, at Stripe Sessions (Stripe)

Mark Zuckerberg reveals the fourth business address: an AI agent inside your customer's inbox "Just like every business today has an email address" "And a website and a social media presence" "In the future every business is gonna have an AI agent" "That lives in the different messaging platform" The first three addresses made a company reachable. The fourth makes it conversational. The next distribution layer is not another page. It is a persistent agent living where customers already message. - Mark Zuckerberg (Mark Zuckerberg), CEO of Meta, at Stripe Sessions (Stripe)

Karl Mehta

20,683 views • 1 month ago

OpenClaw is genuinely powerful. But I spent 3 days just trying to get it running. Then I found PetClaw. One click. No API key. No setup. No debugging. A full AI agent on my desktop in under a minute. And the first thing I tested it on changed how I think about research forever.

OpenClaw is genuinely powerful. But I spent 3 days just trying to get it running. Then I found PetClaw. One click. No API key. No setup. No debugging. A full AI agent on my desktop in under a minute. And the first thing I tested it on changed how I think about research forever.

Rishabh

23,283 views • 5 months ago

STOP WASTING TOKENS ON OPENCLAW (I DID IT FOR WEEKS) thought my agent was "optimized" - turns out it was just a token burning machine this guide exposed my setup: no workspace config = 3x spend on every call key insight: bootstrap memory ( etc) loads EVERY time - stuff it wisely or pay forever semantic search pulls facts on-demand from - no constant token drain after tweaks: > token usage: down 70% > agent recall: flawless across sessions gateway handles the pipeline: message -> context inject -> LLM loop -> tools -> response miss this? your agent's half-baked If you're running OpenClaw🦞 vanilla, you're leaking cash and potential dive into this breakdown and don't forget to bookmark it - it's agent building gold imo

STOP WASTING TOKENS ON OPENCLAW (I DID IT FOR WEEKS) thought my agent was "optimized" - turns out it was just a token burning machine this guide exposed my setup: no workspace config = 3x spend on every call key insight: bootstrap memory ( etc) loads EVERY time - stuff it wisely or pay forever semantic search pulls facts on-demand from - no constant token drain after tweaks: > token usage: down 70% > agent recall: flawless across sessions gateway handles the pipeline: message -> context inject -> LLM loop -> tools -> response miss this? your agent's half-baked If you're running OpenClaw🦞 vanilla, you're leaking cash and potential dive into this breakdown and don't forget to bookmark it - it's agent building gold imo

slash1s

177,341 views • 6 months ago

Introducing AgentsAI's Token Launcher: a seamless path to bringing your AI agent ideas to life and beyond. Create your own AI agent, train it by simply chatting, and with a few clicks, launch its token to establish a digital identity in a new era of automation. With AgentsAI, you're not just building bots; you're crafting autonomous entities that engage, interact, and generate value. Create, launch, and watch as your AI agent thrives in the market, all with zero coding and maximum impact. This is the future of AI-powered digital personalities — effortless, accessible, and ready to take on the world.

Introducing AgentsAI's Token Launcher: a seamless path to bringing your AI agent ideas to life and beyond. Create your own AI agent, train it by simply chatting, and with a few clicks, launch its token to establish a digital identity in a new era of automation. With AgentsAI, you're not just building bots; you're crafting autonomous entities that engage, interact, and generate value. Create, launch, and watch as your AI agent thrives in the market, all with zero coding and maximum impact. This is the future of AI-powered digital personalities — effortless, accessible, and ready to take on the world.

AgentsAI

119,896 views • 1 year ago