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.

Our CSO Advait (∇, ∇) on encrypted, user-owned memory for Al agents. Your data shouldn't be harvested and resold without consent. We're building a system where memory is encrypted by default, permissioned by design, and owned by the user.

OpenGradient (∇, ∇)

160,875 subscribers

170,911 views • 3 months ago •via X (Twitter)

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

Here’s a demo of our Agentic Memory system, inspired by how our own brain holds information in a 3D spatial space. This feels, natural. Extending this further, we announced the Agentic Memory Protocol on July 15th in SF - which enables memory to be local, encrypted and available to other agents and apps based on your permission-only. We believe this is the future of memory - not owned by any one app, spatial, and always improving. Aaron Levie Andrej Karpathy

Here’s a demo of our Agentic Memory system, inspired by how our own brain holds information in a 3D spatial space. This feels, natural. Extending this further, we announced the Agentic Memory Protocol on July 15th in SF - which enables memory to be local, encrypted and available to other agents and apps based on your permission-only. We believe this is the future of memory - not owned by any one app, spatial, and always improving. Aaron Levie Andrej Karpathy

Varun

187,489 views • 10 months ago

introducing for teams one click connections to all the apps, client-side encrypted, and builds your team's memory. finish your tasks by checking your support team's emails, pulling up user interviews done by William, and commits pushed by Lucas. onboarding teams rn at Momo

introducing for teams one click connections to all the apps, client-side encrypted, and builds your team's memory. finish your tasks by checking your support team's emails, pulling up user interviews done by William, and commits pushed by Lucas. onboarding teams rn at Momo

Cailyn Y.

139,867 views • 4 months ago

📢 CredMont on vana is LIVE ✳️ > Contribute and earn. > Private and encrypted 🔐 > Co-Own the future of financial Data. Start Contributing 🔗 Building World’s First and Largest, User-owned Credit Card txn Data Collective.

📢 CredMont on vana is LIVE ✳️ > Contribute and earn. > Private and encrypted 🔐 > Co-Own the future of financial Data. Start Contributing 🔗 Building World’s First and Largest, User-owned Credit Card txn Data Collective.

CredMont

35,461 views • 9 months ago

$Data encryption is now live on Veilnet. Available in @veilnet/mcp-server@0.3.0. Any blob — file, dataset, config, recovery codes, contract draft, research note, agent memory — can now be encrypted on your device, shipped to Veilnet as ciphertext, and fetched back later without the decryption key ever leaving your machine. Three new MCP tools are live: data_store({ label, data }) encrypt + store data on Veilnetdata_fetch({ id }) fetch + decrypt locallydata_list() list stored ids With labels kept encrypted, the flow is simple: user data → encrypted locally → ciphertext stored on Veilnet → key remains on user device → agent fetches when needed → local decryption onlyVeilnet sees encrypted blobs. Your AI agent gets persistent private memory and secure storage.The provider does not need the raw data. This works in Claude Code, Claude Desktop, Cursor, Continue, and Cline. Install: npm i -g @veilnet/mcp-server Bootstrap your key at: → Agent tab Then ask any MCP-aware agent:“store this encrypted on Veilnet.”Docs:docs.veilnet.toPrivate prompts protected what users ask. Private MCP protected what agents run. Wallet Context protected what agents read. Encrypted data storage now protects what agents remember and reuse. All powered by $VEILNET$

Data encryption is now live on Veilnet. Available in @veilnet/[email protected]. Any blob — file, dataset, config, recovery codes, contract draft, research note, agent memory — can now be encrypted on your device, shipped to Veilnet as ciphertext, and fetched back later without the decryption key ever leaving your machine. Three new MCP tools are live: data_store({ label, data }) encrypt + store data on Veilnetdata_fetch({ id }) fetch + decrypt locallydata_list() list stored ids With labels kept encrypted, the flow is simple: user data → encrypted locally → ciphertext stored on Veilnet → key remains on user device → agent fetches when needed → local decryption onlyVeilnet sees encrypted blobs. Your AI agent gets persistent private memory and secure storage.The provider does not need the raw data. This works in Claude Code, Claude Desktop, Cursor, Continue, and Cline. Install: npm i -g @veilnet/mcp-server Bootstrap your key at: → Agent tab Then ask any MCP-aware agent:“store this encrypted on Veilnet.”Docs:docs.veilnet.toPrivate prompts protected what users ask. Private MCP protected what agents run. Wallet Context protected what agents read. Encrypted data storage now protects what agents remember and reuse. All powered by $VEILNET

Veilnet

11,608 views • 13 days ago

User-owned AI: a world where AI is built for you. Works for you. And is owned by you. It's NEARer than you think.

User-owned AI: a world where AI is built for you. Works for you. And is owned by you. It's NEARer than you think.

NEAR Protocol

29,490 views • 1 year ago

SolRouter beta is live on devnet. SDK for developers. MCP support for agents. And our own agent framework with encrypted token research, multi-agent orchestration, and private inference on decentralized GPUs. Private AI infrastructure for Solana. <encrypted> by default.

SolRouter beta is live on devnet. SDK for developers. MCP support for agents. And our own agent framework with encrypted token research, multi-agent orchestration, and private inference on decentralized GPUs. Private AI infrastructure for Solana. <encrypted> by default.

SolRouter

37,673 views • 3 months ago

⏪ Missed the first session of Vana Vibes ⚡? 🎧 Chirper shares how they're building self-sovereign AI agents powered by Vana's user-owned data 👇

⏪ Missed the first session of Vana Vibes ⚡? 🎧 Chirper shares how they're building self-sovereign AI agents powered by Vana's user-owned data 👇

vana

13,280 views • 1 year ago

Illia presenting IronClaw at BUIDL Asia (April 16-17, 2026). "Think of IronClaw as iOS for agents - secure by default." From sandboxed execution and encrypted credential vaults to confidential inference and self-improving skills, IronClaw is building the secure operating system agents need. The future of private, sovereign AI agents is here.

Illia presenting IronClaw at BUIDL Asia (April 16-17, 2026). "Think of IronClaw as iOS for agents - secure by default." From sandboxed execution and encrypted credential vaults to confidential inference and self-improving skills, IronClaw is building the secure operating system agents need. The future of private, sovereign AI agents is here.

NEAR Legion

19,382 views • 27 days ago

Witness the birth of user-owned AI. In a world powered by Chain Abstraction. And reclaim your sovereignty. Cont...

Witness the birth of user-owned AI. In a world powered by Chain Abstraction. And reclaim your sovereignty. Cont...

NEAR Protocol

540,631 views • 2 years ago

User-Owned AI is how we democratize access and protect data privacy. Centralized AI? Your data trains it and you get zilch. Fork that. Choose NEAR. Built for users. Built for agents.

User-Owned AI is how we democratize access and protect data privacy. Centralized AI? Your data trains it and you get zilch. Fork that. Choose NEAR. Built for users. Built for agents.

NEAR Protocol

25,597 views • 10 months ago

User-owned AI. Powered by OpenGradient (∇, ∇). Coming soon...

User-owned AI. Powered by OpenGradient (∇, ∇). Coming soon...

OpenGradient (∇, ∇)

579,470 views • 1 year ago

The time for humans as the internet’s primary user is over. We are building software for AI agents. Introducing Ensue - the shared memory layer for agents.

The time for humans as the internet’s primary user is over. We are building software for AI agents. Introducing Ensue - the shared memory layer for agents.

ensue

84,083 views • 9 months ago

At Co-op, we’re run differently. We’re not owned by a wealthy few, we are owned by our members. And because we're owned by YOU, we can do right by YOU.

At Co-op, we’re run differently. We’re not owned by a wealthy few, we are owned by our members. And because we're owned by YOU, we can do right by YOU.

Co-op

174,331 views • 1 year ago

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

Andrew Ng

157,772 views • 2 months ago

Cycles Pay is the first privacy-preserving crypto payment app for businesses. This is possible because of few specific design choices: First, the private keys stay on your mobile device. User actions are cryptographically signed by your private key before being submitted on-chain. The financial data is encrypted with that key and doesn’t leave your mobile device. Second, Cycles Pay uses a shielded pool to hide account balances on-chain. They are tracked as encrypted commitments and no one can see the underlying amounts or participants. Third, when you make a payment, a ZK proof is generated and verified on-chain to confirm the transaction is valid without revealing the amount or the counterparty. Users get blockchain integrity without exposing the transaction details.

Cycles Pay is the first privacy-preserving crypto payment app for businesses. This is possible because of few specific design choices: First, the private keys stay on your mobile device. User actions are cryptographically signed by your private key before being submitted on-chain. The financial data is encrypted with that key and doesn’t leave your mobile device. Second, Cycles Pay uses a shielded pool to hide account balances on-chain. They are tracked as encrypted commitments and no one can see the underlying amounts or participants. Third, when you make a payment, a ZK proof is generated and verified on-chain to confirm the transaction is valid without revealing the amount or the counterparty. Users get blockchain integrity without exposing the transaction details.

Cycles

12,419 views • 21 days ago

New short course: Long-Term Agentic Memory with LangGraph. Learn to build an agent with long-term memory in this course developed in collaboration with taught by its Co-Founder and CEO, Harrison Chase! Personal assistance and productivity tasks have become important use cases for agents. An important feature of an AI assistant, such as a coding or calendar assistant, is its ability to keep improving over time from its experience. Agent memory is the key capability that enables this. To add memory to an agent, you must first figure out what to store and what to retrieve when it is time to use the information. Additionally, you’ll have to decide when to update the stored information. For example, you might update in each iteration loop of the agent or perform updates in the background, with a helper agent. In this course, you will learn a mental framework to build agents with long-term memory. You'll create a useful email assistant that can respond, ignore, and notify using writing, scheduling, and memory-management tools. You’ll develop your agent's memory by adding facts to its memory store, provide examples to learn the user's preferences, and optimize system prompts to evolve instructions based on previous responses. In detail, you’ll: - Learn how the three types of memory--semantic, episodic, and procedural–and the two update mechanisms–via hot path and in the background–apply to your agents. - Build an email agent with writing, scheduling, and availability tools, along with a router that triages incoming email and handles it accordingly by ignoring, responding, or notifying the user. - Add tools to your email agent that allow it to operate on semantic memory by learning facts about the user, storing them in a long-term memory store, and searching over them in future interactions. - Incorporate episodic memory, in the form of few-shot examples, in the triage step of your agents to help them learn and update user preferences. - Add procedural memory as system prompts, optimized with feedback to improve the instructions the agent follows. Learn how to approach memory in agents, and start building agents with long-term memory with LangGraph! Please sign up here:

New short course: Long-Term Agentic Memory with LangGraph. Learn to build an agent with long-term memory in this course developed in collaboration with taught by its Co-Founder and CEO, Harrison Chase! Personal assistance and productivity tasks have become important use cases for agents. An important feature of an AI assistant, such as a coding or calendar assistant, is its ability to keep improving over time from its experience. Agent memory is the key capability that enables this. To add memory to an agent, you must first figure out what to store and what to retrieve when it is time to use the information. Additionally, you’ll have to decide when to update the stored information. For example, you might update in each iteration loop of the agent or perform updates in the background, with a helper agent. In this course, you will learn a mental framework to build agents with long-term memory. You'll create a useful email assistant that can respond, ignore, and notify using writing, scheduling, and memory-management tools. You’ll develop your agent's memory by adding facts to its memory store, provide examples to learn the user's preferences, and optimize system prompts to evolve instructions based on previous responses. In detail, you’ll: - Learn how the three types of memory--semantic, episodic, and procedural–and the two update mechanisms–via hot path and in the background–apply to your agents. - Build an email agent with writing, scheduling, and availability tools, along with a router that triages incoming email and handles it accordingly by ignoring, responding, or notifying the user. - Add tools to your email agent that allow it to operate on semantic memory by learning facts about the user, storing them in a long-term memory store, and searching over them in future interactions. - Incorporate episodic memory, in the form of few-shot examples, in the triage step of your agents to help them learn and update user preferences. - Add procedural memory as system prompts, optimized with feedback to improve the instructions the agent follows. Learn how to approach memory in agents, and start building agents with long-term memory with LangGraph! Please sign up here:

Andrew Ng

131,640 views • 1 year ago

.Karoline Leavitt: "Under the terms of this deal, TikTok will be owned by a majority of American investors...Oracle will serve as TikTok's trusted security partner, and they will independently monitor the safety and data security of all U.S. user data on TikTok's platform."🇺🇸

.Karoline Leavitt: "Under the terms of this deal, TikTok will be owned by a majority of American investors...Oracle will serve as TikTok's trusted security partner, and they will independently monitor the safety and data security of all U.S. user data on TikTok's platform."🇺🇸

William Martin

52,121 views • 8 months ago

Meet Data Scout. It's a $500k data scientist for every employee. One of those agents every business needs. > Has Snowflake access (+ Notion, Slack, Github) > Runs deep analysis on all user and account data > Can be called by other agents for recurring reports Data Scout is one of the most used agents at Notion. And you can build one.

Meet Data Scout. It's a $500k data scientist for every employee. One of those agents every business needs. > Has Snowflake access (+ Notion, Slack, Github) > Runs deep analysis on all user and account data > Can be called by other agents for recurring reports Data Scout is one of the most used agents at Notion. And you can build one.

Hurley

33,218 views • 2 months ago

The #DeCC x Shielding Summit is in session!🛡️ COTI's CEPO Joshua Maddox joined the panel 'Building with Privacy by Design' 'As a user your should have control over your data to make choices on what you want to be transparent and what you want to be private' $COTI

The #DeCC x Shielding Summit is in session!🛡️ COTI's CEPO Joshua Maddox joined the panel 'Building with Privacy by Design' 'As a user your should have control over your data to make choices on what you want to be transparent and what you want to be private' $COTI

COTI Foundation

19,439 views • 1 year ago