Tabi 💢

@TabiVibe

The Modular Layer for Consumer AI. Backed by @animocabrands & @YZilabs

已收录 17 条帖子
  1. #1

    Preview first. Execute later. Capital workflows need an exit path.

    Tabi 💢 @TabiVibe ·
    Preview first. Execute later. Capital workflows need an exit path.
  2. #2

    The next step after enforcing policy is making policy legible to the agent.

    Tabi 💢 @TabiVibe ·
    The next step after enforcing policy is making policy legible to the agent.
  3. #3

    Sometimes, a simple “I get you” is warm enough.

    Tabi 💢 @TabiVibe ·
    Sometimes, a simple “I get you” is warm enough.
  4. #4

    Still on the road. Still moving.

    Tabi 💢 @TabiVibe ·
    Still on the road. Still moving.
  5. #5

    “Give the agent $100” is not a risk policy. A real funding policy needs dimensions. PredictClaw’s Vault overlay can now express constraints such as: Per transaction How much can m…

    Tabi 💢 @TabiVibe ·
    “Give the agent $100” is not a risk policy. A real funding policy needs dimensi…
  6. #6

    Keep the identity. Upgrade the control plane. 💢

    Tabi 💢 @TabiVibe ·
    Keep the identity. Upgrade the control plane. 💢
  7. #7

    From there, users can choose the workflow they actually need: → read-only → EOA → Predict Account → Predict Account + Vault

    Tabi 💢 @TabiVibe ·
    From there, users can choose the workflow they actually need: → read-only → EOA…
  8. #8

    Monday: Brain loading… Coffee ready. Human still buffering.

    Tabi 💢 @TabiVibe ·
    Monday: Brain loading… Coffee ready. Human still buffering.
  9. #9

    …anyway, back to building.

    Tabi 💢 @TabiVibe ·
    …anyway, back to building.
  10. #10

    We don’t want ERC-8192 to become a Tabi-specific execution framework. The goal is a minimal, composable execution primitive. Three questions we’re actively pressure-testing: 1. Is…

    Tabi 💢 @TabiVibe ·
    We don’t want ERC-8192 to become a Tabi-specific execution framework. The goal…
  11. #11

    Bears don’t kill projects. They kill weak conviction.

    Tabi 💢 @TabiVibe ·
    Bears don’t kill projects. They kill weak conviction.
  12. #12

    Good agent infrastructure is defined as much by what it refuses to execute as what it allows. ERC-8192 currently enforces controls including: → signed mandates → nonce / replay pr…

    Tabi 💢 @TabiVibe ·
    Good agent infrastructure is defined as much by what it refuses to execute as w…
  13. #13

    gm

    Tabi 💢 @TabiVibe ·
    gm
  14. #14

    Moving from architecture diagrams to executable infrastructure. 💢

    Tabi 💢 @TabiVibe ·
    Moving from architecture diagrams to executable infrastructure. 💢
  15. #15

    How did you meet Tabi?

    Tabi 💢 @TabiVibe ·
    How did you meet Tabi?
  16. #16

    GM. First Monday of October.

    Tabi 💢 @TabiVibe ·
    GM. First Monday of October.
  17. #17

    1/6 Tabi: the Modular Layer for Consumer AI. It is the composable, onchain-native infrastructure for the next generation of AI Agents.

    Tabi 💢 @TabiVibe ·
    1/6 Tabi: the Modular Layer for Consumer AI. It is the composable, onchain-nati…