<![CDATA[AI on Cloudron]]>AI is set to make a lot of advances and appear in unusual places. Cloudron might be able to help.

This thread is to stimulate discussion and form an early focal point for AI related ideas and news for those on Cloudron interested in this topic.

To get the ball rolling, there is now an AI search engine available:

https://you.com

You.com permits you to request that an application be added to improve search results. For example, you could ask that SepiaSearch, (PeerTube's content search) be included. Owncast is federated too, and you could request that be included as an application, also.

https://yousearch.canny.io/feature-requests/

]]>https://forum.cloudron.io/topic/8390/ai-on-cloudronRSS for NodeFri, 10 Apr 2026 15:37:29 GMTSun, 08 Jan 2023 10:45:46 GMT60<![CDATA[Reply to AI on Cloudron on Sun, 22 Feb 2026 18:51:29 GMT]]>You're going to be seeing alot more of these going forward.

Https://Cognitum.one is another impressive FPGA+rPi4 for fast, ultra low power local AI agents

]]>https://forum.cloudron.io/post/120588https://forum.cloudron.io/post/120588Sun, 22 Feb 2026 18:51:29 GMT<![CDATA[Reply to AI on Cloudron on Sun, 22 Feb 2026 14:38:00 GMT]]>https://taalas.com/products/

This new hardware is 40 times faster tokens/second than an Nvidia H200, much less expensive and consumes less power.

Demo:
https://chatjimmy.ai/

API access available on request

]]>https://forum.cloudron.io/post/120582https://forum.cloudron.io/post/120582Sun, 22 Feb 2026 14:38:00 GMT<![CDATA[Reply to AI on Cloudron on Fri, 06 Feb 2026 21:28:05 GMT]]>@staff

Shannon

This is a powerful ai security tool. You can point it at a website and after a couple of hours it can often find a way to break in, gain admin rights and take the database.

https://github.com/KeygraphHQ/shannon

]]>https://forum.cloudron.io/post/119810https://forum.cloudron.io/post/119810Fri, 06 Feb 2026 21:28:05 GMT<![CDATA[Reply to AI on Cloudron on Sat, 23 Aug 2025 21:29:48 GMT]]>@marcusquinn ooops, well caught, sorry ❎

]]>https://forum.cloudron.io/post/111956https://forum.cloudron.io/post/111956Sat, 23 Aug 2025 21:29:48 GMT<![CDATA[Reply to AI on Cloudron on Sat, 23 Aug 2025 21:21:59 GMT]]>@Eventsryoth FO spam wnkr.

@jdaviescoates @timconsidine you upvoting spam? 😂

@james Spambo links above 👆

]]>https://forum.cloudron.io/post/111955https://forum.cloudron.io/post/111955Sat, 23 Aug 2025 21:21:59 GMT<![CDATA[Reply to AI on Cloudron on Sat, 23 Aug 2025 06:26:13 GMT]]>Just tried out that AI search engine link you shared, and it’s surprisingly handy. I used it to pull up some obscure PeerTube stuff, and it actually picked up apps I didn’t expect. Also stumbled on an ai detector tool that really made the outputs feel more human—Humanizer AI or something like that. Made the text feel way more natural, like chatting with a person instead of reading a bot response. Definitely going to play around with it more.

]]>https://forum.cloudron.io/post/111920https://forum.cloudron.io/post/111920Sat, 23 Aug 2025 06:26:13 GMT<![CDATA[Reply to AI on Cloudron on Mon, 11 Aug 2025 13:17:45 GMT]]>AMD are hosting GPT-OSS-120B on hugging face and it is available gratis and fast:

https://huggingface.co/spaces/amd/gpt-oss-120b-chatbot

]]>https://forum.cloudron.io/post/111472https://forum.cloudron.io/post/111472Mon, 11 Aug 2025 13:17:45 GMT<![CDATA[Reply to AI on Cloudron on Tue, 08 Jul 2025 22:07:29 GMT]]>US$4000 mini super computer:
https://wccftech.com/nvidia-mini-supercomputer-the-dgx-spark-launches-this-month/

]]>https://forum.cloudron.io/post/109865https://forum.cloudron.io/post/109865Tue, 08 Jul 2025 22:07:29 GMT<![CDATA[Reply to AI on Cloudron on Sun, 06 Jul 2025 13:53:32 GMT]]>https://localai.io/basics/getting_started/

Would be super interesting to get this on Cloudron, they have a Docker port.

]]>https://forum.cloudron.io/post/109698https://forum.cloudron.io/post/109698Sun, 06 Jul 2025 13:53:32 GMT<![CDATA[Reply to AI on Cloudron on Mon, 26 May 2025 13:33:16 GMT]]>@necrevistonnezr Yeah, seen some not-good reading on demographic targeting by those capturing system admin permissions for cultural preference/detriment/targeting objectives.

Doesn't matter what these company leaders and politicians say or do, we all know the power admin permissions can give for the nefarious, and the power that vast amounts of personal data can give for tracking and algo tuning for mind-bending targets.

]]>https://forum.cloudron.io/post/107710https://forum.cloudron.io/post/107710Mon, 26 May 2025 13:33:16 GMT<![CDATA[Reply to AI on Cloudron on Sat, 24 May 2025 06:00:58 GMT]]>@marcusquinn it’s from an interview with one of the best-known network political activists in Germany Markus Beckedahl. The trained IT merchant created the online medium netzpolitik.org and is one of the founders of the re:publica conference. He is also co-founder of the Society for Freedom Rights, who bring lawsuits dealing with constitutional rigths to court on behalf of citizens. He blogs at digitalpolitik.de.
See https://www.heise.de/news/Interview-mit-Markus-Beckedahl-Musk-putscht-mit-Software-statt-Panzern-10379742.html (German)

]]>https://forum.cloudron.io/post/107610https://forum.cloudron.io/post/107610Sat, 24 May 2025 06:00:58 GMT<![CDATA[Reply to AI on Cloudron on Thu, 22 May 2025 21:07:06 GMT]]>@necrevistonnezr Interesting take. Companies are already more powerful that governments in many ways.

]]>https://forum.cloudron.io/post/107565https://forum.cloudron.io/post/107565Thu, 22 May 2025 21:07:06 GMT<![CDATA[Reply to AI on Cloudron on Thu, 22 May 2025 18:01:10 GMT]]>@LoudLemur said in AI on Cloudron:

Live Search is available on Grok's API without charge for a limited time for beta testing:

https://docs.x.ai/docs/guides/live-search

search through realtime data from 𝕏, the internet, trending news, RSS feeds,

In the US, Musk is simply walking into the authorities with a presidential power of attorney and copying everything he can. Once the files are copied, they end up in the system of Musk's X AI. Or they are poured into Palantir software with the aim of creating deportation lists.
So please boycott this PoS and his PoS endeavors.

]]>https://forum.cloudron.io/post/107548https://forum.cloudron.io/post/107548Thu, 22 May 2025 18:01:10 GMT<![CDATA[Reply to AI on Cloudron on Thu, 22 May 2025 07:59:33 GMT]]>Live Search is available on Grok's API without charge for a limited time for beta testing:

https://docs.x.ai/docs/guides/live-search

search through realtime data from 𝕏, the internet, trending news, RSS feeds,

]]>https://forum.cloudron.io/post/107521https://forum.cloudron.io/post/107521Thu, 22 May 2025 07:59:33 GMT<![CDATA[Reply to AI on Cloudron on Fri, 02 May 2025 20:35:18 GMT]]>@jdaviescoates I just tried it.
Qwen 3 is very good!

]]>https://forum.cloudron.io/post/106569https://forum.cloudron.io/post/106569Fri, 02 May 2025 20:35:18 GMT<![CDATA[Reply to AI on Cloudron on Fri, 02 May 2025 15:28:03 GMT]]>LLM VRAM Calculator

If you would like to know what models your VRAM can handle, you can check with this online tool:

https://apxml.com/tools/vram-calculator

]]>https://forum.cloudron.io/post/106562https://forum.cloudron.io/post/106562Fri, 02 May 2025 15:28:03 GMT<![CDATA[Reply to AI on Cloudron on Fri, 02 May 2025 12:27:43 GMT]]>Apparently this is one of the best open source models yet:

https://qwenlm.github.io/blog/qwen3/

]]>https://forum.cloudron.io/post/106551https://forum.cloudron.io/post/106551Fri, 02 May 2025 12:27:43 GMT<![CDATA[Reply to AI on Cloudron on Fri, 02 May 2025 12:11:30 GMT]]>AI Search with Lepton
This helps you have an ai language model which makes internet searches.

An interesting feature that Cloudron might like is its one-click deployment tool.

https://github.com/leptonai/search_with_lepton?tab=readme-ov-file

]]>https://forum.cloudron.io/post/106548https://forum.cloudron.io/post/106548Fri, 02 May 2025 12:11:30 GMT<![CDATA[Reply to AI on Cloudron on Fri, 02 May 2025 12:10:10 GMT]]>StabilityMatrix

If you use a lot of inferencing software, one thing this can do is have the models kept in one folder, which saves storage and bandwidth.

https://github.com/LykosAI/StabilityMatrix/releases/tag/v2.14.0

]]>https://forum.cloudron.io/post/106547https://forum.cloudron.io/post/106547Fri, 02 May 2025 12:10:10 GMT<![CDATA[Reply to AI on Cloudron on Fri, 18 Apr 2025 23:12:06 GMT]]>RAG with documents in a Docker
https://github.com/SciPhi-AI/R2R

]]>https://forum.cloudron.io/post/105944https://forum.cloudron.io/post/105944Fri, 18 Apr 2025 23:12:06 GMT<![CDATA[Reply to AI on Cloudron on Wed, 16 Apr 2025 20:52:47 GMT]]>For those that want to experience how simple it is to build an agent and imagine implementing it on Cloudron.. read on: https://github.com/voxmenthe/coding-agent/blob/main/tutorial.md

]]>https://forum.cloudron.io/post/105848https://forum.cloudron.io/post/105848Wed, 16 Apr 2025 20:52:47 GMT<![CDATA[Reply to AI on Cloudron on Mon, 14 Apr 2025 00:30:02 GMT]]>It would be great to have additional MCP support in OWUI.
@girish or @nebulon can you take a look?

It requires a few things added to the package it seems.

https://github.com/open-webui/openapi-servers

Also, the import functions feature seems to be broken, although one can use the +
Add function manually and copy/paste the code from https://openwebui.com/functions

]]>https://forum.cloudron.io/post/105605https://forum.cloudron.io/post/105605Mon, 14 Apr 2025 00:30:02 GMT<![CDATA[Reply to AI on Cloudron on Thu, 03 Apr 2025 15:09:49 GMT]]>@LoudLemur said in AI on Cloudron:

MCP (Model Context Protocol)
https://modelcontextprotocol.io/introduction

According to the CEO of Anthropic, this is what is going to be writing 90% of code in 6 months, and almost all of it by the end of the year.

MCP has been adopted by OpenAI and will hence be the de-facto standard https://techcrunch.com/2025/03/26/openai-adopts-rival-anthropics-standard-for-connecting-ai-models-to-data/

In a post on X on Wednesday, OpenAI CEO Sam Altman said that OpenAI will add support for Anthropic’s Model Context Protocol, or MCP, across its products, including the desktop app for ChatGPT. MCP is an open source standard that helps AI models produce better, more relevant responses to certain queries.

]]>https://forum.cloudron.io/post/105105https://forum.cloudron.io/post/105105Thu, 03 Apr 2025 15:09:49 GMT<![CDATA[Reply to AI on Cloudron on Thu, 03 Apr 2025 00:37:58 GMT]]>@jdaviescoates Thanks again for the correction.

]]>https://forum.cloudron.io/post/105040https://forum.cloudron.io/post/105040Thu, 03 Apr 2025 00:37:58 GMT