Local LLMs, I'm surprised no one brought that up yet. I've got an old GPU in my server, and I'm running some local models with openweb-ui for use in the browser and Maid for an Android app to connect to it.
this post was submitted on 03 May 2025
136 points (94.7% liked)
Selfhosted
46672 readers
186 users here now
A place to share alternatives to popular online services that can be self-hosted without giving up privacy or locking you into a service you don't control.
Rules:
-
Be civil: we're here to support and learn from one another. Insults won't be tolerated. Flame wars are frowned upon.
-
No spam posting.
-
Posts have to be centered around self-hosting. There are other communities for discussing hardware or home computing. If it's not obvious why your post topic revolves around selfhosting, please include details to make it clear.
-
Don't duplicate the full text of your blog or github here. Just post the link for folks to click.
-
Submission headline should match the article title (don’t cherry-pick information from the title to fit your agenda).
-
No trolling.
Resources:
- selfh.st Newsletter and index of selfhosted software and apps
- awesome-selfhosted software
- awesome-sysadmin resources
- Self-Hosted Podcast from Jupiter Broadcasting
Any issues on the community? Report it using the report flag.
Questions? DM the mods!
founded 2 years ago
MODERATORS
You’re a brave one admitting that on here. Don’t you know LLM’s are pure evil? You might as well be torturing children!
The tech itself is great.
But:
- Businesses push that shit where it doesn't belong
- Businesses replacing people by AI when it is objectively worst, to make a buck
- Business stealing the work of million of people to train their model
Completely agree
I think most people on here are reasonable, and I think local LLMs are reasonable.
The race to AGI and companies trying to shove "AI" into everything is kind of insane, but it's hard to deny LLMs are useful and running them locally you dont have privacy concerns.
Interesting, this has not been my experience. Most people on here seem to treat AI as completely black and white, with zero shades of grey.
I see a mix, don't get me wrong, Lemmy is definitely opinionated lol, but I don't think it's quite black and white.
Also, generally, I'm not going to not share my thoughts or opinions because I'm afraid of people that don't understand nuance, sometimes I don't feel like dealing with it, but I'm going to share my opinion most of the time.
OP asked what you self host that isn't media, self hosted LLMs is something I find very useful and I didn't see mentioned. Home assistant, pihole, etc, all great answers... But those were already mentioned.
I still have positive upvotes on that comment, and no one has flamed me yet, but we will see.
load more comments
(2 replies)
Concur. In particular models focused on image output.
I think looking through the comments on this post about AI stuff is a pretty good representation of my experience on lemmy. Definitely some opinions, but most people are pretty reasonable 🙂
Ais fine as a tool, trying to replace workers and artists while blatantly ripping stuff off is annoying, it can be a timesaver or just helpful for searching through your own docs/files
If you agree it’s a time saver, then you agree it makes workers more efficient. You now have a team of 5 doing the work of a team of 6. From a business perspective it’s idiotic to have more people than you need to, so someone would be let go from that team.
I personally don’t see any issue with this, as it’s been happening for the existence of humanity.
Tools are constantly improving that make us more efficient.
Most of people’s issue with AI is more an issue with greedy humans, and not the technology itself. Lord knows that new team of 5 is not getting the collective pay as the previous team of 6.
Nor will they get the workload of 6 people. They might for a couple of months, but at some point the KPI's will suddenly say that it's possible to squeeze out the workload of 2 more people. With maybe even 1 worker less!
Are you my project manager??
load more comments
(2 replies)
LLMs are perfectly fine, and cool tech. Problem is they're billed as being actual intelligence or things that can replace humans. Sure they mimic humans well enough, but it would take a lot more than just absorbing content to be good enough at it to replace a human, rather than just aiding them. Either the content needs to be manually processed to add social context, or new tech needs to be made that includes models for how to interpret content in every culture represented by every piece of content, including dead cultures who's work is available to the model. Otherwise, "hallucinations" (e.g. misinterpretation and thus miscategorization of data) will make them totally unreliable without human filtering.
That being said, there many more targeted uses of the tech that are quite good, but always with the need for a human to verify.
load more comments
(1 replies)
- Matrix server
- Element web GUI
- NocoDB for various Mini databases and forms
- Joplin server
- KanBan Board
- Mealie to store recipes
- Grocy as a home ERP
- Grafana for various metrics
- Home Assistant
- NodeRed(non HA, different node)
- InfluxDB
- Zabbix for monitoring
- Vaultwarden
- etherpad
- Technitium DNS
- A NTP server
- Mesh Central
- A win11 VM with RDP
- paperless NGX
- calibre Web (or does that count as Media already)
- Agent DVR
- Spoolmann
- OrcaSlicer via Browser(linuxserver.io)
- Omada Controller
- Univention to bring everything together
- netbox to document half of the shit
- wiki.js to document the other half
Honestly,I think I have a problem.
You have all the solutions lol
It sounds like it, but there are a few things I still need to do.
-
AMP Gamemanager to get better control of the servers for the kiddos
-
Codeproject AI for better image recognition with agent dvr
-
A proper voice AI setup with HA
-
I need to get my PBX setup going again
-
I will soon clean up my media and storage solution and move to TrueNAS
And I need to automate more. One day....
Can confirm you have a problem. I mean, you have two services to document your stuff.
Yeah, but Netbox is really really neat to document cabeling, IPAM, the rack and does asset management as well with a plugin.
But it's really hard to document HOWTOs in it. And wiki.js is really a bad idea for the former.
Storyteller, ever wish you could listen to an Audio book and read an ebook at the same time.
Storyteller can combine an Audio book and and ebook to create a single ebook that can be read like a normal ebook or you can listen to it and watch the actively spoken sentences highlighted in real time like a karaoke song lyrics.
ever wish you could listen to an Audio book and read an ebook at the same time.
Lol no? Absolutely not.
I don't mean actively reading and listening to the audio book, think of it like English subtitles for a English movie. You can ignore them for the most part, until you hear something you didn't quiet catch or you were not paying attention and missed something, it's much easier to scroll back a little and read the text to catch up rather than play the part again. Happens a lot for me when listening to audio books. And rewinding the book to catch up on the part I missed is annoying, it's better to just quickly read the last few lines instead.
This is pretty neat!
https://storyteller-platform.gitlab.io/storyteller/docs/intro/what-is-this
Sounds like you need both the audio and the ebook to make it work?
I typically only have one or the other.
load more comments
(1 replies)
I self-host web apps I write myself? ¯\(ツ)/¯
I used to get the light prices on my phone widget via a public api. Some years ago they closed the api and started asking for full name and id in order to get api access. So I just made a scrapper that takes the numbers I want from their website and serves an API for the widget.
That's the only self made app I self host, but I'm quite proud of it.
load more comments
(8 replies)
I randomly think about something I want, and then usually find it here. Used to be a GitHub repo, but it got so popular and useful they got a nice site with search and all, now.
https://awesome-selfhosted.net/
I don't have as much running anymore outside media/games, but I do still run Stirling PDF as an Acrobat Pro alternative.
Headscale
Matrix server (conduwuit, soon to be tuwunel)
Matrix bridges (slack, discord, whatsapp)
Adguard
Pihole
Findmydevice
Redlib
Linkwarden
Forgejo
Ntfy
Molly socket
Home assistant
Uptime Kuma
There's probably more that I'm forgetting lol
load more comments
(4 replies)
Joplin. I have it as a sync server. But have it tucked away in a cloud server for the times when I'm traveling so j always have a way to access data in case my phone gets stolen/confiscated.
Foundry VTT (I know it's technically for a game but it's technically a virtual tabletop and not a game itself)
AI Chatbots for tech support
I technically self-host an image generation AI through my main home PC, but that's made less accessable and only on when I specifically demand it via ssh lol
Occasionally I'll throw a temp website up for local events for like event schedules or whatever, an easily accessable and editable html file or whatever
I see mention of Foundry, I upvote. My friends and I have been using it for a couple years and still find new ways to be impressed by it.
load more comments
(1 replies)
load more comments
(1 replies)
Baikal for calendar, todo and contact syncing
Forgejo for version control
Silverbullet for markdown notes
FreshRSS for aggregated news
Linkding for bookmarks
- Forgejo - git hosting
- actual budget - spending tracking mostly
- Vaultwarden
- home assistant - still configuring
still configuring.
In my experience, this is always the case with ha
Lol. :)
SearXNG, Forgejo, Linkwarden, Vaultwarden, copyparty, all the Servarr apps, qBittorrent and SABnzbd for downloads, Syncthing, Mastodon, and all the various containers like databases and other tools that support the aforementioned.
- Gitlab (version control)
- Bookstack (wiki)
- Joplin (not a webapp, but sync server)
- Semaphore (does all of my infra updating via Ansible)
- Uptime-Kuma (monitoring/alerting)
Been thinking about adding NextCloud mostly for the Google Docs/MS Office replacement at some point.
But honestly most of my stuff is just for me, my family prefers to to use whatever commercial thing is out there. So I tend to limit things to infrastructure type things that are of personal interest to me alone.
load more comments
(4 replies)
Ombi for media requests.
view more: next ›