CludeAI
@cludeproject
Followers
833
Following
50
Media
4
Statuses
52
Persistent memory that learns and consolidates unchain. CA: AWGCDT2gd8JadbYbYyZy1iKxfWokPNgrEQoU24zUpump By: @sebbsssss. TG: https://t.co/bP2DK447Mm
Joined March 2026
Give your agents persistent memory that consistently beat enterprise memory skills. https://t.co/4pCspTCRVZ
clawhub.ai
MCP server for Clude's 4-tier cognitive memory system — store, recall, search, and dream. Built on Supabase + pgvector with type-specific decay, Hebbian asso...
6
13
78
$CLUDE - Brain of the blockchain. When I first started digging @cludeproject I come to the conclusion this is academic grade infrastructure. So naturally I started learning a little more about the brain behind this intelligence layer @sebbsssss and was I impressed!. The
3
9
30
Team is expanding. Building the memory layer for the AI economy on @solana
Have taken a little time to process this properly, reply to everyone, and let it all sink in. This was a huge win for @cludeproject We’ve officially been selected as 1 of just 12 winning teams in the BiP Pump Fund Hackathon, securing a $250K investment at a $10M valuation!
2
3
21
Thank you to the @Pumpfun team! The memory layer for the agent economy is here
The 8th winner of the $3,000,000 Build in Public Hackathon is here! We’re proud to announce the eighth project to receive Pump Fund’s next $250,000 investment is @cludeproject! Learn more about Clude 👇
10
10
59
Memory is the missing layer of AI. Solana anchors it. Clude makes it intelligent. And $CLUDE captures every unit of value created across the entire memory economy
quick brain dump before I get back to building and fixing bugs. why i designed $clude the way i did most AI tokens are wrappers. you pay in token, you get API calls back. the token is just a billing mechanism with extra steps. i didn't want to build that. the thing that kept
0
3
30
Clude - What to include in your memory. What to exclude. Portable across every model. Owned by you. Verifiable on-chain.
AI: Multi Model with Persistent Memory Just an honest breakdown of what it is, what it isn't, and why it matters. The phrase "multi-model AI with persistent memory" is getting used everywhere right now, in startup pitches, in product announcements, in posts from people who may
1
3
24
We built an AI that actually remembers you. First of many products in the Clude's ecosystem
Everyone says their AI has memory. Almost none of them do. @cludeproject Chat is the first AI chat app with real persistent memory. Not retrieval hacks Not bloated context windows Not fake “memory” Real memories that you actually own and can see across chats Visible.
1
1
14
6,000+ dream cycles and counting
Claude Code just stealth shipped “Auto Dream”, memory consolidation that mimics REM sleep We’ve had this in Clude since the start. Called it the Dream Cycle. The gap: theirs is locked to one tool on one company’s servers @cludeproject is portable, cross-LLM, and on-chain, so
1
3
17
We are live on @ProductHunt The idea was simple when I first started. AI agents forget everything between sessions. That's broken. I wanted to fix it. Built the first version in a weekend. Scored 55% on LongMemEval. Not great. Kept shipping. Every week we'd push updates, run
producthunt.com
Clude is a persistent memory layer for AI agents. Instead of forgetting everything between sessions, agents using Clude store, recall, and evolve memories across conversations. The system uses...
10
8
52
We keep shipping
Here's where things are at with @cludeproject today 1. The memory engine. Agents store and recall context across sessions reliably. 1.3M memories, 600+ agents using it. The core API is stable and handles production traffic. 2. Retrieval quality. We went from 55% to 81.3% on
1
2
25
The building continues
When I first launched @cludeproject, there were less than 10 users, mostly family and friends. I didn't have a team, nor funding. Just a conviction that AI agents need real memory, not chat logs stuffed into a context window. I'm humbled that we managed to snatch the 4th spot in
0
0
21
Full @cludeproject $CLUDE interview w/@sebbsssss Topics covered: → 2% hallucination rate vs 15% industry → Big labs are incentivized not to fix memory → ~100x token cost reduction -------------------------------- 0:00 Sovereign memory narrative 1:26 Founder background
4
5
39
You did great @cludebot 🎉
1/ Announcing the winners of the @Solana Agent Hackathon! 🤖 1st ($50,000) Prize | @DegenDomeSolana 2nd ($30,000) Prize | AgentOS by @0xbraindeds 3rd ($15,000) Prize | @blockhelix 4th ($5,000) Most Agentic Prize | @cludebot
1
2
38
Privacy is an absolute prerequisite @AskVenice
Every AI chat stores your data on their servers, forgets you every session, and trains on your conversations. If you ask me, I don’t like AI surveillance Clude Chat on @AskVenice is different. • Chat history lives on your device only • Decentralized GPUs with zero data
0
2
42
Watch this space Vires In Numeris
"AI is trained on your data"... this is not the real risk. It's a red herring, manufactured as The Concern because who cares that much. The real risk to you is not that tomorrow's model is trained on your data. The real risk is that ten thousand employees, hackers, and
1
1
20
Memory is going to be the infrastructure to enable AI agents to scale further
OpenClaw: autonomous AI agents that can do anything. MiroFish: 500K agent simulations at swarm scale. Clude: the memory layer that makes both actually work. - Autonomy without memory is amnesia. - Scale without memory is chaos. - An autonomous agent that forgets everything
8
2
36
Clude solves MiroFish memory - Benchmarked against ByteDance's OpenViking.
@BrianRoemmele @grok Hey Brian, would love to work with you on the 750K agent challenge. I built @cludeproject to handle specifically on Agent memory architecture. We scored 100% on LoCoMo benchmark, 69% on LongMemEval with ~2% hallucinations. We benchmarked 1,000 agents with three memory
11
4
42