Notes on Cross-Platform Computer Use Agents for macOS and Windows — Selection with Hermes Agent and cua-driver as of September 2026

Notes from comparing Computer Use agents that can operate native apps on both macOS and Windows as of September 2026. Among official apps, only the ChatGPT and Claude desktop apps clear the bar of two-OS support plus full-OS control. On the open-source side, Nous Research's Hermes Agent paired with trycua's cua-driver is the strongest starting point, with UI-TARS, Agent S, and Open Interpreter as adjacent candidates. This article focuses on what feature-matrix comparisons tend to hide: the actual scope of the 'no-foreground contract' for background operation, TCC and Accessibility on macOS, UIPI and Session 0 on Windows, multi-monitor limits, and Japanese IME behavior.

Hand It an Issue, Get Back a PR — A Hermes Agent Skill Looping Between Codex and Claude Code

When agents write the code, the highest-value human work is neither writing nor reviewing it. It is building the foundation the loop runs on, and planning the issue. Shipping this skill made that conclusion concrete.

Loop Engineering works best for solopreneur-style new products — when you built it from scratch and hold the whole design

Loop Engineering is not universal; it works cleanly in some repositories and grinds in others. The dividing line is who owns the spec, whether the verification substrate is real, and whether the merge decision closes back to the same person who wrote the issue. A solopreneur-style new product is one of the few settings where all three line up, which is why the design of Loop Engineering pays off there the most.