Double upvote!
Double upvote!


Rules 1, 2 and 6


Interesting! I’ve seen the sidebar but not thought of much advantage from it. I’ll take another look. Model/provider change is a breeze, I just assumed Claude would do the same but maybe they want to make it harder to leave their models? Workspaces? Sounds interesting - gotta check it out.
I just discovered how easy it is to view/switch sessions in opencode.


I use opencode, have seen Claude but never used it. What are some examples of things opencode does that Claude doesn’t?


I use Cirrus because I love its widget, and it does have rain radar. It’s GPL-3.0


I i think it’s great that you’re spreading the word about the fediverse and helping get people off of big data.
You might consider using a youtube alternative for your channel, perhaps a PeerTube instance.


Is this basically a Kokoro alternative? Does anyone have experience with both and can offer compsrisons?


I don’t think it means what he thinks it means.


Ah.
I use Cirrus becau I love its ingenious widget: it shows the next 12 hours of weather (not temperature) in a tiny space that’s super easy to read.



I don’t care if AI was used in its creation. I do care if it’s FOSS/libre.
And also, it’s a bit weird to me that copying YouTube’s UI is considered good. I havent used YouTube in a long time, but I recall there being some good aspects and some bad. Why not create your own vesion of a UI?


I agree that more options is a good thing, and that activitypub would be a plus. But FYI, I wont be using it because of the license. I use only FOSS whenevr possible.


Server01: 64 Server02: 19 Plus a bunch of sidecar containers solely for configs that aren’t running.


I was going to submit Journiv for review at It’s Really FOSS but one of their conditions to accept a project is that the project claims to be open source - and I can’t find anywhere that Journiv claims to be open source!
In this discussion on Journiv’s github Swalab Tech says:
You’re absolutely right, Journiv’s core is source available, and it currently includes a built Flutter web version client…As of now there are no plans of making client’s source available.
…
I can understand your concerns so let me answer them in detail.
First thing first, why is frontend code not open source:
…


Fyi, you could consider the app server as source available, but the web client is proprietary and closed and its license probihibits reverse engineering and the like.


Journiv looks pretty cool and i want to try it, but I only use FOSS software whenever possible and Journiv is not under an open source license. The debatably-FOSS license covers the server and prohibits commercial use, which i dont like but maybe could live wirh, but the web client’s license is not debatable: it is clearly not FOSS because it’s proprietary software owned and copyrighted by Swalab Tech and is not licensed under the PolyForm Noncommercial License 1.0.0.
Here’s an LLM’s summary of why it’s not FOSS: The PolyForm‑Noncommercial 1.0.0 is a non‑commercial license that blocks any commercial use of the code without a separate written agreement. That places it near the bottom of most freedom scales, such as the Open Source Definition or the Free Software Definition. FOSS people would point out that the licence allows use, copy and modification for personal or non‑commercial purposes but disallows commercial deployment or monetised use, so it fails the “freedom” test. The licence also requires contributors to assign all rights to the owner, which removes copyright retention and any freedom to license derivatives. Because the web client is explicitly excluded from the licence and cannot be hosted or redistributed as part of a service, the package is effectively a hybrid licence that is not accepted as open source. On a freedom scale of 0 to 100, it would be roughly 10–20, and FOSS communities would typically call it “not open source” or “proprietary‑style” and advise against using it in a truly FOSS project.


Thanks for explaining. 🙂


I’d assume that many services were created to send an activation link via email and don’t know how to talk to a Matrix server. In those cases, do they email their activation link to a service or proxy that then communicates it to the appropriate matrix server/account/room?


Not positive, but I think you left in a reference to real info (twilightparadox.com) instead of “example-fying” it (mydomain.com), in the paragraph just before section 4:
For example say I have home-assistant running on a Pi with the local address 192.168.0.11, I could create a subdomain named ha that has the value mysub.twilightparadox.com then create the following nginx config
server{ listen 80; server_name ha.mydomain.com; resolver 192.168.0.1; location / { proxy_pass http://192.168.0.11/; } }When nginx sees a request for ha.mydomain.com it passes it to the address 192.168.0.11 port 80.
I’m my experience, running Ollama locally works great. I do have a beefy GPU, but even on affordable consumer grade GPUs you can get good results with smaller models.
So it technically works to run an AI agent locally, but my experience has been that coding agents don’t work well. I haven’t tried using general AI agents.
I think the amount of VRAM affordable/available to consumers is nowhere near enough to support a context length that’s necessary for a coding agent to remain coherent. There are tools like Get Shit Done which are supposed to help with this, but I didn’t have much luck.
So I’m using OpenCode via OpenRouter to use LLMs in the cloud. Sad that I can’t get local-only to work well enough to use for coding agents, but this arrangement works for me (for now).