Ethics of AIDocs
Back to site

Getting started

  • Overview

Remote MCP

  • Meeting users where they are: why we built MCP
  • Connect your AI client to Ethics of AI
  • Assistive, not autopilot: how interactive assessments stay yours
  • How we built a remote MCP server for Ethics of AI

AgentRoom

  • What AgentRoom is
  • How AgentRoom is put together
  • The coding agents AgentRoom drives
  • Trust and safety
  • Install AgentRoom and pair your Vision Pro
On this page
  • Docs in this topic

Docs

AgentRoom

How AgentRoom runs coding agents on your own Mac and drives them from a Vision Pro: the architecture, the agents it supports, and the trust boundaries it holds.

Docs in this topic

Concept4 min read

What AgentRoom is

AgentRoom runs coding agents on your own Mac and lets you drive them from a Vision Pro. Here is the model, the three pieces, and why there is no hosted control plane.

Implementation5 min read

How AgentRoom is put together

The boundaries that hold AgentRoom together. What the backend owns, what a client is allowed to ask for, how workspace access is bounded, and why a thread outlives the process that created it.

Implementation4 min read

The coding agents AgentRoom drives

AgentRoom ships with four built-in coding agents and can register external ones over Agent Client Protocol. What each needs to be set up, and what each one loads from your workspace.

Decision6 min read

Trust and safety

What AgentRoom bounds, what it ships switched off, and where the sharp edges are. Including the things it does not protect you from.

Install guide4 min read

Install AgentRoom and pair your Vision Pro

Join the AgentRoom TestFlight beta, set up the backend on your Mac, register a folder, and connect the headset over your local network.

On this page

  • Docs in this topic