Hacker Newsnew | past | comments | ask | show | jobs | submit | ahriad's commentslogin

No Windows?!


I only tested it on WSL locally, there is bo way im connecting it to a live server without seeing the sourcecode.


This is exactly the gap I needed filled, a proper desktop panel that manages my Linux servers over SSH without installing anything on them.

Is it open source?


Thank you...

Source code will be released day after tomorrow. I will add a comment in this thread itself, as well as update the site with a link to Github.


Thank you, I tried it, so far working great. One small thing I hit: when I tried connecting to a server I'd never connected to before, it refused at first with no clear error. I had to SSH in from my terminal once to accept the host key signature, and then it worked fine. Minor, but thought I'd pass it along. Great work!


Thank you for testing. I'll fix the issue.. tomorrow.. too tired as of now.


They gated it to US providers only, fucking garbage


Not intentionally, we just haven't gotten around to expanding the provider list beyond what we use regularly.

There is ollama (local LLM) support in there.

But we'll probably expand it to everything pi-agent-core supports, just need some UI work.


I'm talking about setting up one provider for the entire OS not about BYOK per user. Right now only cloudflare AI gateway is supported and in it you hardcoded it to US providers. Plus your AI workers and from your model you only supporting two.


The code currently supports Anthropic, OpenAI, Gemini, Workers AI, and ollama as AI providers.

It additionally optionally supports sending all requests through Cloudflare AI Gateway as a proxy. The same set of providers is supported either way, but when you configure AI Gateway, we assume you intend to install side-wide API keys into the gateway. The idea here is that you're setting up the gateway for your entire company, and you want all users to use the same keys. So we no longer let individual users configure their own keys in this mode -- instead they can choose from among the providers you have configured site-wide.

We will expand the provider list soon.


I can't get an AI Gateway custom provider to work within CFOS (deployed to my CF account). No matter what custom model path I use in the cfos admin add provider mechanism, I get a model not found error when attempting to use the model in a conversation...


Yeah sorry, only the providers I listed are supported right now. We'll be widening support soon.


How does the cloudflare-based deployment of cfos get updated? If I "redeploy" will it get updates from cfos upstream? Eg, for when you add new stuff like this upstream..


We're adding an update function.

Didn't need it yet on day one. :)


Awesome!


How it compares to Fyne?


I use Lichess pwa, i prefer it over their app.


I use Kilocode Vscode extension, still can't give up the IDE


Love the way it looks, but sadly it's only Mac for now.


Thank you.

Linux / Windows is in plan, Otty will support those OS as well :)


Signed for the waitlist, hopefully i get to try it soon.


Edge is better, with only downside is that MS keep pushing Bing on its users.


... And all your searches, preferences and and browsing history is linked to your Microsoft + Windows account so you can be targeted by ads better..

I have no idea why people chose Edge over Brave or Vivaldi.


Because Brave have no way to store my data ( Passwords and bookmarks) for futures install.


I am like you were late to the AI party, and still find it hard to give up on coding and let the AI do everything, however i learned to trust the AI a little in the past few months.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: