1. X
  2. Vellum
Log inSign up
Vellum
376 posts
user avatar
Vellum
@vellum_ai
A personal AI assistant that evolves with you 👾
New York
vellum.ai
Joined May 2023
56
Following
1,712
Followers
RepliesRepliesMediaMedia
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

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.

  • Pinned
    user avatar
    Vellum
    @vellum_ai
    May 7
    The world's first Personal Intelligence is OUT NOW!
    user avatar
    akash · vellum.ai
    @asharma_53
    May 7
    We’ve raised 25M to build the world’s first Personal Intelligence. Introducing Vellum: AI that belongs to you. My assistant @ash_vellum has his own X (like grok), tag him and he'll answer.
    00:00
    12K
  • user avatar
    Vellum
    @vellum_ai
    Jul 24
    New in Vellum: Self-improving skills 🍄✨ Your assistant notices what you do often and creates new skills on the go. The next time you ask it to plan a trip, organize your week, or follow up with a client, it will do it faster and better. Available on every plan, including
    00:00
    3K
  • user avatar
    Vellum
    @vellum_ai
    Jul 22
    Assistants can make you go viral using our new @virlomain Plugin It gives your Assistant access to to 21K+ creators and 4M+ videos to tell you > Viral trends in your niche > The best creators doing it > What viral content to make Unlocks for your viral marketing strategy 🧵
    00:00
    1.9K
  • user avatar
    Vellum
    @vellum_ai
    Jul 20
    We launched a new memory system for your assistant with @cognee_ This plugin replaces Vellum’s native memory with Cognee’s knowledge graph memory engine giving your assistant: > persistent long-term memory across sessions > connects everything it learns into a knowledge graph >
    3.3K
  • user avatar
    Vellum
    @vellum_ai
    Jul 15
    When your Assistant is stuck or needs another opinion it will consult a Advisor agent running on a more powerful model like Fable 5 or GPT-5.6 Sol. This saves you tons on token spend by keeping spend on frontier models only when you need to.
    708