I have so much personal automation and small web apps running on my VPS, laptop, and on my phone it's hard to know where to start.
- laptop, phone (termux), Linux VPS, and home inference machine can all see each other on the same Wireguard network via the VPS.
- Todo list web app for our family shopping list. Used daily for many years now.
- Personal daily updating dashboard with important numbers I care about, life metrics, weather, etc.
- Projects priority list which tells me what to do each day based on last update for each project (each project has a desired frequency of work and it prioritises by "lateness"). Checks git activity and RSS feeds to see what I'm neglecting.
- "Note to self" app and voice automation which transcribes and adds to my Joplin notebook on my laptop.
- AI agent on my phone I can long-press power button and give spoken commands ("add milk to the shopping list"). Uses private home inference machine, see below.
- Social media POSSE syndication scripts. Mastodon posts are syndicated to other networks.
- Blog posting pipeline from my Joplin notebook out to the web.
- Home inference machine (mostly solar powered) I use for personal finance, automation, note search, and other sensitive AI tasks.
- Self-hosted calendar and contacts (separate VPS but same idea).
I don't log in to Google at all. With LLMs now it's very little work to build and maintain these things. Absolutely wild time to be a home tinkerer.
> Projects priority list which tells me what to do each day based on last update for each project (each project has a desired frequency of work and it prioritises by "lateness"). Checks git activity and RSS feeds to see what I'm neglecting
I've been meaning to find or build something like this for a while, specifically for house maintenance and projects. Did you make this yourself? Available anywhere?
What do you use for you self-hosted calendar and contracts? I'm mostly de-googled but contacts especially have been problematic.
Also, what inference hardware are you using that's so efficient you can do it solar powered?
Nextcloud for calendar and contacts. Android sync with DAVx.
The inference machine is a basic headless gaming PC with a second hand RTX3090 and 64GB RAM.
The solar panels clock 5kW which is mostly fed back into the grid. It's sunny a lot here. The maximum consumption of the PC is 700W and it's mostly idle. Broad strokes we're net positive.
Can you share more about how you use the inference engine? Sounds very useful
Anyone have ACLs or tips on them for securing their tailscale? I'm concerned at the ability for lateral without wanting to sacrifice convenience.
ACLs are super simple and work well, just dig into them. I use groups as rbac (one group per role), and share parts of my network with friends/family (game servers), and colleagues (work collab stuff, such as live coding).
Toggling users on/off also works great, and disabled users don't count towards the limit.
I use tags. For example, anything with a server tag can accept ingress ssh connections but not egress.
> "Absolutely wild time to be a home tinkerer."
This!! There is no end to the side projects and idea lists, and all of them feel possible
We're like the proverbial kids in the candy store!
What stack do you use for that home inference? I’m rolling my own with gemma4, but even with Claude helping with the implementation it’s a lot of moving pieces to figure out.
Ollama running Meta's Glimmer model at the moment. I find it really capable for what I'm doing and it doesn't suffer censorship problems.
Are you using the API or is it self hosted as well?
(sorry if this question doesn't make sense)
It is self hosted.
Ollama serves models on an OpenAI compatible API directly on the inference machine, which most open source harness software will connect to. The inference machine has a name like inferencemachine.local on my home network so the Ollama URL looks like http://inference machine:11434/v1 to connect to any model I've downloaded.
> AI agent on my phone I can long-press power button and give spoken commands ("add milk to the shopping list"). Uses private home inference machine, see below.
For this part, are you using a tool-calling harness like Pi or Codex? Or did you sort of hack it together with prompts that tell it what json to emit?
I just got the rest of the “application layer” for my setup working yesterday, with a small set of evals. Auto-filing voice notes is what’s next for me.
Thanks for this goldmine of ideas!
No worries!