The GitHub Wanxing team (MemOS) that makes memory bases for DeepSeek Harness, Hermes, OpenClaw and other agents
I really want to brag about this new project that has just been open sourced. Probably one of the most worth installing local AI infrastructure this year, It solves a pain point problem that I have endured using AI Agent for more than half a year: Changing an AI tool requires re-explaining the project background, technology selection, and pitfalls.
This AI just turned deepseek V4 flash into a vision-powered agent
It sees, reasons, and takes action.
用Three.js做一个北京天坛的动画： GLM-5.3-Flash直接拉完了。
DeepSeek-V4-Flash-0813就跟闹着玩的似得。 GPT-5.6-Sol还是碾压局。 模型一次性生成，不依赖外部Harness完成。
$NVDA vs $CBRS JensenHuang jimcramer
$spy $iwm $gld $uso $spcx $tsla $amd $intc Cerebras does not “sidestep expensive memory.” That line is the lie. They sidestep HBM and CoWoS. That is a supply-chain fact. It is not a memory miracle. WSE-3 has 44 GB of on-chip SRAM. Frontier
You have reached the end of the archive
All of deepseek