quote: “If I switch products, I have to start over. If I use three agents, each rebuilds from scratch what the others already know." — @duncan Great article in @radar, written by @duncan. That exact problem, context trapped inside vendor silos, is why Walrus Memory was built. A portable memory layer sits under your control, letting agents request permissioned access to recall and update context across runtimes. Switch models, keep the state. Read the quickstart: walrus.xyz/memory | Every agent I use is building a model of me. @claudeai has learned how I like my prose. @ChatGPT remembers what I'm working on. I don't mind this, but if I switch products, I have to start over. If I use three agents, each rebuilds from scratch what the others already know. Everything an agent learns lives with its vendor. It doesn't need to be this way. What if every person had a canonical, user-controlled repository of context that any agent could request permission to use? It's not a unique idea, of course. Lots of geeks have started down this road by pointing agents at a pile of Markdown files, and the best-known recent example is probably @karpathy LLM Wiki — elegant not just as a design but as a document: You give the description to your agent, and the agent builds a version tailored to you. I’ve been using a pile of Markdown files in a folder for a year, and it’s taught me five things a personal context system has to get right — and led me to a bigger question: where should that context live? I've written about both on O'Reilly Radar: https://t.co/YYzLJHhhkK

quote: “If I switch products, I have to start over. If I use three agents, each rebuilds from scratch what the others already know." — @duncan Great article in @radar, written by @duncan. That exact problem, context trapped inside vendor silos, is why Walrus Memory was built. A portable memory layer sits under your control, letting agents request permissioned access to recall and update context across runtimes. Switch models, keep the state. Read the quickstart: walrus.xyz/memory | Every agent I use is building a model of me. @claudeai has learned how I like my prose. @ChatGPT remembers what I'm working on. I don't mind this, but if I switch products, I have to start over. If I use three agents, each rebuilds from scratch what the others already know. Everything an agent learns lives with its vendor. It doesn't need to be this way. What if every person had a canonical, user-controlled repository of context that any agent could request permission to use? It's not a unique idea, of course. Lots of geeks have started down this road by pointing agents at a pile of Markdown files, and the best-known recent example is probably @karpathy LLM Wiki — elegant not just as a design but as a document: You give the description to your agent, and the agent builds a version tailored to you. I’ve been using a pile of Markdown files in a folder for a year, and it’s taught me five things a personal context system has to get right — and led me to a bigger question: where should that context live? I've written about both on O'Reilly Radar: https://t.co/YYzLJHhhkK

Source:https://x.com/WalrusProtocol/status/2087633973317140821