Cloudron Forum

@Stefan EspoCRM probably your best bet, you can configure it to do anything you need.

@joseph Yup, agreed.

I've been having issues with email deliverability to Google & Microsoft servers.

It seems that as well as now needing a PTR record for the ip6 on the host, we also need AAAA records for the subdomain (mail. in my case), to point to that same ip6 address (any DNS proxying disabled, too).

I only just learned of the ip6 option on the Network settings page. Perhaps there should be a warning when that's not set?

Probably something Cloudron DNS setup should be able to check and automate? @girish @nebulon

@marylou In the meantime, maybe better options with a WordPress plugin?

• https://www.myeventon.com/

• https://nextcloud.com/assistant/

Just wondering if anyone running Local AI with Cloudron Nextcloud?

Or connected to AI services?

Still think this would be a high-value app. Latest updates are great. Solid UX. Encrypted. Decentralised. What's not to like?

Seems a bit mean that the open-source version doesn't allow for more than one Admin user when you can just share the Owner login credentials with other Admins to do the sensible things that Admins need to do.

Be interested if anyone finds any other workaround for this deliberate limitation.

Updated the screenshots above, as it's developed a lot since I first posted this.

Does seem like a very high value win if we can get this packaged here.

Cloudron isn't hosting any apps to offer as SaaS, it's just scripts for self-hosting, so that feels to be within the license terms.

Great find!

Needs some screenshots:

@girish Any chance of adding popular python packages to this Cloudron App?

Quite a few functions here needing them: https://openwebui.com/functions

Eg:

• https://openwebui.com/f/fovendor/flux_inpainting
• https://openwebui.com/f/fovendor/flux_gen

@p44 Open WebUI is just an interface (don't bother with the local Ollama on a VPS without a GPU).

Yes, you have to create an account with each API service to get a key, and usually deposit a few dollars for them to work.

Short-term cost, but long-term saving from having subscriptions for thing you won't use that much.

So far I've setup the Functions / Pipes for: OpenAI, Anthropic V2, Google GenAI, Deepseek, Grok.

All pretty much the same process, and then gives you the ability to quickly compare responses from multiple models in the same chat window.

Looks cool. Could do with some screenshots:

@p44 I think it's worth the effort, as the app actually has a ton of potential when setup, it's kinda like poe.com but more, because you can get into web scraping, content repurposing, lots of things with models, tools, functions.

Can confirm, this works really well. Just search for the model you want, eg: "anthropic", and pick the most popular: https://openwebui.com/functions?query=

Then it's a bit of copy/paste (Name, Description/Content) into Open WebUI > Admin Panel > Functions > +

Recommend you stick at it. It does work, and there's quite a bit more to this app that meets the eye. Worth figuring out, it's not technical, just a but unfamiliar way of working at first.

@NCKNE V Interesting. Great share. Thanks you!

@LoudLemur Thanks. I'm using Shottr, and just found the resize x0.5 option, so that seems to work.

@NCKNE Thanks. Not seen that before. I'm not a fan of the WebUI interface, but it it's possible, it is highly valuable! Thanks for the pointer, I'll give it a try.

@jdaviescoates Tired, impatient, and time-sensitive. Sorry!

If you get anything from me here it is always to save time, our most precious resources, and I have a lot less of it left them most.

Doubly impatient when I have to resize screenshots up upload them to this NodeBB setup, but here we are...

• https://www.librechat.ai/docs/features/agents
• https://www.librechat.ai/docs/features/agents#sharing-and-permissions

It's all there in the docs.

This is an "Agent" (what Poe.com calls a "App". You only have to use Poe.com for 30 seconds to get what they are.)

Create these, and have a server-hosted (Cloudron-hosted) instance of LibreChat, and now your pre-trained "Agents" (in LibreChat lingo), can be shared.

This feature just doesn't exist in OpenWebUI, and I can't see it coming any time soon.

The difference to me with having LibreChat on Cloudron is probably $100/month plus compared to doing the same with Poe.com. Plus not having my knowledge training setups locked up in someone else's SaaS.

Plus, frickin hours, and hours, and hours of long-hand wasted time teaching a team how to all setup the same pre-trained chat, and keep updating it as it is refined — when this is an already a solved problem but LibreChat Agents and sharing those Agents among users on the same server. Not conversations. Agents. AKA Apps in Poe.com language.

With the bridge between problem and solution apparently being persuasion that there is a LOT more value to this in LibreChat, and this specific highly valuable time, money and settings-saving thing value is not in OpenWebUI.

If you don't work with a team, you probably don't need it.

If you work with a team, and are going to be using AI, then this has a lot of value that I'm not seeing anywhere else.

That's the use-case and value-proposition.

Is there anyone left in this thread that still doesn't get it?

@jdaviescoates Yeah. I can see why people look at the basics of it being a chat app, and think they compare.

There's so many man-hours that are saved with collaborative tools.

When you setup a collaborative tool on Poe.com, you are locking that entire team into it a subscription to it for life to continue to use.

If we had the same with LibreChat on Cloudron, all those processes are now owned and self-hosted, with no per-user pricing, to utilise and get value from.

I don't doubt WebUI is useful, and great it already packaged.

We just missed out on having the collaborative LibreChat, so I have to make a value case for it, so it's not dismissed as similar enough to not be a priority.

If collaboration had no value, I can use LibreChat, locally — but the ability to share identical, maintained, pre-trained knowledge apps/agents with LibreChat is so damn valuable if you work with a team.

The biggest overhead with all teamwork is "explaining". Pre-trained LibreChat agents mostly eliminate that explaining and updating everyone overhead, and gives an interface to consistent input/output for all users.

AI is notoriously inconsistent and lacking in recent or private knowledge.

LibreChat solves all of this, when hosted on a server for multiple users to share.