Why I gave Claude Code a computer instead of building another IDE

A developer built Superagent, a Mac app that gives Claude Code and other AI agents a real computer environment to work in, rather than a chat window. The app consists of an Electron desktop app, a SwiftUI iOS companion, and a Cloudflare Worker relay for pairing and rate limiting. The developer emphasizes that the main challenges were environmental, such as handling DOM elements not in the accessibility tree and simulator state drift.

Most "AI coding" products still put a chat window next to your editor and call it a day. I wanted something closer to what Claude Code already does well on a server: give it a real computer and let it drive. Superagent is a Mac app that gives Claude Code or any agent you point it at an actual environment to work in, not just a text box. Concretely: The core idea is boring on purpose: don't build a smarter chat window, build a better place for the agent to act. Most of the interesting failures I hit while building this weren't in the model, they were in the environment: synthetic file inputs that don't persist through a web form's upload component, elements that exist in the DOM but aren't in the accessibility tree, simulator state that drifts from what a screenshot shows. Fixing those is what actually makes an agent reliable to hand a task to. It's built as three pieces: an Electron desktop app, a SwiftUI iOS companion, and a small Cloudflare Worker relay that pairs the two with per-address rate limits so a lost phone can't be used to spam a stranger's Mac. If you want to see it: https://peerlist.io/pungme/project/superagent-for-mac https://peerlist.io/pungme/project/superagent-for-mac Happy to answer questions about the browser automation approach, the simulator driving, or the relay's pairing/security model in the comments.