@james said in Nextcloud All-In-One (AIO): Hello @hgieldanowski and welcome to the Cloudron forum Glad to be here

I would love to have PayloadCMS here!

AnythingLLM has had enormous improvements since it was first requested by @TheMoodBoardz In particular, support for agents and RAG has been advanced to try and keep up with the huge demand in this area. Installing AnythingLLM on GNU+Linux now automatically installs Ollama, too. Here is a summary of the main advances. If you want to make RAG and ai agents easier, AnythingLLM would be a great application to support. Comparison between v1.0Based.0 and v1.9.0 of AnythingLLM, here are the most significant changes categorized into key areas: Agent System Overhaul Complete redesign of the agent experience with real-time streaming tool calls Agents can now download and ingest web files (PDF, Excel, CSV) during conversations All providers and models support agentic streaming capabilities Local LLM Integration Added Microsoft Foundry Local integration for Windows/MacOS (free local LLM solution) Linux now includes Ollama (0.11.4) built-in for immediate local LLM support ARM64 support for both Linux and Windows platforms Platform & Infrastructure Expanded Linux support with automatic apparmor rules and .desktop file creation NVIDIA NIM being phased out in favor of newer solutions Upgraded core Electron version for improved stability UI/UX Improvements Model swap capability during chats (Ctrl/Cmd+Shift+L) Workspace and thread searching in sidebar System prompt version tracking and restoration Enhanced mobile support with Android beta app Developer Features MCP (Model Context Protocol) compatibility No-code AI agent builder Enhanced API endpoints and developer tools Multi-modal support for both open and closed-source LLMs Internationalization Added Portuguese and Estonian translations Improved multi-language OCR support Expanded localization coverage The update represents a massive leap from the initial version, transforming from a basic document chat system to a comprehensive AI agent platform with robust local operation capabilities and extensive customization options.

+1 Lack of GlitchTip (or any other Sentry alternative) is what prevents me from switching over to Cloudron from PikaPods currently.

I also use seafile and would love to have it on my cloudron

@nebulon Nice! I would be interested in both, vector and raster tile server

@markjames anyone can build and install packages. there is a tutorial at https://docs.cloudron.io/packaging/tutorial/ . the source code of the package is at https://git.cloudron.io/playground/supertokens-app . Let us know if you need help building / installing on your Cloudron.

@SansGuidon said in AFFiNE - open-source Notion, Miro, Monday, Outline, Appflowy alternative: Yet we are not the only ones suffering from this product making things unnecessarily more complicated Yes, people are struggling. But this is still Alpha software (version 0.25.5 right now) so some instabilities are permissable. It does look pretty powerful but they are open about AI features on self-hosted not having feature parity yet. @SansGuidon said in AFFiNE - open-source Notion, Miro, Monday, Outline, Appflowy alternative: selfhosted=true parameter This is already passed in the package

It seems that yt-dlp is now requiring a js runtime https://github.com/yt-dlp/yt-dlp/issues/15012 I didn't adapt yet, it's on my low-priority to do list so I'll happily reuse anyone's solution instead

@timconsidine had a quick play with it yesterday, i think worth a look. I suggest using Qwen, AugmentCode or similar CLIs and asking them to install it locally and get it working. Then ask them for ideas on what it can do, and ask it to setup some example processes. I can see more future in this than n8n. I think it'll speak to you once you get your head around the GUI being more of a monitor for what you've created, than a workbench for designing it. Doesn't have any of the restrictions of n8n, so if it can be done with Python, it can be designed and managed with Agno.

Seems to have evolved a lot since I first posted this. Worth another look?

[image: 1762909849444-do-it-ben-stiller.gif] A touch rude, but I'd also love to see this!

@timconsidine But looks like it would simply run in the LAMP stack

@jdaviescoates Thanks and done

This would work beautifully with my cloudron proxy app behind a vpn setup. Might give packaging this one a go.