#端侧

Where does your AI keep everything you’ve told it? The 2am stuff. The passwords you typed while an agent was running. Your browsing history. Right now the answer is “on a server somewhere.” Agents are finally good enough to actually run your errands, and the price is that your whole life goes with them. We didn’t love that trade. So we built a computer your agents can live on, at home. Otto is a little box that sits on your desk. The agents are already on it when it arrives. You plug it in, tap your phone to it, and that’s the whole setup! Everything they read, type and remember stays in your house. - Agents set up before it ships, nothing to install
- 2,000+ apps with one tap, passwords stay on the box
- Thinks on the box, uses the cloud only if you tell it to
- Check in and approve things from your phone, anywhere.

materia release 1.0.0: blood panel in, cited supplement and herb options out. every claim traceable to a source, withheld when the citation doesn't hold. 100% open weights on CPU: @OpenBMB MiniCPM5-2B for chat and reranking, MiniCPM-OCR-1.0 for lab-report OCR, llama.cpp, SQLite BM25, a deterministic safety screen. Not a diagnosis, not a prescription. Local, no cloud, 100% private. github.com/RegeneratusLabs/ma…

What if your devices, apps and agents knew what you wanted? You finish breakfast, and your Uber is booked. Running late, your agent sends a “Running late” text. You reach home, and your lights turn on. AI is proactive now. But it still needs your yes. It waits, for you to unlock your phone, open an app and tap approve. Every time, hundreds of times a day. AI needs its own interface. Aina is a ring with a screen that predicts and shows you the three things you’ll need next. One flick of your thumb, and it’s done. For everything. ✦ Cues: proactive suggestions, ready before you need them ✦ Voice: talk to your agents, take notes, dictate ✦ Remote: control your music, Mac and TV ✦ Calls: right from your hand Pre-orders open now aina.com

手机本地大模型＋ESP32：我做了个热量摄入提醒器 本期做了一个开源小项目：用手机拍一下正在吃的，本地大模型识别食物并估算热量，再用一块 ESP32 小屏幕同步显示每日摄入进度。 方案明细： 手机 App：本地部署 MiniCPM-V-4.7-35B-A3B，在手机本地完成图片理解 热量估算：列出识别到的食物，分别估算热量并展示合计 ESP32 屏幕：同步 App 中的今日数据，直观显示每日摄入进度 圆环提示：用绿色、黄色和红色区分当前热量摄入状态 磁吸装置：可以吸在冰箱门上，也能放在咖啡机旁或零食区附近
 热量数值为模型估算，适合日常记录与摄入提醒。 项目已开源至 esp32-intake仓库：github.com/emwstudio/esp32-in… #esp32 #MiniCPM #端侧AI #AI硬件 #创客 @OpenBMB @modelbest_ai

Congrats to @OpenBMB on MiniCPM-OCR! Now in Nativ 🎉 OCR 1.0 (1.3B) reads the page in Nativ. Jev (2B), its fact-checker, runs on your Mac too and flags the lines worth a second look. On an M5 Max in full BF16: 🧾 an invoice read in 0.38 s 📄 a packed full page in under 3 s 🎯 each read checked in about 63 ms Still retyping totals off scanned invoices? Drop the page in and it's text before you've found the first number, and the scan never leaves your Mac. Download for macOS 💻 runnativ.ai Github repo 🛠 github.com/Blaizzy/nativ

Tested voice cloning with Ming-3.0-tts-0.5B by @AntLingAGI and it is even more insane. For a model of this size, voice cloning happens really well, i tested my own voice, half drunk, in a room full of noise (fan noise mostly) and it instantly cloned it. It needed just a 5-second sample of my voice, and it speaks faster than real time: about 4 seconds of speech in 2–3 seconds. All running locally on my RTX 3090. Ming takes about 3.3 GB of VRAM, and the whole model is under 3 GB on disk. Great time for Local AI.