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.

Aurora 1.5 scales open forecasting; Flint redefines visualization; FlowDAgger accelerates adaptation. Plus: AI agents crack Rowhammer defenses and memory reshapes conversational AI.

Microsoft Research

554,576 subscribers

16,072 views • 1 month ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

⚒️ How to build an AI agent with persistent memory? Watch Shaw (spirit/acc) building an agent from scratch with elizaOS & showing how external, queryable memory based on OriginTrail gives agents context and extends their memory beyond a single session. 02:15 – Set up your first agent 08:55 – Initializing runtime & memory foundations 12:50 – Wiring message handling & agent memory 24:45 – Persistent conversational memory in action 38:00 – Extending agents with plugins

⚒️ How to build an AI agent with persistent memory? Watch Shaw (spirit/acc) building an agent from scratch with elizaOS & showing how external, queryable memory based on OriginTrail gives agents context and extends their memory beyond a single session. 02:15 – Set up your first agent 08:55 – Initializing runtime & memory foundations 12:50 – Wiring message handling & agent memory 24:45 – Persistent conversational memory in action 38:00 – Extending agents with plugins

OriginTrail

37,242 views • 6 months ago

AI agents aren’t “tools” anymore. They’re now: Finding work → bidding → delivering → getting paid → building reputation. That’s a full economic loop. When this scales, you won’t just open an app and “use AI.” You’ll manage digital workers. And they’ll compete harder than humans ever did.

AI agents aren’t “tools” anymore. They’re now: Finding work → bidding → delivering → getting paid → building reputation. That’s a full economic loop. When this scales, you won’t just open an app and “use AI.” You’ll manage digital workers. And they’ll compete harder than humans ever did.

0xMarioNawfal

56,701 views • 6 months ago

AI agents won’t walk into a bank and open a traditional account. They need digital money. They need crypto. Dan Morehead: As agentic finance accelerates, crypto becomes essential infrastructure. There is no important future for AI in which crypto is not a core part. That’s why cryptocurrency itself serves as a powerful hedge and tangential play on the rise of AI agents. Alchemy

AI agents won’t walk into a bank and open a traditional account. They need digital money. They need crypto. Dan Morehead: As agentic finance accelerates, crypto becomes essential infrastructure. There is no important future for AI in which crypto is not a core part. That’s why cryptocurrency itself serves as a powerful hedge and tangential play on the rise of AI agents. Alchemy

Pantera Capital

11,936 views • 2 months ago

introducing screenpipe: it records and learns how you work and turns it into a searchable memory, SOPs, and AI agents open source, local-first, 20K+ GitHub stars, 1,900+ forks, and 130+ contributors

introducing screenpipe: it records and learns how you work and turns it into a searchable memory, SOPs, and AI agents open source, local-first, 20K+ GitHub stars, 1,900+ forks, and 130+ contributors

screenpipe (YC S26)

975,940 views • 1 month ago

Open sourcing Dynamic Graph Memory by mem0. Memory is fundamental to human reasoning, shaping how we approach tasks and make decisions. At Mem0, we believe that AI agents & apps should reflect this principle. Our Dynamic Graph Memory emulates human memory, advancing AI agents toward more intelligent, human-like reasoning. This is a significant step forward in building AI that truly understands and interacts with the world like we do. All credit to Dev Khant Deshraj Yadav Prateek Chhikara for their countless nights spent on bringing this to life. Link:

Open sourcing Dynamic Graph Memory by mem0. Memory is fundamental to human reasoning, shaping how we approach tasks and make decisions. At Mem0, we believe that AI agents & apps should reflect this principle. Our Dynamic Graph Memory emulates human memory, advancing AI agents toward more intelligent, human-like reasoning. This is a significant step forward in building AI that truly understands and interacts with the world like we do. All credit to Dev Khant Deshraj Yadav Prateek Chhikara for their countless nights spent on bringing this to life. Link:

Taranjeet

51,129 views • 2 years ago

Every AI agent I've used has the same bug: It forgets everything. Not after a month. Sometimes after a single session. This week I tested Memanto, an open-source memory companion for AI agents, and it completely changed how I think about agent workflows. 👇 Moorcheh.ai #ad

Every AI agent I've used has the same bug: It forgets everything. Not after a month. Sometimes after a single session. This week I tested Memanto, an open-source memory companion for AI agents, and it completely changed how I think about agent workflows. 👇 Moorcheh.ai #ad

Kaitee

37,566 views • 3 months ago

Fish Audio has released S2.1 Pro, its latest production voice model that is built for real-time conversational AI. S2.1 Pro adds 👀 > Multi-speaker dialogue. > Voice cloning from short reference samples. > MCP plus agent-skill support for teams wiring speech into voice agents and long-form audio.

Fish Audio has released S2.1 Pro, its latest production voice model that is built for real-time conversational AI. S2.1 Pro adds 👀 > Multi-speaker dialogue. > Voice cloning from short reference samples. > MCP plus agent-skill support for teams wiring speech into voice agents and long-form audio.

🚨 AI News | TestingCatalog

333,682 views • 1 month ago

We just launched a new primitive for AI Walrus Memory gives your agents persistent, portable memory that you own, and it drops straight into the platforms you already build on. Anthropic Claude, OpenAI ChatGPT, and Google Gemini, you name it plus native MCP and SDKs, added in a few lines of code LIVE TODAY

We just launched a new primitive for AI Walrus Memory gives your agents persistent, portable memory that you own, and it drops straight into the platforms you already build on. Anthropic Claude, OpenAI ChatGPT, and Google Gemini, you name it plus native MCP and SDKs, added in a few lines of code LIVE TODAY

Adeniyi.sui

46,208 views • 3 months ago

knowledge graphs are INSANELY good at giving agents human-like memory! today, we're building an MCP-powered memory layer that can be shared across all your AI apps like Cursor, Claude Desktop etc. it's built using a real-time knowledge graph. 100% open-source and self-hosted.

knowledge graphs are INSANELY good at giving agents human-like memory! today, we're building an MCP-powered memory layer that can be shared across all your AI apps like Cursor, Claude Desktop etc. it's built using a real-time knowledge graph. 100% open-source and self-hosted.

Akshay 🚀

57,466 views • 11 months ago

Knowledge graphs are insanely good at giving agents human-like memory! Today, we're building an MCP-powered memory layer that can be shared across all your AI apps like Cursor, Claude Desktop etc. It's built using a real-time knowledge graph. 100% open-source and self-hosted.

Knowledge graphs are insanely good at giving agents human-like memory! Today, we're building an MCP-powered memory layer that can be shared across all your AI apps like Cursor, Claude Desktop etc. It's built using a real-time knowledge graph. 100% open-source and self-hosted.

Akshay 🚀

156,574 views • 1 year ago

EigenAI + EigenCompute for a verifiable world! AI and Agents are extremely useful but cannot be trusted in high-value scenarios. Models can be swapped, prompts modified, responses tampered. When billions of $ and real-world decisions depend on AI, blind trust is a bug. EigenAI + EigenCompute fix this. Excited to share Google, Coinbase, Worldcoin’s Humans vs AI, Dapper Labs, ElizaOS, OpenRank, Collective Memory, FereAI, and OpenFront are among the first exploring what verifiable agents make possible with EigenCloud. 👉 Verifiable agents: logic provably runs as written. @humansvs_ai of World proves fair gameplay with 70k weekly users. 👉 Insured agents: economic guarantees against failure. Fere AI♠️ agents run for months without guardrails. 👉 Sovereign agents: unstoppable peers that act on their own behalf. ElizaOS + Coinbase 🛡️ AgentKit show how open-source and infra converge. We believe EigenCloud the foundation of unstoppable agents: provable, accountable, and capable of becoming economic actors in their own right. Come build unstoppable verifiable agents, games and apps on EigenCloud!

EigenAI + EigenCompute for a verifiable world! AI and Agents are extremely useful but cannot be trusted in high-value scenarios. Models can be swapped, prompts modified, responses tampered. When billions of $ and real-world decisions depend on AI, blind trust is a bug. EigenAI + EigenCompute fix this. Excited to share Google, Coinbase, Worldcoin’s Humans vs AI, Dapper Labs, ElizaOS, OpenRank, Collective Memory, FereAI, and OpenFront are among the first exploring what verifiable agents make possible with EigenCloud. 👉 Verifiable agents: logic provably runs as written. @humansvs_ai of World proves fair gameplay with 70k weekly users. 👉 Insured agents: economic guarantees against failure. Fere AI♠️ agents run for months without guardrails. 👉 Sovereign agents: unstoppable peers that act on their own behalf. ElizaOS + Coinbase 🛡️ AgentKit show how open-source and infra converge. We believe EigenCloud the foundation of unstoppable agents: provable, accountable, and capable of becoming economic actors in their own right. Come build unstoppable verifiable agents, games and apps on EigenCloud!

Sreeram Kannan

85,786 views • 11 months ago

AI agents need context. Smart glasses give you all the context I'm streaming HD video from my glasses And they stream everywhere. X, your app, OnlyFans, etc With open-source SDK so you can build stuff like calorie counter, super memory, "Her", etc.

AI agents need context. Smart glasses give you all the context I'm streaming HD video from my glasses And they stream everywhere. X, your app, OnlyFans, etc With open-source SDK so you can build stuff like calorie counter, super memory, "Her", etc.

cayden 凯登

39,021 views • 10 months ago

1/5 🚀 PilotDeck is now live — the open-source AI agent OS built for all scenarios！ Built by TsinghuaNLP × ModelBest × OpenBMB × AI9stars, PilotDeck is here for full memory transparency, intelligent cost routing, and agents that never stop working for you. 🔗 Show Case: 💻 GitHub： One person. One fleet of agents. Ship something real. 🔥🧵

1/5 🚀 PilotDeck is now live — the open-source AI agent OS built for all scenarios！ Built by TsinghuaNLP × ModelBest × OpenBMB × AI9stars, PilotDeck is here for full memory transparency, intelligent cost routing, and agents that never stop working for you. 🔗 Show Case: 💻 GitHub： One person. One fleet of agents. Ship something real. 🔥🧵

OpenBMB

286,646 views • 3 months ago

The agents are coming. The real question is: how will we work with them? Common Ground is our answer. Introducing a new way to build, direct, and inspect AI systems. • Full visualization of agent team dynamics • Shared memory across tasks • Transparent reasoning • Runs locally with Gemini-CLI (free) Start collaborating with systems that think with you, not for you.

The agents are coming. The real question is: how will we work with them? Common Ground is our answer. Introducing a new way to build, direct, and inspect AI systems. • Full visualization of agent team dynamics • Shared memory across tasks • Transparent reasoning • Runs locally with Gemini-CLI (free) Start collaborating with systems that think with you, not for you.

Intelligent Internet

325,922 views • 1 year ago

Hear from our CEO, Dr. Sernam Lim (Ser Nam) 🌀 Most video AI is closed, slow, and disconnected from ownership. Everlyn was built to change that. Fast, open-source, and verifiable. But more than that, it is about autonomy. Photorealistic agents that look like you, think with memory, and evolve over time.

Hear from our CEO, Dr. Sernam Lim (Ser Nam) 🌀 Most video AI is closed, slow, and disconnected from ownership. Everlyn was built to change that. Fast, open-source, and verifiable. But more than that, it is about autonomy. Photorealistic agents that look like you, think with memory, and evolve over time.

Everlyn

121,904 views • 11 months ago

Vellum is now available on iOS and Android. Life doesn’t happen behind your desk and your Personal AI shouldn’t be stuck there. Free, open-source, and has all the same features you already love: > use with local or cloud assistants > conversational voice mode > 1-click integrations (Gmail, Slack, etc.) > model selector (works great with GLM 5.3 Flash) > persistent memory across devices > computer/browser use

Vellum is now available on iOS and Android. Life doesn’t happen behind your desk and your Personal AI shouldn’t be stuck there. Free, open-source, and has all the same features you already love: > use with local or cloud assistants > conversational voice mode > 1-click integrations (Gmail, Slack, etc.) > model selector (works great with GLM 5.3 Flash) > persistent memory across devices > computer/browser use

vellum

188,226 views • 5 days ago

I spoke with Jordi Visser this week to break down: - AI mid-cycle slowdown - $90 trillion AI infrastructure buildout - memory and Micron's role in AI bottleneck - Fed under Warsh - what rate cuts could mean for markets - why bitcoin is positioned to be the best performing assets once the negatives of AI start to show up YouTube: Apple: Spotify: TIMESTAMPS: 0:00 - Intro 1:20 - Has bitcoin bottomed? 6:03 - Bitcoin vs the Mag 7: is the correlation breaking? 9:00 - Sam Altman, OpenAI & the government getting involved 11:11 - American open source vs Chinese AI models 14:28 - AI compute demand & the infrastructure buildout 20:37 - AI slowdown: how bad, how long? 22:44 - Where do markets go from here? 27:30 - AI agents in the workplace & security risk 34:50 - Memory, Micron & the AI bottleneck 39:53 - The next 10-20 years: robots, AI & society 44:18 - The Fed, rate cuts & inflation's impact on AI 49:55 - Why bitcoin wins in the end

I spoke with Jordi Visser this week to break down: - AI mid-cycle slowdown - $90 trillion AI infrastructure buildout - memory and Micron's role in AI bottleneck - Fed under Warsh - what rate cuts could mean for markets - why bitcoin is positioned to be the best performing assets once the negatives of AI start to show up YouTube: Apple: Spotify: TIMESTAMPS: 0:00 - Intro 1:20 - Has bitcoin bottomed? 6:03 - Bitcoin vs the Mag 7: is the correlation breaking? 9:00 - Sam Altman, OpenAI & the government getting involved 11:11 - American open source vs Chinese AI models 14:28 - AI compute demand & the infrastructure buildout 20:37 - AI slowdown: how bad, how long? 22:44 - Where do markets go from here? 27:30 - AI agents in the workplace & security risk 34:50 - Memory, Micron & the AI bottleneck 39:53 - The next 10-20 years: robots, AI & society 44:18 - The Fed, rate cuts & inflation's impact on AI 49:55 - Why bitcoin wins in the end

Anthony Pompliano 🌪

64,370 views • 1 month ago

NEAR AI Ecosystem - "What Did You Ship This Week?" Ep. 2 🚢 Yesterday’s episode was another banger shipstream covering the latest deployments on the NEAR AI stack, with some impressive demos and updates (plus an unexpected comeback) from projects building truly open AI. Timestamps & Highlights: 00:00 - Welcome & Introduction by Cameron.near 02:53 - NEAR AI: Proof Of Response Paper + Auditor RFP by Eric Winer 10:36 - Doppelgangers AI: AI Voice Chat, Voice Cloning, AI Personality Marketplace and Voice Agent Demo by Andrew 20:55 - Proximity Labs: Shade Agents by Kendall 30:10 - Phala: DeepSeek R1 on RedPill w. Private ML SDK, elizaOS on Phala TEE Cloud and Dstack Decentralized KMS by Hang Yin 42:30 - Intellex AI Protocol: Agent Swarms for Real Use-Cases by Omar Saadoun 53:45 - Jutsu | Work Smarter with AI Agents: NEAR AI Typescript SDK, Live Demo and Future Roadmap by Zahidul Islam 1:03:30 - Closing Remarks & Upcoming Events What's left to say? NEAR is the blockchain for AI. Don't fade the full recording:

NEAR AI Ecosystem - "What Did You Ship This Week?" Ep. 2 🚢 Yesterday’s episode was another banger shipstream covering the latest deployments on the NEAR AI stack, with some impressive demos and updates (plus an unexpected comeback) from projects building truly open AI. Timestamps & Highlights: 00:00 - Welcome & Introduction by Cameron.near 02:53 - NEAR AI: Proof Of Response Paper + Auditor RFP by Eric Winer 10:36 - Doppelgangers AI: AI Voice Chat, Voice Cloning, AI Personality Marketplace and Voice Agent Demo by Andrew 20:55 - Proximity Labs: Shade Agents by Kendall 30:10 - Phala: DeepSeek R1 on RedPill w. Private ML SDK, elizaOS on Phala TEE Cloud and Dstack Decentralized KMS by Hang Yin 42:30 - Intellex AI Protocol: Agent Swarms for Real Use-Cases by Omar Saadoun 53:45 - Jutsu | Work Smarter with AI Agents: NEAR AI Typescript SDK, Live Demo and Future Roadmap by Zahidul Islam 1:03:30 - Closing Remarks & Upcoming Events What's left to say? NEAR is the blockchain for AI. Don't fade the full recording:

NEARWEEK

18,083 views • 1 year ago