Log inSign up
MemOS profile banner
user avatar

MemOS

@MemOS_dev
🧠 Memory Operating System for AI Agents 🌟 Our Repo: github.com/MemTensor/MemOS
π‚π²π›πžπ« & π…πšπ›π₯𝐞
memos.openmem.net
Joined December 2025
31
Following
381
Followers
RepliesArticlesMedia
  • Pinned
    user avatar
    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 πŸ™ NOW we need somebody to adopt
    Image
    00:00
  • user avatar
    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 β€” and pick up exactly where they left off 🦾
    Image
  • user avatar
    MemOS
    @MemOS_dev
    Aug 4
    A successful trajectory β‰  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
    Image
  • user avatar
    MemOS
    @MemOS_dev
    Aug 4
    Huge thx for Adina for sharing our work πŸ€— Memory should be native to foundation models. And that's why we release Metis to help move native memory research forward πŸƒπŸ»β€βž‘οΈ Feel free to check it out πŸ‘€
    user avatar
    Adina Yakup
    @AdinaYakup
    Jul 31
    MetisπŸš€ Memory Foundation Model released by Memtensor Research Group Probably the first LLM that internalizes memory into its backboneπŸ‘€ - 4B/9B/27B weights + code + paper - No external RAG: memory is inside the model - One forward pass = full read/write - Weights frozen at
    Image
  • user avatar
    MemOS
    @MemOS_dev
    Jul 31
    New paper's here: Metis β€” the 1st prototype of a memory foundation model. In Metis, the model weights remain fixed during inference. What changes instead is a persistent memory state. This state carries information across interactions, updates during the forward pass, and is
    Image