Log inSign up
mem0
731 posts
mem0 profile banner
@mem0ai

mem0

@mem0ai
Memory Layer for your AI agents. Open source: github.com/mem0ai/mem0
San Francisco
mem0.ai/?utm_source=tw…
Joined June 2023
30
Following
19.9K
Followers
RepliesRepliesRepostsRepostsMediaMediaArticlesArticles

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
  • Pinned
    @mem0ai
    mem0
    @mem0ai
    Apr 16
    Article cover image
    Article
    How We Built the Token-Efficient Memory Algorithm
    New @mem0ai memory algorithm hits competitive accuracy across LoCoMo, LongMemEval, and BEAM at <7,000 tokens/query (≈3–4x fewer tokens), while most systems run at 25,000+. Fully open source. We...
    22
  • @mem0ai
    mem0
    @mem0ai
    Aug 27
    Article cover image
    Article
    State of Memory in RL Environments
    Reinforcement learning is how the labs now train coding agents. The environment is a sandbox with tools, and the reward is something a machine can check without a human in the loop: the tests pass,...
    7
  • @mem0ai
    mem0
    @mem0ai
    Aug 25
    Your @NousResearch Hermes agent has a 2,200-character memory. Its notes live inside the instructions it loads at session start, so the space never grows. Hit the cap and the next thing it learns gets rejected - to remember something new, it has to delete something it already
    Image
    00:00
    15
  • @mem0ai
    mem0
    @mem0ai
    Aug 17
    Thanks for the deep dive into Mem0's architecture by @_alejandroao! 🧠
    @_alejandroao
    Alejandro AO 🤗
    @_alejandroao
    Aug 17
    I took Mem0 apart to understand how AI agent memory really works. 0:00 Introduction 0:55 What is agent memory 4:26 Persistent memory stores 8:06 LLM-based ingestion 15:30 Semantic + BM25 retrieval 19:19 Entity boosting 25:38 Local open models A practical architecture deep dive
    Image
    00:00
    1
  • @mem0ai
    mem0
    @mem0ai
    Aug 14
    Context Corner 2.0 is here! 🍽️🤖 Loved the first conversation on context, memory, and agents? We’re back for round two, with even more time around the table and an incredible lunch to match! If you're a developer building, experimenting, or stuck on the frontlines of AI memory
    Image
    Context Corner: A Lunch Series for Developers · Luma
    From luma.com
    1
Advertisement
Advertisement