Builder story
Deploy by Suize: How an Agent Ships a Walrus Website End to End
Suize is an agent-first publishing service: one MCP tool call and one gasless payment turn a static build folder into a live, verified Walrus website.
Builder story
Suize is an agent-first publishing service: one MCP tool call and one gasless payment turn a static build folder into a live, verified Walrus website.
No single database model answers every question about agent data. Match each kind to the store built for it, and give durable memory its own layer.
Announcement
Blockticity is extending more than 1 million authenticated trade records, representing over $7.7 billion in real-world assets, onto Walrus, strengthening the verifiability of evidence supporting global trade
Agent memory
Context engineering is the design and management of information a model sees at runtime, including instructions, state, tools, retrieval, and recalled memory.
Agent memory
AI agents learn from past interactions by storing what happened and retrieving it later, not by retraining the model after every conversation.
Agent memory
AI agents store long-term memory in an external system that saves selected information outside the model, then retrieves it into the context window when it's relevant.
Agent memory
AI agents lose memory between sessions because LLM calls are stateless, where each request is processed on its own with no record of the ones before it.
Tutorial
Claude Code remembers your project, but only on one machine. Walrus Memory makes agent memory portable across Codex, Cursor, and your own agents.
Announcement
The Walrus Verifiable Trading Standard (WVTS) is the foundation agentic trading has lacked: an open standard for trading records AI agents can verify.
Analysis
What AI agent memory is, why memory debt compounds, and how a portable memory layer keeps agents from starting at zero.
Announcement
IPFS builders can now store data on Walrus Protocol directly from Lighthouse – verifiable, high-performance storage with no migration or rewrite.
Product update
Carry context across apps and sessions, coordinate across agents, and own your memory. Walrus Memory plugs into AI platforms, frameworks, and your stack.
Product update
Walrus moves to predictable USD pricing: $0.023/GB/mo for verifiable, decentralized storage. Paid in WAL, with cloud-level reliability built in.
Tutorial
iWalrusSDK is a community-built Swift SDK that saves developer time by giving them a native path to upload, download, and cache data on Walrus.
Product update
A new Walrus Memory plugin gives NemoClaw and OpenClaw agents portable, verifiable memory across runs, teams, and environments.
Tutorial
Walrus is a decentralized blob storage protocol built on the Sui blockchain. If you're a Python developer, walrus-python gives you a native SDK to store, retrieve, and manage data on Walrus, no blockchain experience required. This tutorial walks you through the full SDK: setting up a client,
Announcement
Tatum, a leading blockchain infrastructure provider, is making 11TB of historical blockchain datasets instantly accessible to builders and AI agents on Walrus.
Tutorial
A step-by-step guide to using Dartus, the native Dart and Flutter SDK for Walrus. Upload, retrieve, and manage blobs without dropping into raw HTTP.
News
How Walrus grew in 2025 — Mainnet, new features, and the beta launch of Walrus Memory for AI agents.