59 points | 41h ago | Discuss on Hacker News | Back to Radar
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.
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.
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.
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.
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
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.
Basically it's just a loop with bubblewrap based sandboxing for the tools (not really enough if you're going to expose it to a lot of untrusted data - I intend to move the entire thing into a vm) and the "identity", "soul" and "memory" split that the original openclaw used to give the agents persistent identity.
The e-mail access is read-only simply by virtue of it having no direct access to credentials but access to tools to run read only operations on my mailbox.
They also have tools to read and send Matrix messages, but at the end of the turn any new messages also get injected automatically if any to start a new turn. In additional there's heartbeat that triggers occasional requests to clean ensure anything they "want to remember" is consolidated in the memory files, and to clean up, or advance any tasks, and a very basic reminder system.
I'm using a mix of Kimi, GLM5 to run the actual agents at the moment.
I might release parts of the code at some point. It's nothing special, but it's small and easily auditable unlike OpenClaw.
I picked Matrix because it's trivial to self-host with federation turned off so the agents are reasonably isolated (with the caveat that they do have web access but at least they'll have to work a bit more to leak my data - but be careful). I run it on in my wireguard network and can access it via a Matrix client on my phone and/or a web app on my home machine.
I can also access it via Claude, Codex, Kimi CLI via a trivial little mcp server that wraps the same Matrix client code the agents use.
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.
Comments are loaded live from Hacker News and are not stored by Mid or Real.
shlewis 36h ago on HN