Remembering you is useful. Deciding who can read it matters just as much. Thank you @Laloba_002 for this careful look at Nourva Mind: you choose which apps can read or save your memory, and you can see, fix, export or delete it anytime. Launching this week.
teapawt.net/Laloba_002/status/2122…
recently, i've found myself looking beyond how intelligent an ai is.
i'm paying more attention to its memory and, more importantly, the privacy surrounding that memory.
i really like that developers are taking the memory layer of AI agents to the next level.
but have you ever thought about this?
ai memory solves one problem but opens up a new challenge
you know how frustrating it is to explain your work, preferences and ongoing projects every time you switch ai tools.
you want an assistant to remember what you were working on yesterday, what you discussed with a client and where you stopped.
you want that context to follow you.
this is where shared memory infrastructure and protocols like the model context protocol (mcp) become something to understand
mcp allows ai applications to connect with external tools, data sources and services.
it makes it easier for different ai tools to access context and continue work across applications.
but the other side of the matter - the infrastructure issues
portability doesn't guarantee privacy.
when personal context moves between applications, we need to understand where that information passes through, who can access it, how it's stored and what happens after another application receives it.
this is one of the challenges worth examining in ai infrastructure.
and it's part of what made me interested in @nourvaai.
nourva mind is building a memory layer that allows your context to travel across different ai tools through mcp.
nourva doesn't stop at remembering.
you can decide which connected applications can read your memory, which can save information, and withdraw their access when you want.
you can also inspect, correct, export and delete what it remembers.
there are still important privacy questions to examine.
nourva's privacy policy states that its cloud memory uses AES-256-GCM encryption at rest, but its encryption keys are held by its servers.
to buttress more, when nourva stores your memories on its cloud servers, it encrypts them so that someone who gets hold of the stored data cannot easily read them.
it also explains that once a connected application receives your memory, that application's own privacy policy and retention practices apply.
nourva gives users control over which connected applications can access their memory, but that does not determine how those applications handle the information afterwards.
nourva.ai/policy
this is very important.
as we're moving towards a world where ai tools won't just need to be intelligent.
they'll need to share context without making users lose control of their personal information.
that's one part of ai memory i want to explore with @nourvaai.
remembering your context is useful. knowing who gets access to it is just as important.
Your ideas. Your memory. Your world.
Well said, @TheChainVanta.
teapawt.net/TheChainVanta/status/2…
VANTA PRIME retweeted
GM Everyone
Your ideas deserve more than a blank page. @nourvaai remembers how you work, drafts what you need, and keeps up with you across every chat✨
#AI #ContentCreators #Productivity"
GM Everyone
Your ideas deserve more than a blank page. @nourvaai remembers how you work, drafts what you need, and keeps up with you across every chat✨
#AI #ContentCreators #Productivity"
VANTA PRIME retweeted
Replying to @nourvaai
VANTA PRIME retweeted
I just started using @nourvaai, and it's like having a personal intelligence that actually remembers me and gets things done. Chat, writing, translation, live web search, all in one place.
The world adapts to you.
#Nourva #AI #PersonalAI #Productivity #TechTwitter
VANTA PRIME retweeted
3 DAYS UNTIL @solana BREAKPOINT LONDON! 💜
After weeks of counting down, planning, stressing and preparing for this moment… it’s FINALLY happening!
My first international trip. My first crypto conference. And soon, I’ll finally meet people I’ve known online for YEARS.
Next stop: LONDON!
LET’S GOOOOOO! 💜
I just started using @nourvaai, and it's like having a personal intelligence that actually remembers me and gets things done. Chat, writing, translation, live web search, all in one place.
The world adapts to you.
#Nourva #AI #PersonalAI #Productivity #TechTwitter
Nobody talks about this part of using AI in Web3.
Meanwhile, the ones quietly winning are using AI to:
• Find undervalued protocols before they trend
• Write better research threads in minutes
• Automate wallet tracking & alpha alerts
#Ai #Tech #CryptoMarket
VANTA PRIME retweeted
Vitalik is already thinking about the next 10 yearsAI agents will be the primary users of blockchains.
That single shift changes everything Wallets will need to support autonomous agents→Smart contracts will talk to models,not just people→Value will flow between machines 24/7
Vitalik: AI Will Become the New UI
On October 6, 2026, Ethereum co-founder Vitalik Buterin @VitalikButerin said at OKX NOW @okx in Singapore that AI will become the new user interface in more and more scenarios. He shared how a local AI agent wrote a script to update his ENS hash in about five minutes, and said performing complex blockchain operations without a traditional UI will become normal.
This could reduce security risks associated with traditional frontends, while introducing new challenges such as prompt injection, AI safety, and whether agents correctly understand onchain operations.
Vitalik is already thinking about the next 10 yearsAI agents will be the primary users of blockchains.
That single shift changes everything Wallets will need to support autonomous agents→Smart contracts will talk to models,not just people→Value will flow between machines 24/7
Vitalik: AI Will Become the New UI
On October 6, 2026, Ethereum co-founder Vitalik Buterin @VitalikButerin said at OKX NOW @okx in Singapore that AI will become the new user interface in more and more scenarios. He shared how a local AI agent wrote a script to update his ENS hash in about five minutes, and said performing complex blockchain operations without a traditional UI will become normal.
This could reduce security risks associated with traditional frontends, while introducing new challenges such as prompt injection, AI safety, and whether agents correctly understand onchain operations.





