Show HN: NanoMuse – An open-source AI agent for your phone and computer | Hacker News Reader

Show HN: NanoMuse – An open-source AI agent for your phone and computer

github.com

54 pointsilreb20 comments

Great name to be replaced in about a week.

Great! We need any and all open source alternatives to products that people obviously find useful but do not respect their privacy. Looks good! I‘d reconsider the name.

If name changing becomes main topic, i suggest nanoCat :). Btw how do you handle security boundaries?

audit the installer: a similar tool, state dir redirected, still wrote eleven other assistants' config files and a port 4400 daemon.

Sounds like a meta product made to steal my data on yet another device, not good marketing

Anyone running ai agents directly on their phone deserves exactly what they get.

A phone is a much more secure environment to run untrusted apps than Linux/mac/Windows since the apps are sandboxed.

On Linux is free for all, a regular app running as a user can read/exfiltrate anything owned by that user.

And sandboxing like snap/flatpak is not popular.

Yeah not installing this on my daily phone yet...

I honestly can't imagine ever having, needing or wanting an AI assistant on any of my devices.

Have people really been struggling so badly all these years with managing their emails and gym memberships?

> Have people really been struggling so badly all these years with managing their emails and gym memberships?

Yes. I have ADHD and Hermes Agent has been extremely helpful for symptom management. LLMs have been an absolute revolution in accommodation for me.

Same, as a dev with ADHD, the coding was always the easier part.

I've hated LLMs because the wall of text generated by all my colleagues when I ask questions or they need to document anything has largely become indigestible and they took away the part I really enjoyed - deep focus on a precise problem.

Finding Hermes has been a real game changer for me, I can set the rules for the output and most of all executive function goes from intent to execution rather than deliberate effort to enforce habits to try function.

You guys work for Hermes right?

No, only been using it for the last few months, personally at home and recently at work.

It's still just an agent, but I can retain the memory and scripts etc. Big win for me is that it just has all the plumbing in place to be actually useful upfront.

Could you elaborate on how you use Hermes for symptom management? I'm especially interested in what it does that can't be done with the usual AI chatbot or agent.

Wait until you start getting even more emails and phone calls about suspicious activity on your accounts, or weird emails "you" have sent, or from friends asking why you didn't turn up, or that your flight was successfully rescheduled. Then your ADHD is really going to flare up!

Everyone has their own struggles, yes. And we're all different, so it's often difficult to imagine the struggles other people have because we take certain things for granted.

For those of us with executive function disorders, yes, the amount of information being shoved at us in this modern world is well past the level where we can make sense of it easily, and we certainly can't keep track of it all. Assistants that can read and understand natural language and _assist_ us have been accessibility revolutions.

If you can do it all yourself, that's great. Not everyone can, and not everyone can have a person helping them or doing it for them all the time, either. Being able to just throw _life_ at something in a box and say "Help. Please." and get help? Indescribably useful.

Now if we can just fix the risk and privacy nightmare part we'll be golden.

Actually I'm pretty good advocate for an accessible web. I think speech to text must be an awesome quality of life improvement for some people.

But I don't see why anyone would need an autonomous agent let loose on their device, u less they are actually braindead in which case its not going to help anyway.

People saying it helps with ADHD, but if you suffer from things related to over stimulation from your environment an autonomous agent is going to potentially make things much much worse when it fucks up your life by send a bad email or instant message

An agent means that when I decide to ignore my e-mail for a week because it's overwhelming, I still get gentle nudges about just the most important ones.

And you don't need to grant them access to send things without gating it on explicit approvals. My agents doesn't have write/send access to my email at all.

I didn't even plan for this, or think it was something I needed, but I gave my personal assistant agent on my private Matrix server read-only access to my e-mail, and it decided of its own accord to summarise the e-mails that look most important for me and now I don't want to ever go back.

Can you talk more about this setup? What assistant agent are you running? And how did you grant it read-only access to your email?

Reply on news.ycombinator.com