Ollama's new app • Hacker News Board

Re: Ollama's new app

#81

Post by KoftaBob » Thu, Jul 31, 2025, 1:34 AM UTC

In addition to what others have said, I've had great experiences with LobeChat: https://github.com/lobehub/lobe-chat

Re: Ollama's new app

#82

Post by egonschiele » Thu, Jul 31, 2025, 1:35 AM UTC

apitman wrote: post #38

I've been on something of a quest to find a really good chat interface for LLMs. Most import feature for me is that I want to be able to chat with local models, remote models on my other machines, and cloud models (OpenAI API compatible). Anything that makes it easier to switch between models or query them simultaneously is important. Here's what I've learned so far: * Msty - my current favorite. Can do true simultan…

Build your own! It's a great way to learn, keeps you interested in the latest developments. Plus you get to try out cool UX experiments and see what works. I built my own interface back in 2023 and have been slowly adding to it since. I added local models via MLX last month. I'm surprised more devs aren't rolling their own interface, they are easy to make and you learn a lot.

Re: Ollama's new app

#83

Post by spacecadet » Thu, Jul 31, 2025, 1:39 AM UTC

Im surprised it took this long. I vibe coded the same interface last year using electron... just not Ollama because there are just better architectures/pipelines...

Re: Ollama's new app

#84

Post by nguyenkien » Thu, Jul 31, 2025, 1:41 AM UTC

IceWreck wrote: post #4

Why not Linux? The UI looks to be some kind chrome based thingy - probably electron - should be easy to port to Linux. Also is there a link to the source?

> Download Ollama’s new app today on macOS and Windows.

> For pure CLI versions of Ollama, standalone downloads are available on Ollama’s GitHub releases page.

Sound like closed source. Plus, As I check, the app seem to be tauri app, as it use system webview instead of chromium.

Re: Ollama's new app

#85

Post by rasengan0 » Thu, Jul 31, 2025, 1:42 AM UTC

Enjoy Ollama CLI so the output can be redirected or piped; definitely a useful feature.

Re: Ollama's new app

#86

Post by peterb » Thu, Jul 31, 2025, 1:48 AM UTC

apitman wrote: post #38

I've been on something of a quest to find a really good chat interface for LLMs. Most import feature for me is that I want to be able to chat with local models, remote models on my other machines, and cloud models (OpenAI API compatible). Anything that makes it easier to switch between models or query them simultaneously is important. Here's what I've learned so far: * Msty - my current favorite. Can do true simultan…

gptel in emacs does this. You can run the same prompt against different models in separate emacs windows (local or via api w/ keys) at the same time to compare outputs. I highly recommended it. https://github.com/karthink/gptel

Re: Ollama's new app

#87

Post by bakugo » Thu, Jul 31, 2025, 1:48 AM UTC

apitman wrote: post #38

I've been on something of a quest to find a really good chat interface for LLMs. Most import feature for me is that I want to be able to chat with local models, remote models on my other machines, and cloud models (OpenAI API compatible). Anything that makes it easier to switch between models or query them simultaneously is important. Here's what I've learned so far: * Msty - my current favorite. Can do true simultan…

Open WebUI is definitely what you want. Supports any OpenAI-compatible provider, lets you manually configure your model list and settings for each model in a very user-friendly way, switching between models is instant, and it lets you send the same prompt to multiple models simultaneously in the same chat and displays them side by side.

Re: Ollama's new app

#88

Post by nguyenkien » Thu, Jul 31, 2025, 1:51 AM UTC

nicce wrote: post #19

IceWreck wrote: post #4

Why not Linux? The UI looks to be some kind chrome based thingy - probably electron - should be easy to port to Linux. Also is there a link to the source?

Electron… wonder how this can be marketed as native then.

Also, this is not electron app. It does use system webview thought.

Re: Ollama's new app

#89

Post by kanestreet » Thu, Jul 31, 2025, 1:52 AM UTC

mchiang wrote: post #65

behnamoh wrote: post #39

Earlier quoted context omitted.

not too late for VC money-grab tho. Edit: I hope I'm wrong about this. Thanks for clarifying.

Ben, we've had private conversations about this previously. I don't see any VC money grab nor am I aware of any. Building a product that we've dreamed of building is not wrong. Making money does not need to be evil. I, and the folks who worked tirelessly to make Ollama better will continue to build our dreams.

I mean you’re a YC backed startup soo it’s not like it’s out of the question lol

Re: Ollama's new app

#90

Post by doctoboggan » Thu, Jul 31, 2025, 1:56 AM UTC

jonahbenton wrote: post #56

apitman wrote: post #38

I've been on something of a quest to find a really good chat interface for LLMs. Most import feature for me is that I want to be able to chat with local models, remote models on my other machines, and cloud models (OpenAI API compatible). Anything that makes it easier to switch between models or query them simultaneously is important. Here's what I've learned so far: * Msty - my current favorite. Can do true simultan…

OpenWebUI is what you are looking for from a usability perspective. Supports many models chat.

Last I tried OpenWebUI (A few months ago), it was pretty painful to connect non-OpenAI externally hosted models. There was a workaround that involved installing a 3rd party "function" (or was it a "pipeline"?), but it didn't feel smooth.

Is this easier now? Specifically, I would like to easily connect anthropic models just by plugging in my API key.