Log inSign up
supermemory
1,140 posts
user avatar
supermemory
@supermemory
The memory and context cloud for AI agents supermemory.ai
San Francisco, CA
git.new/memory
Joined May 2024
45
Following
25.9K
Followers
  • Pinned
    user avatar
    supermemory
    @supermemory
    Jun 10
    You can now run supermemory locally. Just one command - npx supermemory local Open source binary, available now - git.new/memory
    user avatar
    Dhravya Shah
    supermemory
    @DhravyaShah
    Jun 10
    You can now run @supermemory locally. Introducing the supermemory local - Fully self-contained. Comes with our graph engine, embedding model, etc. - Run on any machine, with your @openclaw, hermes, claude, etc. - SDKs to add memory to your agent, or build your company brain.
    00:00
    23K
  • user avatar
    supermemory
    @supermemory
    37m
    Quick explainer on SMFS and why we think agent memory has been measured wrong ↓ everyone optimizes for retrieval speed. but the real cost is how many lookups it takes to answer, often ten tool calls a question, each one burning tokens. SMFS goes after the count. it mounts your
    564
    user avatar
    supermemory
    @supermemory
    37m
    paper + benchmark, both public:
    smfs.ai
    Memory as a Filesystem | smfs research
    SMFS mounts a Supermemory container as a real, kernel-level filesystem with semantic search wired into path operations. Evaluated on xAFS: 53.8% fewer tokens, 53.1% lower cost per correct answer at...
    140
  • supermemory reposted
    user avatar
    Dhravya Shah
    supermemory
    @DhravyaShah
    16h
    Introducing the $100 max plan on @supermemory cloud - 7x limit from pro plan and 10x cheaper than self-hosting same amount of usage - Granola, Gmail and other connectors - Most API features enabled - Best for startups, internal team and heavy personal use!
    00:00
    52K
  • user avatar
    supermemory
    @supermemory
    17h
    supermemory now runs entirely on your own machine! npx supermemory local > full stack runs locally: graph engine, embeddings, fact extraction, user profiles > works with any model (openai, anthropic, gemini, groq) or fully offline via ollama > plugs into claude code, cursor,
    user avatar
    Dhravya Shah
    supermemory
    @DhravyaShah
    Jun 30
    it is INSANE to see the adoption for supermemory local. This is over one week. It already processes many BILLIONS of tokens. all running on our users machines - for free.
    22K
    user avatar
    supermemory
    @supermemory
    17h
    Start here:
    GitHub - supermemoryai/supermemory: Memory and context engine + app that is extremely fast,...
    From github.com
    938
  • user avatar
    supermemory
    @supermemory
    Jun 29
    Your agent only knows what you've uploaded. Docs change, emails land, commits ship, none of it reaches your agent. Connectors fix that. Plug in your sources once. Supermemory syncs the rest. How it works: → You authenticate once. Setup, extraction, and indexing run
    00:00
    2.1K
    user avatar
    supermemory
    @supermemory
    Jun 29
    →
    Connectors — Supermemory
    From supermemory.ai
    408
  • supermemory reposted
    user avatar
    Ishaan Gupta
    @_ishaanxgupta
    Jun 28
    The supermemory chat just got a serious upgrade. • Grok 4.3 alongside GPT, Claude & Gemini • Attach files & images • Thinking mode for deeper reasoning One chat. Backed by @supermemory.
    958
  • supermemory reposted
    user avatar
    Dhravya Shah
    supermemory
    @DhravyaShah
    Jun 28
    This is something we think and care about a LOT at @supermemory Most people forget that memory is not just about remembering things or storing them (no matter if it's 100k files....) it's also the things on the harness!!! There's tons of people building in memory that almost
    user avatar
    Matt Van Horn
    @mvanhorn
    Jun 27
    Article cover image
    Article
    Your AI's Memory Is Quietly Making It Dumber (I Cut Mine to 6 Files)
    I gave a talk last week and said it out loud: delete that memory, agent. When your agent learns a lesson, do not park it in some private memory file. Make a pull request that improves the skill, so...
    14K
  • supermemory reposted
    user avatar
    Shardul Mane
    supermemory
    @shardul_mane
    Jun 27
    when friends do epic shit, you gotta pull up
    4.1K
  • supermemory reposted
    user avatar
    Muskan Jain
    supermemory
    @Muskanjain0401
    Jun 27
    this guy is building @os_vanta, a health OS for people who treat their body like a high-performance machine you plug in everything: ~ whoop, oura, apple watch ~ bloodwork + glucose ~ diet, supplements, training it runs on @supermemory, so the system never forgets you, your
    00:00
    7.3K
  • supermemory reposted
    user avatar
    Vedant Mahajan
    @vedx09
    Jun 26
    27000+ stars on supermemoryai/supermemory crazy to go from watching this repo grow to building it every day grateful for everyone starring, using, and contributing to @supermemory
    00:00
    1.4K
  • supermemory reposted
    user avatar
    sujit
    @sujitenv
    Jun 26
    Replying to @sujitenv and @DhravyaShah
    first ai-era app ive experienced actually working smoothly in one-click @supermemory
    893
  • supermemory reposted
    user avatar
    sujit
    @sujitenv
    Jun 26
    holy shit
    1.2K
  • supermemory reposted
    user avatar
    supermemory
    @supermemory
    Jun 24
    Introducing Memory 101 🧠 Every ai tool you use is a goldfish. brilliant for one chat, close the tab and it forgets you completely. memory is the most underbuilt layer in ai right now. so we're explaining how it actually works, one episode at a time. coming up: → rag vs
    00:00
    16K

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up