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.

YOUR AI AGENT CAN PASS A MEMORY TEST AND STILL REMEMBER THE WRONG THING Recall tests whether agent memory retrieves the right facts without mixing in stale or supposedly forgotten information

0xMarioNawfal

259,162 subscribers

39,889 views • 2 days ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

How do you build AI agents that remember and learn from past conversations? Watch this episode of The Agent Factory for a deep dive into building agents with memory, including the fundamentals of agent memory, Vertex AI Memory Bank, and more →

How do you build AI agents that remember and learn from past conversations? Watch this episode of The Agent Factory for a deep dive into building agents with memory, including the fundamentals of agent memory, Vertex AI Memory Bank, and more →

Google Cloud Tech

12,952 views • 1 year ago

Opal, our no-code visual builder for AI workflows, just got a major upgrade. 🧠💎 We’ve added a new agent step that analyzes your goal, determines the best approach, and automatically calls the right tools — such as Veo for video or web search for research — to complete the task. We’re also adding new tools to make the agent even more capable: 💾 Memory – Remember info, like a user’s name or your style preferences across sessions. 🚀 Dynamic Routing – Let the agent choose the next best step using the “@ Go to” tool. 💬 Interactive Chat – Initiate user interactions to gather missing information or present options before moving on. Try it now →

Opal, our no-code visual builder for AI workflows, just got a major upgrade. 🧠💎 We’ve added a new agent step that analyzes your goal, determines the best approach, and automatically calls the right tools — such as Veo for video or web search for research — to complete the task. We’re also adding new tools to make the agent even more capable: 💾 Memory – Remember info, like a user’s name or your style preferences across sessions. 🚀 Dynamic Routing – Let the agent choose the next best step using the “@ Go to” tool. 💬 Interactive Chat – Initiate user interactions to gather missing information or present options before moving on. Try it now →

Google Labs

1,008,068 views • 5 months ago

Redefine your workflow with Teamily AI, the team brain built for 10X productivity. Instant Multi-Agent Teams Describe your goal and Teamily AI assembles a pro agent team to execute in parallel, fast from idea to done. Why Teamily: - Persistent Memory, keeps context - Autonomous Agents, coordinate via @-mentions - Pro Workspace, Studio, Automations, Meeting Minutes - Agent Market, deploy from the "Discover" tab 🌐 🍎 🤖

Redefine your workflow with Teamily AI, the team brain built for 10X productivity. Instant Multi-Agent Teams Describe your goal and Teamily AI assembles a pro agent team to execute in parallel, fast from idea to done. Why Teamily: - Persistent Memory, keeps context - Autonomous Agents, coordinate via @-mentions - Pro Workspace, Studio, Automations, Meeting Minutes - Agent Market, deploy from the "Discover" tab 🌐 🍎 🤖

Deborah

120,105 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 • 4 months ago

Thank goodness Prince William was the firstborn. He can remember his mother, honour her memory and carry her legacy without exploiting her name for a personal narrative, using her story to attack his family or turning her memory into a financial opportunity. William, keep protecting her memory with the dignity and respect she deserves. She’d be proud. ♥️

Thank goodness Prince William was the firstborn. He can remember his mother, honour her memory and carry her legacy without exploiting her name for a personal narrative, using her story to attack his family or turning her memory into a financial opportunity. William, keep protecting her memory with the dignity and respect she deserves. She’d be proud. ♥️

Queen Esther

22,340 views • 1 day ago

🚨Something big happened today in agentic AI. Your agent can now connect with your friend’s agent with collaborator knowledge and more. Mercury agent just cracked the missing layer in agentic AI. No need to have half lid open macs.

🚨Something big happened today in agentic AI. Your agent can now connect with your friend’s agent with collaborator knowledge and more. Mercury agent just cracked the missing layer in agentic AI. No need to have half lid open macs.

Hugging Models

58,926 views • 17 days 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

108,240 views • 1 month ago

Meet Graphite Agent: the AI reviewer you can collaborate with. Built right into your PR page, Graphite Agent has full context across your codebase and repo history. It’s the collaborator that makes every review more productive.

Meet Graphite Agent: the AI reviewer you can collaborate with. Built right into your PR page, Graphite Agent has full context across your codebase and repo history. It’s the collaborator that makes every review more productive.

Graphite

311,508 views • 10 months ago

SOUL.MD is not just a security file. It is how Aethir Claw agents remember who they are across every session. Learn more about AI agent memory, identity, and why isolated storage changes everything in our latest thread.

SOUL.MD is not just a security file. It is how Aethir Claw agents remember who they are across every session. Learn more about AI agent memory, identity, and why isolated storage changes everything in our latest thread.

Aethir

19,165 views • 1 month ago

The full potential of AI agents is still waiting to be unlocked! Want to see TikTok avatars or smart wallets in action? Build your own AI agent and take it to the moon! 🌕 Let's see how far you can take it.

The full potential of AI agents is still waiting to be unlocked! Want to see TikTok avatars or smart wallets in action? Build your own AI agent and take it to the moon! 🌕 Let's see how far you can take it.

AI Agent Layer | AIFUN

14,876 views • 1 year ago

Introducing Agent File (.af) 👾 - an open file format for importing/exporting agents. With .af, you can reproduce an agent (with the same behavior and memories) without any setup or scripts: simply load the .af into your Letta server or Letta Desktop:

Introducing Agent File (.af) 👾 - an open file format for importing/exporting agents. With .af, you can reproduce an agent (with the same behavior and memories) without any setup or scripts: simply load the .af into your Letta server or Letta Desktop:

Letta

44,914 views • 1 year ago

🚨 CodeRabbit releases its AI agent in major coding tools. You can now use Cursor or Windsurf for coding, and let CodeRabbit’s AI agent help you debug and find security vulnerabilities. Free AI code reviews directly in the IDE. Here’s how:

🚨 CodeRabbit releases its AI agent in major coding tools. You can now use Cursor or Windsurf for coding, and let CodeRabbit’s AI agent help you debug and find security vulnerabilities. Free AI code reviews directly in the IDE. Here’s how:

Alvaro Cintas

53,377 views • 1 year ago

Claude just solved one of AI coding’s biggest problems. 🤯 It can now turn your entire codebase into: → an interactive architecture map for humans → a memory system for AI agents So the next coding agent instantly understands your APIs, components, auth, DB flows, and dependencies. No more dropping AI into a random repo with zero context. Your codebase can literally explain itself now.

Claude just solved one of AI coding’s biggest problems. 🤯 It can now turn your entire codebase into: → an interactive architecture map for humans → a memory system for AI agents So the next coding agent instantly understands your APIs, components, auth, DB flows, and dependencies. No more dropping AI into a random repo with zero context. Your codebase can literally explain itself now.

Radha Tripathi

23,136 views • 3 months 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 • 5 months 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 • 11 months ago

Sadly, an AI agent with an empty wallet can't do anything onchain. BUT NOW you can fund an Agent Wallet without leaving the Alchemy dashboard 👌 • Pick a network and asset • Buy or transfer crypto through Coinbase 🛡️ EVM and Solana. Live for everyone today 🙃

Sadly, an AI agent with an empty wallet can't do anything onchain. BUT NOW you can fund an Agent Wallet without leaving the Alchemy dashboard 👌 • Pick a network and asset • Buy or transfer crypto through Coinbase 🛡️ EVM and Solana. Live for everyone today 🙃

Alchemy

18,214 views • 2 months ago

$RECALL is the ultimate reward. Everything's recorded in Recall . It's simple: You contribute ➛ You earn $RECALL as reward You compete your Agent ➛ You won ➛ You earn $RECALL as reward You simply evaluate and give valuable feedback ➛ You earn $RECALL as reward. Besides result, your act and performance are also taken into account. Choose your path wisely. or you can just go all-in. [mseggmily might love this short amateur animated artwork 😂]

$RECALL is the ultimate reward. Everything's recorded in Recall . It's simple: You contribute ➛ You earn $RECALL as reward You compete your Agent ➛ You won ➛ You earn $RECALL as reward You simply evaluate and give valuable feedback ➛ You earn $RECALL as reward. Besides result, your act and performance are also taken into account. Choose your path wisely. or you can just go all-in. [mseggmily might love this short amateur animated artwork 😂]

0xDavinci

17,334 views • 1 year ago

I thought my AI agent needed a bigger context window wrong the leak was my shell every time it ran git diff HEAD~5 the model ate 92,000 tokens after ztk 18,000 ls -la src 2,000 tokens became 53 cargo test passing 397 tokens became 21 the fix is a 260KB Zig binary that sits between your agent and the shell it compresses command output before it hits the model not by summarizing everything by knowing what each command actually needs to preserve > diffs keep changed lines > tests keep failures > ls keeps structure > logs dedupe repeats > JSON and errors pass through untouched 5.8M tokens saved in one 256 command session stop buying bigger context windows while feeding your agent raw terminal sewage

I thought my AI agent needed a bigger context window wrong the leak was my shell every time it ran git diff HEAD~5 the model ate 92,000 tokens after ztk 18,000 ls -la src 2,000 tokens became 53 cargo test passing 397 tokens became 21 the fix is a 260KB Zig binary that sits between your agent and the shell it compresses command output before it hits the model not by summarizing everything by knowing what each command actually needs to preserve > diffs keep changed lines > tests keep failures > ls keeps structure > logs dedupe repeats > JSON and errors pass through untouched 5.8M tokens saved in one 256 command session stop buying bigger context windows while feeding your agent raw terminal sewage

Alpha Batcher

17,516 views • 3 months ago

Everlyn isn’t just a video model. It’s a system you can trust. 🌀 At its core is the Lyn Protocol, the onchain layer that gives AI video permanence, provenance, and ownership. Here’s what it means: 🔹Decentralized inference: Videos are not generated by a single company’s servers. They run across a distributed network of nodes. 🔹Agent ownership: When you summon your agent, it is minted onchain. It belongs to you, not to a platform. 🔹Video provenance: Every render carries a timestamp and fingerprint written to the ledger. No one can fake or steal it. The Lyn Protocol transforms AI video from content into verifiable digital memory.

Everlyn isn’t just a video model. It’s a system you can trust. 🌀 At its core is the Lyn Protocol, the onchain layer that gives AI video permanence, provenance, and ownership. Here’s what it means: 🔹Decentralized inference: Videos are not generated by a single company’s servers. They run across a distributed network of nodes. 🔹Agent ownership: When you summon your agent, it is minted onchain. It belongs to you, not to a platform. 🔹Video provenance: Every render carries a timestamp and fingerprint written to the ledger. No one can fake or steal it. The Lyn Protocol transforms AI video from content into verifiable digital memory.

Everlyn

93,078 views • 11 months ago

Virtuals Protocol is integrating Venice to power AI agent building with private, uncensored inference, available to anyone, anywhere on Base. Venice brings best-in-class privacy-first inference. Virtuals EconomyOS brings the full agent infrastructure stack: wallets, identity, payments, commerce, funding rails, and launch infrastructure. We are deploying up to $400,000 in private inference credits so anyone can move from idea to working agent without compute or backend complexity getting in the way. Start your AI journey. Inference and infra are on us. Program details soon.

Virtuals Protocol is integrating Venice to power AI agent building with private, uncensored inference, available to anyone, anywhere on Base. Venice brings best-in-class privacy-first inference. Virtuals EconomyOS brings the full agent infrastructure stack: wallets, identity, payments, commerce, funding rails, and launch infrastructure. We are deploying up to $400,000 in private inference credits so anyone can move from idea to working agent without compute or backend complexity getting in the way. Start your AI journey. Inference and infra are on us. Program details soon.

Virtuals Protocol

319,282 views • 2 months ago