Terminal Mode by Even Realities

Great Job! I see that this is great for approving permissions and finishing off a task. One thing I was wondering was that if I have multiple terminals open will the glasses auto summarize every terminal or do I have to link it to one specific terminal and am restricted to only using one instance of an agent. For AI like Claude where I have to direct it to specific folders or give it specific instructions, does the voice recognition support skills like if I wanted to use a skill in code and also how easy is it for me to rewind if the voice diction doesn't work properly and I need to go back to the previous state. Apart from the peripheral vision what is the difference between the glasses vs setting it up on my phone using /remote control. Will these glasses be Bluetooth and does that mean I will need to still have my phone on me

Agent supervision shouldn't require sitting at a desk all day. Simple idea, but an important one

Honestly didn't expect smart glasses to find their killer feature in waiting for Claude Code to ask permission, but here we are — and it makes total sense. Most of my agent downtime is exactly this: it's blocked on a yes/no while I'm away from the desk getting coffee.How fast does a voice instruction actually reach the agent? If there's a noticeable lag, that glance-and-approve flow loses its magic.Anyway, interesting product. Curious where this goes as agents run longer on their own.

This is one of those ideas that seems obvious in hindsight but nobody was doing. Having agent output always visible while coding is a genuine workflow improvement, not just a nice-to-have. Curious how it handles multi-file refactors where you need to jump between contexts.

This is exactly what the 'agentic' future needs! I'm deep into building web utilities and custom backend automation right now. The biggest friction point is always the micro-approvals—an agent waiting idle for me to confirm a script change just because I walked away from the screen. Giving voice instructions on the go sounds like a massive productivity unlock. Amazing work bridging this gap!"

Clean launch for Terminal Mode by Even Realities: Keep coding agents always in sight. How are you measuring whether it is working for people?

Our dev team has been deep in claude code lately and the "agent stalled while you stepped away" problem is real. curious about the price point - is this for individual buyers or do you see teams equipping multiple devs?

A question about the glasses in general: as far as I remember, your glasses don’t have a camera. Have you considered adding a camera with a small physical shutter that can be opened or closed with a finger?

Keeping an agent's output in my peripheral view instead of alt-tabbing to a terminal is a genuinely different way to babysit long-running jobs. How readable is a streaming log on the display in practice — do you diff it down, or show the raw tail?

This is one of the first smart glasses use cases that actually feels practical to me. Catching the moment an agent needs input, without babysitting the laptop, is a real workflow fix.

I've talked to developers who basically set a timer and walk away from their agent runs, then come back and see what happened. That works until the agent hits a decision point halfway through and spins for an hour. Live visibility changes that risk calculation entirely.

I noticed the connection stability improvements in the latest release. What was causing the issue before?

Terminal Mode is the first feature that makes me feel like I've been underusing the hardware I already own. That's the best thing a software update can do.

Are non-coding use cases already being explored, or is the focus staying on developers for now?

Smart glasses have been looking for a killer use case for years. 'Ambient supervisor for AI agents' is interesting because it targets a workflow that's actively growing, not a general consumer behavior