AI Agent – TRMNL(help.trmnl.com) |
AI Agent – TRMNL(help.trmnl.com) |
Note: Yes, I know what I'm about to say could be done using TRMNL (as part of it)
I was able to set it up so that it rotates book quotes every day with a picture of the book cover next to the quote. That, on its own, is far from impressive. What made me giddy was that it shows book quotes that I've highlighted in KOReader on my jailbroken Kindle. KOReader syncs up to BookOrbit (open source ebook manager/reading tracking tool). The whole thing happens 100% local to my network.
BookOrbit is running in a docker, my little server to render the book/quote runs in a docker, my Kindle talks to BookOrbit, my ReTerminal talks to HomeAssistant (ESPHome). It's 100% local and it's silly but it's mine and I love it. As I'm reading I highlight something and a day, a week, a month later I see it on the display on my dresser or in my office.
I want to put these all over the place in my house and I already modified it once so each screen will get a different random quote so I don't have to worry about duplicates. I'm considering getting 1 display per book shelf where I have a full series and configuring it so that it just shows quotes I've highlighted from that series. The sky's the limit.
I fully understand no one cares, I get it, this is super-duper-custom, "just for me", and that's what I love.
I recognize some folk dislike mixing tech and politics, but human ethics and actions impact the world.
It’s fair to feel distrust for any product based on the values that product’s creator expresses.
I saw the author of TRMNL in this thread so perhaps I can invite him to address that — and in replies, let’s keep discourse civil and HN-like please.
I was not familiar with at TRMNL was and from the link I went to there was no way to get to the "home page" of the product (https://trmnl.com)
I did not see anything in the footer section and clicking on the logo on top only sent me to Help home.
I was trapped with no easy way to learn more about you guys
> We're seeing an average of $1-3 per plugin.
Is this really true, or is it overstated to be safe? Isn't it just a handful of html markup and JS?
the agent also has a model switcher, and the estimate you quoted is based on Haiku when we launched.
https://en.wikipedia.org/wiki/List_of_telephone_country_code...
the AI Agent exists to empower less technical folks to turn their vision into reality, and we're proud of what's possible with it. meanwhile our top community developers continue to hand craft beautiful, useful plugins for everyone to install, LLM free.
Previously most "personal computing" (building custom stuff for your specific needs) was limited to people that either already are intimately aware of how computers and programming work, or people that were interested in starting down that path.
Plenty of people do not have the time/energy to go down that path, but still want custom stuff. Yes you can't zero-shot robust enterprise software, but the models are good enough to few-shot solid results when it's bounded to some interface requirements (like an SDK).
I don't make many predictions but this is one I am comfortable saying is the future of personal computing and what "harnesses" will look like in the future. Models will shrink and post-train to the use case at the enterprise level, and agent harnesses will go from things like codex/claude code to what look like self-assembling software. Give regular users an app with a plugin system, an agent, and a clear set of entry points and thats all they need to run.