Live data from Hacker News

Viewing profile — kwstx

kwstx

HN member
Joined
Sat, Mar 14, 2026, 1:14 PM UTC
HN karma
0
Public activity
13 items

About kwstx

Hello everyone! I’m Kostas, a software engineer who likes to automate everything if it has to be done more than once, and build tools for the agent economy in order to be friends with the robots.

Recent public activity

  1. comment
    Comment #47660273

    I'm glad you like it? What you think about the problem and the approach I'm taking to solve it? Any kind of feedback is welcome.

  2. comment
  3. story
  4. story
  5. comment
    Comment #47417751

    A bit more context on how this works under the hood: Right now the middleware sits as a translation/orchestration layer between agents. Instead of forcing a shared schema, it: vali…

  6. story
    Show HN: Middleware for translating between AI agent protocols

    I’ve been working on a problem that kept coming up while building multi-agent systems: agents don’t interoperate cleanly. Even when two agents can technically connect, they often: …

  7. comment
    Comment #47402843

    Fun experiment. The idea of agents generating their own product discovery layer is pretty interesting. One thing I’m curious about: how do you verify that a participant is actually…

  8. comment
    Comment #47386446

    Treating an agent as a versioned repo artifact is a neat idea, especially being able to diff prompt/behavior changes like normal code. One thing I’m wondering,how opinionated is th…

  9. comment
    Comment #47386421

    Interesting problem I’ve run into the same thing when building agents that need their own identity for email workflows. Quick question: are these real mailboxes (IMAP/SMTP) or more…

  10. comment
    Comment #47376859

    This is a smart approach, giving agents access without exposing secrets is definitely needed. Curious how you handle dynamic access policies for agents that need temporary elevated…

  11. comment
    Comment #47376807

    Really cool approach, I like the “Unix philosophy” for agents. Curious how you handle state persistence and chaining sub-agents when agents are depth-limited. Also, do you have any…

  12. comment
    Comment #47376691

    This looks fantastic, agent security is definitely under-addressed. Curious how you handle inter-agent trust scoring when multiple agents collaborate or share state, especially in …

  13. comment
    Comment #47376605

    Really cool! I’m curious how Glass Arc handles changes across multiple files — do you validate dependencies or check for side effects before applying fixes? The multiplayer sync al…