Hacker News new | ask | show | jobs
by atonse 29 days ago
I am especially hopeful for this for my daily stuff, not just testing.

Meaning, having a hopefully seamless way to perform some automations in the browser on my behalf but since it’s the browser I’m logged in to, it just makes the handoff between myself and the agent feel more seamless.

And that’s because I’ve used safari as my main browser, not chrome, because it isn’t as much of a battery hog.
3 comments
kordlessagain 29 days ago
I'm working on Hyperia and it has full agentic control of a webpane (Electron based) for doing crazy things with it: https://github.com/deepbluedynamics/hyperia.

Uses an agent container orchestrator as well, which has MCP tools to expose ports in the container (and thus can display the work in the webpane): https://github.com/DeepBlueDynamics/nemesis8

I'll add the Safari MCP wiring to n8 today...

New releases landing tonight with more features.

link
ccouzens 29 days ago
> It also does not have access to your personal information in Safari (e.g. AutoFill or other browser activity).

I read this as meaning you won't be logged into the instance the agent interacts with

link
mooreds 29 days ago
> it just makes the handoff between myself and the agent feel more seamless.

This terrifies me because there's no way for the services on the other side of the browser to know who is doing what.

How do you constrain the agent?

How do you keep track of what you have done vs the agent?

What am I missing? Am I just behind the times?

Edit, added reference to what terrifies me.

link