Hermes Desktop update: agent can now click, type and navigate the browser pane you watch
Teknium · x · 2026-08-23
Hermes Desktop from Nous Research got a major update: the agent can now actually use the preview pane browser — clicking, typing, scrolling, navigating and annotating, not just opening or reading a page.
This turns Hermes Desktop from a chat window attached to tools into an agent that works through web tasks in front of you. Cited use cases include opening docs and pointing to where a setting lives, walking through setup flows, working through dashboards under supervision, reproducing web issues step by step, and filling out multi-step web workflows.
More from coding & agent
- YC F26's Praxis launches AI agents to run law firm ops end to end — ycombinator · 2026-10-16
- Developer builds inter-agent messaging for his AI agents — complete with message undo — baditaflorin · 2026-10-16
- iOS 'dots' workflow: one Siri command turns screenshots into a background shopping and saving agent — nickbaumann_ · 2026-10-16
- Your widget tree is already a list of options: where Jev fits in Flutter — rseroter · 2026-10-16
- How OpenAI's Codex went from failed side project to 40M weekly users in under a year — danshipper · 2026-10-16
- Photon 2.0 launches unified messaging API for AI agents across iMessage and more — Scobleizer · 2026-10-16