Terminal Mode by Even Realities - Keep coding agents always in sight
by•
Terminal Mode by Even Realities unlocks an ambient terminal on Even G2 smart glasses. When a coding agent stalls, you catch it: see which agent needs you now, give direction, and approve key steps while your laptop runs long tasks, so token-maxers get more from every run and vibe coders stay in flow.
Replies
How are blocked, waiting, and failed states differentiated visually?
@yvette_luo
There is a status bar on the bottom,
The UI is quite clear (at least the UI team thinks LOL)
How does Terminal Mode behave when a phone call or notification comes in?
@yvette_luo1
Good question;
It does not behave at all. In this mode, all noise is stripped out. Tunnel vision on that C++ code Yvette!
Congratulations on Launch!!.
A few things I'm genuinely curious about: The "approve key step" tap is only useful if I actually understand what I'm approving. How much context fits in the glasses view before it becomes too cramped to read comfortably? Also the most important multiple agent at once.
@abhishek_srivastava_eng
I find myself to have enough context without having to see the whole stream. We keep the terminal screen relatively info dense, so you can get a good idea most of the time.
@harini_mukesh
Balancing what to show and what to cut - since these can be super personalized.
Been following and watching ''even'' videos for a while now, finally found the product hunt launch. The product is great and looking forward to have my hands on it. I believe i was dreaming to have a cool gadget like even . Looking forward it it ( : ,. also may be next time would love to even hunt Even As a hunter on product hunt.
Kudos to the launch ( :
@istiakahmad
Thank you! Your support means a lot to us. <3
Interesting angle. The part I’d want to see is how it handles the boring but important moments: failed tests, half-finished changes, and when the agent needs approval before touching risky files.
For long-running coding agents, visibility matters less as “cool UI” and more as a stop/ask boundary.
Nice angle. The part I’d care about most is not just seeing the agent, but knowing when it’s stuck or about to do something risky.
For long-running coding agents, the boring signals matter a lot: failed tests, files it wants to touch, whether it needs approval, and a short summary of what changed since the last checkpoint.
Interesting angle. The useful part for me is not just keeping the agent visible, but making the interruption actionable: what is blocked, what decision is needed, and what happens if I ignore it.
For long-running coding agents, that handoff quality matters a lot more than another stream of logs.
This looks really promising. Wish I could get graded lenses in Italy.