MemOS

@MemOS_dev

🧠 Memory Operating System for AI Agents 🌟 Our Repo: github.com/MemTensor/MemOS

𝐂𝐲𝐛𝐞𝐫 & 𝐅𝐚𝐛𝐥𝐞

memos.openmem.net

Replies Reposts Media Articles

Pinned
MemOS
@MemOS_dev
Jul 21
Hey guys it's been a while cuz we are having a cozy experiment But thing's going a little bit too far… We accidentally give a onigiri long-term memory To make up for it we had to give this onigiri 30M tokens just to successfully se porta bonita 🍙 NOW we need somebody to adopt
00:00
2
MemOS
@MemOS_dev
Aug 17
🐳 @deepseek_ai Harness says: Everything is a Plugin. We took that literally. Memory is now one too. MemOS Local Plugin connects to a DSH profile through Cordis—no fork and no changes to DSH core. When DSH runs a task, it can retrieve context that matters instead of starting
1
MemOS
@MemOS_dev
Aug 7
🎊 EXTRA EXTRA: MemTensor Named to MVP30! Founder Park put us on MVP30 of 2026 list for our work on AI infra & long-term memory. Once Agents live in your workflow, finishing one task isn't enough. They must remember — and pick up exactly where they left off 🦾
MemOS
@MemOS_dev
Aug 4
A successful trajectory ≠ A successful skill LLM agent's long-horizon runs may contain good decisions, failed attempts, retries, details that may only work in one environment, and save all of it when done. Looks messy, and getting messier next time. MSCE (Memory-Skill
1
MemOS
@MemOS_dev
Aug 4
Huge thx for Adina for sharing our work 🤗 Memory should be native to foundation models. And that's why we release Metis to help move native memory research forward 🏃🏻‍➡️ Feel free to check it out 👀
Adina Yakup
@AdinaYakup
Jul 31
Metis🚀 Memory Foundation Model released by Memtensor Research Group Probably the first LLM that internalizes memory into its backbone👀 - 4B/9B/27B weights + code + paper - No external RAG: memory is inside the model - One forward pass = full read/write - Weights frozen at