Log inSign up
Rhys profile banner
user avatar

Rhys

Executor
@RhysSullivan
building executor.sh to connect any agent to every tool, API, and service your team uses | yc 26
San Francisco, CA
rhys.dev
Joined November 2007
1,484
Following
59.1K
Followers
RepliesArticlesMedia
  • Pinned
    user avatar
    Rhys
    Executor
    @RhysSullivan
    Jun 23
    Executor is joining the YC S26 batch! We're building an open source MCP gateway to connect any agent to any service Your team is constantly spinning up new agents, trying out new tools, wrangling multiple accounts. You need one place to configure everything once, and use them
    Image
  • user avatar
    Rhys
    Executor
    @RhysSullivan
    13h
    Computer Use team at OpenAI continues to be my favorite
    user avatar
    Ari Weinstein
    @AriX
    14h
    Today we're releasing Computer History in ChatGPT. It lets ChatGPT learn from everything you do on your computer, so it can better understand how you work, finish tasks that you're in the middle of, and suggest skills and automations based on how you use your computer.
    Image
    00:00
  • user avatar
    Rhys
    Executor
    @RhysSullivan
    21h
    Setting up @bot and so happy I’ve got Executor setup Just signed in once to the Executor MCP and now my 5 Google accounts are all connected, along with all the other services I use Makes it so easy to explore new tools, feels like 1Password for my MCPs
  • user avatar
    Rhys
    Executor
    @RhysSullivan
    Aug 12
    On AI policy, what’s the best arguments you’ve seen on agents autonomously committing crime? i.e in the OpenClaw hacking a gym database scenario, is the owner of that agent responsible even though their prompt wasn’t malicious?
  • user avatar
    Rhys
    Executor
    @RhysSullivan
    Aug 12
    Even more important is the computers are acting now We’re well past the point of “a computer should never make a decision” What happens when someone’s agent hacks a company on their behalf from a non malicious prompt?