75
Is anyone self-hosting their own AI? (thelemmy.club)
submitted 11 hours ago by to c/selfhosted@lemmy.world
109 comments fedilink hide all child comments
 

Does anyone run their own AI service?

If so,

Which one?

What hardware?

Do you have a way to access it from outside or from a phone?

And, if you're open to sharing, what do you do with it?

I know AI-enabling hardware is insanely expensive right now, but some of the smaller (<32GB) more efficient models (think deepseek- or qwen-based) don't absolutely need specialized hardware to run and perform well enough for many purposes.

I am so aware of the absolutely abysmal privacy practices of basically all AI companies that I'm not comfortable using them to help me with web searches and the such, because there's no way that all this information won't be going into a profile. This makes me want to have my own "helper" service.

you are viewing a single comment's thread
view the rest of the comments
[–] 5 points 9 hours ago (6 children)

Yes, with OpenClaw I can expose my agents via discord apps on my home discord server, I like that route because of the rich media and UI options (agents can give me drop down selector lists and approve/reject buttons). I have two 24gb Nvidia cards for local models usually Qwen, Mistral, and nemo based models for different purposes. I can chat with the agents anywhere I'm logged into discord and I expose privileged control surfaces and nodes via tailscale and family/shared endpoints via caddy and cloudflared

  • permalink
  • fedilink
  • source
  • hideshow 6 child comments
    •
  • [–] 4 points 9 hours ago (5 children)

    What are the agents doing for you?

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 5 child comments
    •
  • [–] 2 points 8 hours ago (2 children)

    So one thing that's really helpful to automate is checking all the repos for my self hosted stacks and testing/validating/deploying new versions when they come out. They're also good at writing helper scripts in Python to automate things deterministically so I don't have to keep using LLMs for it. There's an agent that is focused on learning and managing my wife's school schedule, ingests her grades and syllabi and reviews her homework and makes helpful 10 minute podcasts on concepts she's struggling with in her engineering program (not notebookLM, a self hosted lookalike), there's a domestic agent that accepts uploads of grocery receipts and does our meal planning and schedules time for meal prep and chores and divides it up between us and the kids depending on everyone's calendars, there's a home media agent that manages qbittorrent and my ratios on private torrent trackers and files new manga or TV shows or movies ebooks audiobooks etc in the right library when new things come out we might like, viewing/reading/watching metadata tells the agent what content is popular to queue up in the next sweep - there's a home assistant front door agent that can make automations or report sensor state or trigger scenes or entities in the general text channel of our home discord server and can tell me where my phone or keys are thanks to ESPresence being able to use cheap ATOM esp boards throughout the house (tiny little USB powered things with Bluetooth and wifi) to triangulate the location of any watched Bluetooth device or tracker tag in 3 dimensions through floors and walls - what else..there's a home security red-team agent that looks for security holes in my cloudflare tunnel/kv worker/tailscale/caddy/protonVPN routes and monitors a cyber security RSS feed, I have a job/market research bot that ingests another RSS feed for news relevant to my industry and organization and gives me email and voice briefings on new regulations and corporate leadership signals, stuff like that. What else.. there's a game dev bot where my kids can talk to a discord bot that routes to a game dev agent that has Godot MCP and Unity MCP and renpy MCP and lots of other fun tools like Roblox MCP and Minecraft to make custom games we can deploy on Google cloud for their friends to play (my daughter is really into visual novels for some reason I don't get it) - all sorts of fun stuff. Discord is kind of the family shared interface and then the privileged control planes are routed to my phone through tailscale and the home media server stacks are exposed through cloudflared.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 1 point 7 hours ago* (1 child)

    I'm confused about some of these. For example everything you mentioned in the torrent agent (maintaining ratios, watching for new media, seeing what's popular) are already settings in the *arr suite that uses significantly fewer resources, no?

    there’s a home assistant front door agent that can make automations or report sensor state or trigger scenes or entities

    This is all basic functionality of Home Assistant, yes? I'm confused about what is the agent is doing?

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 1 point 4 hours ago

    In the case of HA, the agent is receiving ambiguous natural language requests and converting them into HA MCP calls. I can open the HA app and press buttons, sure, but the agent can reason over time about patterns of water/electricity use, provide natural language feedback, push back on my automation ideas with counterexamples from sensor logs - and all the sensors in the home and on the phones carrying the companion app are rich signal sources for an agent. It unlocks neat tricks like when our babysitter comes over the front door agent can alert her if there's a water leak and walk her through shutting off the water to the house or locate the backup key for her. It can DM me when someone rings the doorbell and carry on a different conversation with STT depending on if it is a person wearing a uniform or holding a clipboard for example thanks to Frigate and some custom vision ingestion with Qwen 3 VL.

    Regarding the torrents, that agent keeps track of my ratios on the private trackers and I can give it natural language feedback about what I did or didn't like about a show or movie and it will suggest alternatives, find them on a private tracker, download them, unpack them, and ingest them in the library for me, keeps track of the families like and dislikes and suggests media to watch together, watch private trackers for open invites or interview slots and take the knowledge interviews for me on IRC, deduplicate downloads and hunt for releases with minimum quality standards etc. one of my first tasks for it was replacing my music collection that got damaged when my external hard drive got dropped with no backup and I had to get it extracted in a clean room. Lots of rare lifetime accumulated mp3s gone - mostly recovered now. Searching for replacements would have been a long slog so I automated it.

    To your point some of these things could be done by deterministic python scripts and in fact the agents write those to save inference costs later and most of this stuff I could do by siting on my computer an clicking on stuff and reading - the point is that the agents constitute a natural language control surface to trigger all of those actions for me automatically so I can just send a couple chats to a discord bot and it will be done a few minutes later. I'm a busy person I dunno if you can relate. Busy career, got a family to support, parenting obligations, no time to hang out playing video games any more sadly. Building stuff takes time and effort and you have to learn and read about how to do it or pay someone else to do it for you so I was stuck on the easy convenience of windows and Netflix and Amazon/kindle etc. Not anymore! It started with having to install docker desktop to get OpenClaw working and then pretty fast I figured out pretty much everything I wanted to do now that was not work related is better done on Linux and better done self hosted. I would never have gotten over that hump without LLMs.

  • permalink
  • fedilink
  • source
  • parent