HermesBench vs TermRover

HermesBench benchmarks full Hermes personal-agent configurations with public recipes, redacted trace evidence, and reproducibility metadata.

TermRover is a native SSH + Mosh terminal optimized for working with tmux on iPhone and Android. Browser-style tabs, one-tap prefix actions, and scrolling all just work.

About HermesBench

HermesBench benchmarks full Hermes personal-agent configurations with public recipes, redacted trace evidence, and reproducibility metadata. The current public baseline scores 78.2 across 27 personal-agent recipes with redacted traces you can inspect. The site is deliberately clear that this is one early baseline, not a base-model leaderboard. Recipes What was tested Search by category, prompt, goal, and criteria. The public user pathway is intentionally simple: copy the prompt to Codex, Claude, or another coding agent. Full bundle runs are opt-in because they take longer and cost more.

About TermRover

TermRover is a native SSH + Mosh terminal optimized for working with tmux on iPhone and Android. Browser-style tabs, one-tap prefix actions, and scrolling all just work. The tmux prefix, usually Ctrl-b, is awkward on a touchscreen. Scrolling is worse: it usually requires mouse mode and changes to .tmux.conf, with no clear indication whether it is enabled., tapping the terminal should open the keyboard, and sending a screenshot to a coding agent. It immediately made sense for a phone: SSH can drop as you move between networks, while Mosh keeps the terminal working.