Walrus 🦭/acc (@WalrusProtocol)
@WalrusProtocol
0 正在关注 0 粉丝
Your agent's memory shouldn't be tied to a single platform. If you can't take it with you, you don't really own it. Walrus Memory keeps memory portable and under your control, with access you define.
Claude Code's auto memory never leaves Claude Code. Open Codex and your agent starts from zero. Walrus Memory ties memory to your account, not the tool. Write it in Claude Code, recall it in Codex, Cursor, or your own SDK.
Two commands to install.
Here's how ↓
显示更多
There could be 100 AI agents for every person within a few years, and maybe a million each within ten.
@AlliumLabs talks about what that actually looks like, and why those agents are going to need verifiable data underneath them to function.
显示更多
2,000+ teams build on IPFS through @LighthouseWeb3, and now they can upgrade to Walrus without changing how they build.
Keep the same CIDs, gateways, and SDK, but gain high-performance retrieval and verifiable data availability.
Nothing to migrate. Nothing to rewrite.
显示更多
2,000+ teams build on IPFS through @LighthouseWeb3, and now they can upgrade to Walrus without changing how they build.
Keep the same CIDs, gateways, and SDK, but gain high-performance retrieval and verifiable data availability.
Nothing to migrate. Nothing to rewrite.
显示更多
Prompt history is not AI agent memory.
Walrus Memory gives agents a portable memory layer that persists beyond the context window.
Your AI agent’s memory shouldn’t be locked to one app, model, or runtime.
Walrus Memory gives agents portable memory across the tools and workflows they run in.
AI agents need memory they can carry, share, and trust. Walrus Memory is portable by design, fully under your control, and built for agent coordination across apps, sessions, and workflows.
Your AI agent’s memory shouldn’t be locked to one app, model, or runtime. Walrus Memory gives agents portable memory they can carry across sessions, tools, and workflows.
Walrus Memory plugs into the tools AI agent builders already use — with SDKs, MCP support, and integrations for existing workflows.
Your AI agent’s memory shouldn’t be locked to one app, model, or runtime. Walrus Memory gives agents portable memory they can carry across sessions, tools, and workflows.
Introducing: Walrus Memory. 🦭
A portable memory layer that lets your AI agents carry context across every app you run them in.
No more starting from zero.
No more being locked into one platform.…
显示更多
Today, we're going after one of AI's most important unsolved problems.
Introducing: Walrus Memory. 🦭
A portable memory layer that lets your AI agents carry context across every app you run them in.
No more starting from zero.
No more being locked into one platform.
Portable, verifiable, and fully under your control.
Take your agent's memory anywhere:
显示更多
🚨 ICYMI: @MyriadMarkets dropped IPFS and centralized storage and upgraded to Walrus. Every prediction market on their platform is now verifiable and tamper-proof.
5.2M onchain transactions. $10M+ weekly volume.
"We want every aspect of our infrastructure to be onchain… "
显示更多
"It represents a major step forward for our community." - @The_Shareio CEO Charles Bronstein
Creators can now monetize content stored on Walrus in seconds.
Decentralized, tamper-proof, ~80% lower transaction costs. The creator economy just got its data layer. 🦭
显示更多
If you’re running a DEX: How far back can your team reliably access historical market state? 🤔
If a liquidation is disputed 6 months later, can you reconstruct what happened without relying on a single RPC or indexer?
Most teams assume yes. It’s not always true.
显示更多
