Anthropic just introduced Cowork, an AI assistant that runs on your computer — but they can see your data ⚠️⚠️⚠️ We have a secure alternative: 🍫 Local Cocoa — a fully 💻on-device, 🌍open-source AI assistant that runs completely offline. Code: github.com/synvo-ai/Local…

Agents are mind-blowing. But they don't remember things consistently. Or when they do — it's not safe. We built Engram. AES-256 encrypted. Keys stay on your device. Zero-knowledge sync. No cloud. No middleman. Use it. Your agent memory is yours. lmms-lab

In the current agent stack, Memory is often conflated with Context Window. Engram treats memory as a persistent, encrypted layer rather than just extended tokens. It can also store your Claude Code/OpenCode configurations (including skills/agents...), and all the dev related

Introducing LMMs-Lab Writer: Think Deep, Write Easy 🤖 Built-in AI agent writes LaTeX for you ⚡ One-click LaTeX setup & auto package install 🔗 Git integration in sidebar, no paywall 🌏 Full CJK / Unicode support 🖥️ Local-first · Free · MIT licensed

✨Moving beyond static knowledge in Video Understanding! We are thrilled to unveil Demo-ICL🧠, a new framework that challenges current models to do more than just "remember"—we want them to learn from context. We introduce: 1️⃣ Demo-ICL-Bench📜: A massive, challenging

Can MLLMs learn from video demonstrations just like humans do? 🤔 Introducing 𝗗𝗲𝗺𝗼-𝗜𝗖𝗟: 𝗜𝗻-𝗖𝗼𝗻𝘁𝗲𝘅𝘁 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗳𝗼𝗿 𝗣𝗿𝗼𝗰𝗲𝗱𝘂𝗿𝗮𝗹 𝗩𝗶𝗱𝗲𝗼 𝗞𝗻𝗼𝘄𝗹𝗲𝗱𝗴𝗲 𝗔𝗰𝗾𝘂𝗶𝘀𝗶𝘁𝗶𝗼𝗻 Most video MLLMs rely on static internal knowledge. This work

x.com/i/article/2021…

Introducing Engram Teams — persistent memory for AI agent swarms. Agent Swarms are the hottest thing in AI right now. OpenAI shipped Swarm. Anthropic just launched Claude Code Agent Teams. Coordination problem? Solved. But these agents have NO MEMORY. They can't learn. They

Shuai Liu memory is the moat nobody's talking about

Swarms are goated. 2.5x faster on the first run is insane. Now imagine the second time you run a similar task: With