Cloudron Forum

@loudlemur I didn't write the skills . But @james is a good candidate for feedback .

@robi said: @LoudLemur would it be more discoverable if it was published as a blog or docs site and then include llms.txt and llms-full.txt to make parsing easier for the agents? Thanks, @robi You can see the blog here: https://wanderingmonster.dev/blog/cloudron-packaging-assessment-toolkit/

I can second this, opencode was pretty straightforwards to get to work against an ollama running on a different machine locally. However my test system is absolutely too old to make proper use of it. At least I know it is theoretically possible if I would get a proper setup

@scooke It is a bit like buying a fancy car. Having the luxury of that car is brilliant when you are actually driving it but when you need to sleep or park, it is a total waste. Generally, the high end video cards with huge amounts of VRAM are a luxury for most people, who instead make do with buying a much more humble piece of kit. However, if instead of buying the hardware outright, they pay for the car only when they need it, they can enjoy a much more luxurious and capable experience. So many new AI applications are being created these days, I think I shall start a discussion thread on it and what Cloudron could do to support it.

@LoudLemur late reply not sure I understand your question so this answer may not be what you want but in picture form ... [image: 1768330247721-mermaid-diagram-2026-01-13-185009-resized.png]

@marcusquinn Thanks for that. Looks like my post is a duplicate of: https://forum.cloudron.io/topic/13141/litellm-openrouter-self-hosted-alternative-proxy-provides-access-to-openai-bedrock-anthropic-gemini-etc?_=1759700788590 (I posted 3 apps, checked the first one, and then forgot to check if the other two had already been requested!) @girish What is the procedure to merge this dupe with @jagan 's earlier request here? https://forum.cloudron.io/topic/13141/litellm-openrouter-self-hosted-alternative-proxy-provides-access-to-openai-bedrock-anthropic-gemini-etc?_=1759700788590 I can see the topic tools, merge option, but it is a bit confusing on how to paste/include jagan's thread.

@LoudLemur thank you !

Not a bad concept. Doesn't need dedicated hardware, might be able to run on the build/demo server or other sponsoring org. Integrate with CCAI upgraded to a distributed DB or some master/share topology to keep a running list of all custom packages successfully installed and make them available to everyone else.

People are wild about deep research. I hope we can put this into testing soon.

@BrutalBirdie Yup. Quite a few examples of Nani un-gagged: https://x.com/search?q=nani__ooo&src=typed_query

A new release of Firecrawl came available: https://github.com/mendableai/firecrawl/releases/tag/v1.11.0 There are lots of new improvements: Firecrawl v1.11.0 is here! Major Features Launched our Firecrawl Index Speed up scrapes 5x if opted in Improved Activity Logs View webhook events Active crawl management Fire Enrich Example (Open Source Clay) Community Java SDK and a lot more Features Improved Playwright tests and webhook test coverage Added GET /crawl/ongoing endpoint Introduced tag support in change tracking Added integration field to jobs and propagated through queue worker Parallel testing for runpod v2 and updated mu Ported queryIndexAtSplitLevel to RPC Enhanced SDK with index and missing parameters Removed redundant GCS check to improve performance Added credits_billed field across pipeline Enabled domain-level index splitting for better map querying Used index in search and extract operations Removed unused index columns Fixes & Improvements Fixed crawl pre-finishing logic Refactored callWebhook and added logging Improved index testing (FIR-2214) Fixed JS SDK tests Clarified scrape options usage in README Fixed missing PLAYWRIGHT_MICROSERVICE_URL in env example Improved concurrency limit notification emails Removed query param sanitization that broke extract

@scooke It is a fun deepfake of two US Presidents.

I like your song - what I’m afraid of is the increasing tsunami of trash music (much worse than now) that we’ll be faced with everywhere because companies can save a buck.

Yeah, it’s mind-boggling that this is still a problem unsolved. MusicBrainz is ok for some music styles but seriously shite for e.g. electronic music between 1990-2000, in particular for whitelabel releases… I use MP3Tag with various scripts and pull from the sources mentioned above as well as Beatport and Traxsource…

I've had reasonably good performance from ChatGPT. While not perfect, it's pretty good with patience. I've tried others but none are as good as ChatGPT .... in my experience (other's may vary).

You'd have to install GPT-llama and have it use a local LLM, and configure TypeBot to use an alternate AI API URL provided by GPT-llama.