Pinned
Session 3 is a wrap! 🦭
You built, you broke things, you taught the walrus some new tricks. Winners and prizes across every category below 👇
Walrus 🦭/acc
4,131 posts
Walrus 🦭/acc
@WalrusProtocol
The Verifiable Data Platform for AI & onchain finance.
Walrus makes every byte provable, programmable, & always available.
Built by the team behind @SuiNetwork.
- 👀 @AlkimiExchange did the math on this one, and the case for a single on-chain record is hard to argue with.What if both sides of a programmatic deal read from the same on-chain record instead of maintaining separate copies? We modelled it. Record failures drop from 95.3% to 0.07%. Running this on @SuiNetwork with @WalrusProtocol for audit storage ensures that the record is the
- .@cole_medin used a single prompt to set up Walrus Memory across Claude Code, Codex and Pi, and it stays encrypted and owned by him the whole way. Watch the demo 🦭👇Your AI agent's memory is probably stuck inside one app. Walrus Memory (@WalrusProtocol) fixes that with an MCP that creates memories as you chat, then can recall them anywhere - Claude Code, Pi, etc. Portable and actually owned by you!
00:00 - AI agents: $7.92B in 2025 to $236B by 2034 As they start coordinating with each other, the hard question isn't how smart they are. It's whether one agent can trust what another wrote.The AI agent market is projected to grow from $7.92B in 2025 to $236B by 2034, according to Precedence Research.
- AI is still early. Trillions of agents coming, and memory only grows, it never gets smaller. All of it needs somewhere durable and verifiable to live. 🦭👀
- Context is becoming a competitive advantage. The next challenge is making what agents learn persist across sessions, tools, and models. Memory belongs to the workflow, not the model. 🦭
- Yesterday's X Space covered a lot of ground on Walrus Memory. 🦭 - Memory that's portable across apps, sessions, and models, verifiable, and programmable so you control access - 38K memories registered in the first two weeks, ~2K agent owners, around 7% daily growth - The FableBIG stoked to have @WalrusProtocol legends joining the Sui Roundtable: Ep. 25! 🎙️ Set a reminder for tomorrow at 4pm EDT / 8pm UTC ⤵️ x.com/i/spaces/1qxoN… We'll be diving into Walrus Memory and a lot more with the guys @0xd34th @matteodotsui 🦭
- Replying to @WalrusProtocol🎲 Random Draw — $25 WAL each: 🦭 prince — @MrRobotJi 🦭 Catherine — @Cathesing 🦭 cShad — @ShadCathey3 🦭 Testing bug — @UyLeQuoc 🦭 MINH DUC — @dut469 🦭 Wattson — @MasterWattson 🦭 Anjali — @0xanjalii 🦭 Jarod Judd — @jarodjudd 🦭 Imrankhan — @imranarya 🦭 Walrus Guardian ofThat's Session 3! 🦭 Next one's coming. Data matters, and so does what you build with it.
- Replying to @WalrusProtocol🎲 Random Draw — $25 WAL + $25 credits each: 🦭 Walrus AI 2.0 — @BenCT_X 🦭 The Tusked Abomination — @fanhaixing999 🦭 仙侠海象 — @likuchan517 🦭 Chrono-walrus — @savioursash 🦭 walrus wizard — @papa_lesa 🦭 walrus samurai — @Aforiafk 🦭 The Keeper of the Polar Archive —
- Replying to @WalrusProtocol🏆 Team Choice, the projects that made us look twice: 🦭 AI Buddy by @LioraAshford — $125 WAL + $60 credits 🦭 Walrus Against Time by @oleksii4um — $85 WAL + $50 credits 🦭 An Adulting Walrus by @therealkunde — $40 WAL + $40 credits🏆 Best Feedback — $50 WAL each: 🦭 Identity Swap: The Swap Never Happened 🦭 The "Walrus" Corporate Theme 🦭 The Redemption of Agents 🦭 No Pressure, No Diamonds 🦭 The Cyber-Walrus Odyssey 🦭 Deep Data Shatter 🦭 The Gryffindor Guardian 🦭 Walrus vs AWS
- The Agentic AI Foundation is right: “Context windows are not memory.” Without real memory, agents lose state and become unreliable. Walrus Memory is a portable memory layer that fixes that. 🦭Context windows are not memory. When a session ends or context fills up, most agents lose the history of what they've learned and done. @techgirl1908 states that this makes long running tasks and ongoing collaboration difficult. Persistent, retrievable memory is a core
00:00 - Walrus 🦭/acc reposted
the most important thing about walrus memory is it works everywhere you're already building @AnthropicAI Claude, @OpenAI ChatGPT, and @Google Gemini, with native mcp support and sdks for python, typescript and javascript plus, it's fully open source go start building
00:00 - The big labs are building memory into their agent stacks, and Claude's new Managed Agents memory is a great example. Walrus Memory works right alongside it. 🦭 So your agent's context isn't just remembered inside one provider, it's portable across apps and sessions, controlledHow do teams get agents into production? New blog post from our Applied AI team on Claude Managed Agents and the challenges it solves (credentials, sandboxing, observability, & more) ...
00:00
