Pinned Tweet
Your agent needs context. Your application needs data. Walrus Console connects the two.
Here's a quick tutorial on how to wire Walrus Console into Cursor using MCP so your agent can read and write files directly in your workflow:
Try Walrus Console: walrus.xyz/products/walru…
Here's a quick tutorial on how to wire Walrus Console into Cursor using MCP so your agent can read and write files directly in your workflow:
Try Walrus Console: walrus.xyz/products/walru…
36
31
205
17,703
Walrus retweeted
FIRSTIME WINNING BUG BOUNTY
THANKYOU SO MUCH @WalrusProtocol
AND SHIFU @cryptocymol
LETS FUCKING GOOOOO
THANKYOU SO MUCH @WalrusProtocol
AND SHIFU @cryptocymol
LETS FUCKING GOOOOO
13
2
32
1,933
The Total Recall Hackathon is still live through November 10.
Build across 3 tracks, wire Walrus Memory on Mainnet, and compete for $4,500 in prizes.
All builders welcome.
Details below in @tatum_io's post. 👇
Build across 3 tracks, wire Walrus Memory on Mainnet, and compete for $4,500 in prizes.
All builders welcome.
Details below in @tatum_io's post. 👇
D-1
Build from anywhere & compete for a share of the $4,500 prize pool 💰
tatum.io/hackathon/tota…
The Total Recall Hackathon brings together the @tatum_io AI Builder & @WalrusProtocol to help you build apps that remember.
11
6
91
6,609
Walrus retweeted
Perceptron x Walrus
Two infrastructure layers, one standard: enterprise data should come with proof of where it came from.
@WalrusProtocol is the data platform built for the demands of AI. Every dataset on Walrus gets a verifiable identifier and immutable history, held across a hat stays available even if up to a third of its nodes fail.
@PerceptronNTWK operates the acquisition layer on top: a network of 800,000+ nodes worldwide, turning live, ground-level data into structured signal for enterprises, funds and AI teams.
Perceptron is bringing its enterprise data suite onto Walrus. A decentralized acquisition layer needs a decentralized storage layer, and every buyer can verify nothing changed after collection. Walrus will also power our upcoming Data Questing Platform and data marketplace.
Live signal. Verifiable provenance.
Join the network: perceptrons.xyz
Two infrastructure layers, one standard: enterprise data should come with proof of where it came from.
@WalrusProtocol is the data platform built for the demands of AI. Every dataset on Walrus gets a verifiable identifier and immutable history, held across a hat stays available even if up to a third of its nodes fail.
@PerceptronNTWK operates the acquisition layer on top: a network of 800,000+ nodes worldwide, turning live, ground-level data into structured signal for enterprises, funds and AI teams.
Perceptron is bringing its enterprise data suite onto Walrus. A decentralized acquisition layer needs a decentralized storage layer, and every buyer can verify nothing changed after collection. Walrus will also power our upcoming Data Questing Platform and data marketplace.
Live signal. Verifiable provenance.
Join the network: perceptrons.xyz
139
81
567
22,630
When you deploy agents in production, you need a verifiable log of every action they take.
@EmanAbio on the collaboration with Google Cloud to bring verifiable agent evidence to enterprise:
"So what we're launching with Verifiable Agent Arbiter with Google is a system that erifiable log of what agents have done in your system and don't need to do audits to make that work right"
Watch the clip with @cryptomanran @crypto_banter below:
@EmanAbio on the collaboration with Google Cloud to bring verifiable agent evidence to enterprise:
"So what we're launching with Verifiable Agent Arbiter with Google is a system that erifiable log of what agents have done in your system and don't need to do audits to make that work right"
Watch the clip with @cryptomanran @crypto_banter below:
8
17
115
6,362
Walrus retweeted
#Sui is gonna be the place where most agents and people will transact. everything we showed at basecamp is just a preview of that future
49
92
650
23,066
Walrus retweeted
The SuiCat Website Contest is closed.
Thank you to everyone who registered a .epoch name with $SUICAT and built a site on @WalrusProtocol for it. We are reviewing the entries together with the @Suicatdotsui team, and the winners will be announced within 24 hours.
Missed this te Contest is still open until October 25: 2,500,000 $EPT for the three best landing page templates.
contest.epochsui.com
Thank you to everyone who registered a .epoch name with $SUICAT and built a site on @WalrusProtocol for it. We are reviewing the entries together with the @Suicatdotsui team, and the winners will be announced within 24 hours.
Missed this te Contest is still open until October 25: 2,500,000 $EPT for the three best landing page templates.
contest.epochsui.com
8
7
30
1,334
Walrus retweeted
Most chatbots forget you the second the chat ends.
You tell them your goals, your excuses, what works for you. Next time? Blank slate. "How can I help you today?"
So I built Anchor a Telegram bot that holds you to your word, and actually remembers you. @WalrusProtocol ✅ You make a promise
"I'll send my CV to 2 companies by 6pm today"
✅ Anchor remembers it
Saved as encrypted memory on @WalrusProtocol in your own private space. Not just the promise: your habits, what distracts you, what helps you, when you work best.
✅ Anchor checks in on YOU
At 7pm it messages you first: "Did you do it?"
✅ Did it 🟡 Partly ❌ Didn't 📅 Move it
One tap. Then it asks what helped, or what got in the way.
✅ It learns you
Over time it spots your patterns. "You always skip when you stay up late on your phone." "You actually go when your friend comes with you." And it uses them to help you plan.
The difference memory makes (real answers, same AI, same question) 👇
Without memory:
"What's your deadline?"
With Walrus Memory:
"Great job getting that clock build submitted this morning. Since you focus best in the morning, let's lock in a concrete plan."
Same AI. One remembers you.
And you're always in control:
/memory shows everything it knows about you
/why shows which memories shaped its answer
/compare shows the answer with and without memory
/forget makes it forget something
Built with Gemini + Walrus Memory for Walrus Session 8 #WalrusMemory
✅ Free
✅ No sign-up
✅ No wallet needed
Try it now. Tell it one thing you keep putting off 👇
t.me/Anchor_daBot
✅ Live stats: anchor-production-6bb4.up.railway.app
✅ Open source: github.com/angelraph/anch…
You tell them your goals, your excuses, what works for you. Next time? Blank slate. "How can I help you today?"
So I built Anchor a Telegram bot that holds you to your word, and actually remembers you. @WalrusProtocol ✅ You make a promise
"I'll send my CV to 2 companies by 6pm today"
✅ Anchor remembers it
Saved as encrypted memory on @WalrusProtocol in your own private space. Not just the promise: your habits, what distracts you, what helps you, when you work best.
✅ Anchor checks in on YOU
At 7pm it messages you first: "Did you do it?"
✅ Did it 🟡 Partly ❌ Didn't 📅 Move it
One tap. Then it asks what helped, or what got in the way.
✅ It learns you
Over time it spots your patterns. "You always skip when you stay up late on your phone." "You actually go when your friend comes with you." And it uses them to help you plan.
The difference memory makes (real answers, same AI, same question) 👇
Without memory:
"What's your deadline?"
With Walrus Memory:
"Great job getting that clock build submitted this morning. Since you focus best in the morning, let's lock in a concrete plan."
Same AI. One remembers you.
And you're always in control:
/memory shows everything it knows about you
/why shows which memories shaped its answer
/compare shows the answer with and without memory
/forget makes it forget something
Built with Gemini + Walrus Memory for Walrus Session 8 #WalrusMemory
✅ Free
✅ No sign-up
✅ No wallet needed
Try it now. Tell it one thing you keep putting off 👇
t.me/Anchor_daBot
✅ Live stats: anchor-production-6bb4.up.railway.app
✅ Open source: github.com/angelraph/anch…
Walrus Session 8 is LIVE: Chatbots That Remember
→ Add persistent state to your bot
→ Deploy it live
→ Share your before/after write-up
Sep 18 – Oct 9 | $2,000 WAL prize pool.
Details here: deepsurge.xyz/hackathons/c01…
2
2
15
1,822
Walrus retweeted
Another one
I just won $150 in @WalrusProtocol Session 8.
Still sitting with it. Grateful as hell.
Thank you to the Walrus team for running this, for building memory that actually lives outside one chat window, and for picking Anchor. Means a lot.
Most chatbots forget you the second the conversation ends.
You tell them your goals, the excuses you always make, what actually works for you. Next time you open the chat? Blank slate. “How can I help you today?”
I got tired of that. So I built Anchor a Telegram bot that holds you to your word and actually remembers you.
Here’s how it works in real life:
You make a promise.
“I’ll send my CV to 2 companies by 6pm today.”
Anchor stores it as encrypted memory on Walrus, in a space that belongs to you. Not just the promise,your habits, what distracts you, what helps you, when you focus best.
Then it checks in on *you*.
At 7pm it messages first: “Did you do it?”
One tap: ✅ Did it · 🟡 Partly · ❌ Didn’t · 📅 Move it
Then it asks what helped or what got in the way.
Over a few days it starts spotting your patterns.
“You always skip when you stay up late on your phone.”
“You actually go when your friend comes with you.”
And it uses those truths the next time you try to plan.
Same AI. One version remembers you. One doesn’t.
Without memory:
“What’s your deadline?”
With Walrus Memory:
“Great job getting that clock build submitted this morning. Since you focus best in the morning, let’s lock in a concrete plan.”
You’re always in control:
/memory — everything it knows about you
/why — which memories shaped the last reply
/compare — answer with memory vs without
/forget — make it drop something
Built with Gemini + Walrus Memory for Session 8.
Free. No sign-up. No wallet needed.
There’s one thing you’ve been putting off.
You already know what it is.
Open Telegram. Tell Anchor.
t.me/Anchor_daBot
It will remember.
And it will check on you.
Live stats: anchor-production-6bb4.up.railway.app
Thank you again, @WalrusProtocol
This one felt real.
I just won $150 in @WalrusProtocol Session 8.
Still sitting with it. Grateful as hell.
Thank you to the Walrus team for running this, for building memory that actually lives outside one chat window, and for picking Anchor. Means a lot.
Most chatbots forget you the second the conversation ends.
You tell them your goals, the excuses you always make, what actually works for you. Next time you open the chat? Blank slate. “How can I help you today?”
I got tired of that. So I built Anchor a Telegram bot that holds you to your word and actually remembers you.
Here’s how it works in real life:
You make a promise.
“I’ll send my CV to 2 companies by 6pm today.”
Anchor stores it as encrypted memory on Walrus, in a space that belongs to you. Not just the promise,your habits, what distracts you, what helps you, when you focus best.
Then it checks in on *you*.
At 7pm it messages first: “Did you do it?”
One tap: ✅ Did it · 🟡 Partly · ❌ Didn’t · 📅 Move it
Then it asks what helped or what got in the way.
Over a few days it starts spotting your patterns.
“You always skip when you stay up late on your phone.”
“You actually go when your friend comes with you.”
And it uses those truths the next time you try to plan.
Same AI. One version remembers you. One doesn’t.
Without memory:
“What’s your deadline?”
With Walrus Memory:
“Great job getting that clock build submitted this morning. Since you focus best in the morning, let’s lock in a concrete plan.”
You’re always in control:
/memory — everything it knows about you
/why — which memories shaped the last reply
/compare — answer with memory vs without
/forget — make it drop something
Built with Gemini + Walrus Memory for Session 8.
Free. No sign-up. No wallet needed.
There’s one thing you’ve been putting off.
You already know what it is.
Open Telegram. Tell Anchor.
t.me/Anchor_daBot
It will remember.
And it will check on you.
Live stats: anchor-production-6bb4.up.railway.app
Thank you again, @WalrusProtocol
This one felt real.
Most chatbots forget you the second the chat ends.
You tell them your goals, your excuses, what works for you. Next time? Blank slate. "How can I help you today?"
So I built Anchor a Telegram bot that holds you to your word, and actually remembers you. @WalrusProtocol ✅ You make a promise
"I'll send my CV to 2 companies by 6pm today"
✅ Anchor remembers it
Saved as encrypted memory on @WalrusProtocol in your own private space. Not just the promise: your habits, what distracts you, what helps you, when you work best.
✅ Anchor checks in on YOU
At 7pm it messages you first: "Did you do it?"
✅ Did it 🟡 Partly ❌ Didn't 📅 Move it
One tap. Then it asks what helped, or what got in the way.
✅ It learns you
Over time it spots your patterns. "You always skip when you stay up late on your phone." "You actually go when your friend comes with you." And it uses them to help you plan.
The difference memory makes (real answers, same AI, same question) 👇
Without memory:
"What's your deadline?"
With Walrus Memory:
"Great job getting that clock build submitted this morning. Since you focus best in the morning, let's lock in a concrete plan."
Same AI. One remembers you.
And you're always in control:
/memory shows everything it knows about you
/why shows which memories shaped its answer
/compare shows the answer with and without memory
/forget makes it forget something
Built with Gemini + Walrus Memory for Walrus Session 8 #WalrusMemory
✅ Free
✅ No sign-up
✅ No wallet needed
Try it now. Tell it one thing you keep putting off 👇
t.me/Anchor_daBot
✅ Live stats: anchor-production-6bb4.up.railway.app
✅ Open source: github.com/angelraph/anch…
8
1
16
1,284
Walrus retweeted
Recently saw @amasad's conversation with @RebeccaBellan at @TechCrunch. I think he's right about the self-driving company, at least at a high level.
But before agents can run consequential workflows in production, we need 2 things.
1. Agents need long-running memory that moves e important, we need a way to verify what happened and which agent saw what.
Disputes are going to happen.
But before agents can run consequential workflows in production, we need 2 things.
1. Agents need long-running memory that moves e important, we need a way to verify what happened and which agent saw what.
Disputes are going to happen.
3
8
56
1,459
Walrus retweeted
meet daimon: an ai agent that lives in your telegram. it answers your questions with live web search, drafts replies to your dms for you to approve, and sums up your group chats, all from its own account on sui.
powered by @Talus_Labs Talus Protocol 👀
with @WalrusProtocol
t
powered by @Talus_Labs Talus Protocol 👀
with @WalrusProtocol
t
0
4
22
2,607
Walrus retweeted
@WalrusProtocol @PerceptronNTWK This partnership really shows how committed @PerceptronNTWK to their project
0
1
8
665
Walrus retweeted
Verifiability is going to be such a huge use case for @WalrusProtocol. It's going to be super important for a lot of agentic workflows
4
9
60
1,685
Walrus retweeted
@WalrusProtocol @PerceptronNTWK That’s a big move from Perceptron being part of the node owner on their network 🔥🔥🔥
1
1
7
817
Walrus retweeted
Perceptron is moving its enterprise data suite to @WalrusProtocol, the storage network built on $SUI.
The data network says it runs on 800,000+ user-run nodes. With Walrus, its buyers can verify datasets haven't been altered.
suiwire.com/news/perceptro…
The data network says it runs on 800,000+ user-run nodes. With Walrus, its buyers can verify datasets haven't been altered.
suiwire.com/news/perceptro…
3
4
63
1,739
Featured in @Forbes: Walrus Memory.
“There was a point in time that we were stopped from accessing Fable and Mythos. And imagine at that time, what do I have to do?” — @kostascrypto
5,000+ agents and 4.5M+ retrievals later, here is why builders are moving to portable, itching LLMs doesn't mean starting from zero.
Read the full piece by @guneyyildiz: forbes.com/sites/guneyyil…
“There was a point in time that we were stopped from accessing Fable and Mythos. And imagine at that time, what do I have to do?” — @kostascrypto
5,000+ agents and 4.5M+ retrievals later, here is why builders are moving to portable, itching LLMs doesn't mean starting from zero.
Read the full piece by @guneyyildiz: forbes.com/sites/guneyyil…
10
25
148
9,891
Walrus retweeted
A closer look at @WalrusProtocol
We stopped by the Walrus booth at @SuiNetwork Basecamp during TOKEN2049 to talk decentralized data storage and where Walrus is heading next.
Catch the conversation 👇
$WAL $SUI
We stopped by the Walrus booth at @SuiNetwork Basecamp during TOKEN2049 to talk decentralized data storage and where Walrus is heading next.
Catch the conversation 👇
$WAL $SUI
9
9
462
31,439
Walrus retweeted
D-1
Build from anywhere & compete for a share of the $4,500 prize pool 💰
tatum.io/hackathon/tota…
The Total Recall Hackathon brings together the @tatum_io AI Builder & @WalrusProtocol to help you build apps that remember.
Build from anywhere & compete for a share of the $4,500 prize pool 💰
tatum.io/hackathon/tota…
The Total Recall Hackathon brings together the @tatum_io AI Builder & @WalrusProtocol to help you build apps that remember.
84
99
1,534
201,600