Live data from Hacker News

Show HN: Rowboat – Open-source, local-first alternative to Claude Desktop

github.com

111–120 of 121 posts

Re: Show HN: Rowboat – Open-source, local-first alternative to Claude Desktop

#112

Earlier quoted context omitted.

Instead of having to define what “local-first” means to you personally you should emphasize that the data lives on your local machine. For some example messaging take a look at how Apple is marketing their new Siri AI.

That's fair - "your data lives on your machine as plain files" is the concrete claim, and something we should lead with. Will take a look at how Apple frames it, thanks.

You have completely misused and re-purposed this term. The common interpretation is that the software will continue to function without an internet connection which is not the case for your product.

You should choose different language.

Re: Show HN: Rowboat – Open-source, local-first alternative to Claude Desktop

#113

I gave this a real shot, but I found it impossible to use the email client. There are basic things like collapsing replies (in a conversation with multiple lawyers no less, damn do they love their email signatures) are extremely important. Without them, it makes scannning and replying to email, even withe aid of AI, impossible. Really love the whole idea and I hope it gets more usable.

Thanks for trying it out and reporting this.

We looked into the specific issue you mentioned. Collapsing replies does exist in the product, but we found it doesn't work for emails sent from Outlook (our guess on why you might have faced this). We are fixing this in the next release, shipping this week. Hope you give it a try.

Re: Show HN: Rowboat – Open-source, local-first alternative to Claude Desktop

#114

Earlier quoted context omitted.

Update. It has a lot of potential ( and it did get better since I remember it from the original ShowHN ). There are pieces missing, but this may be a project to which I can happily contribute the pieces I think are missing.

That's great to hear! Would love your contributions. Please feel free to find us or DM me on Discord if you want to have a quick chat on anything.

[flagged]

Re: Show HN: Rowboat – Open-source, local-first alternative to Claude Desktop

#115

Earlier quoted context omitted.

I have a hunch that both OpenAI and Anthropic are building towards this very quickly. It's one of the startup ideas that will be killed overnight when it's "officially" launched. Claude Tag was just released which lets Claude participate in chats in Slack - only a matter of time until they move those chats out of Slack and into their own platform.

That hunch is probably right - the labs are likely building towards this. However, our bet is that in knowledge work the labs don't have a structural advantage: the model isn't the product there, unlike coding where it mostly is - and even in coding, opencode and others are gaining real traction. What they do have is funding and distribution, but that's the same advantage every incumbent has against every startup. Th…

I've heard that refrain ("we can switch models so we won't be obsolete!") a hundred times, but it doesn't hold any water for me. OpenAI and Anthropic command such a large percentage of LLM usage that it doesn't really matter which one implements your product - either way, you're screwed.

Your end users literally do not care what model you use behind the scenes or if you're using "the right tool for the job".

> Claude still doesn't have image generation

What? It has for years. Go ask it right now.

Re: Show HN: Rowboat – Open-source, local-first alternative to Claude Desktop

#116

What I'm looking for right now is a tool like this that lets more than one person participate in the conversation: right now Claude Code and similar tools are great for working alone, but I'd like to effectively pair-prompt with a partner who can see what's happening, and take turns steering the conversation. Can Rowboat do this? If not, does anybody know a harness that can?

Have you tried using a purpose built pair programming app? Essentially these are tools with low latency screen sharing and remote control. Then you can pair-prompt in a call.

Zed's original reason for being was collaborative programming

https://zed.dev/docs/collaboration/overview

Not sure if the agent stuff is shared in the "channels", though.

Re: Show HN: Rowboat – Open-source, local-first alternative to Claude Desktop

#117

Earlier quoted context omitted.

That hunch is probably right - the labs are likely building towards this. However, our bet is that in knowledge work the labs don't have a structural advantage: the model isn't the product there, unlike coding where it mostly is - and even in coding, opencode and others are gaining real traction. What they do have is funding and distribution, but that's the same advantage every incumbent has against every startup. Th…

I've heard that refrain ("we can switch models so we won't be obsolete!") a hundred times, but it doesn't hold any water for me. OpenAI and Anthropic command such a large percentage of LLM usage that it doesn't really matter which one implements your product - either way, you're screwed. Your end users literally do not care what model you use behind the scenes or if you're using "the right tool for the job". > Claude…

Just did - asked Claude Opus 4.8 in Claude Desktop to generate an image of a horse. It drew an SVG by hand in code and said (verbatim): "I drew it by hand in code, not with an AI image generator. There's no diffusion/photo image model wired into this session."

On the labs: agreed that end users don't care about the model - only that the job gets done well, which is our argument too. At any point some model is best at a given job, so any single lab is behind for a portion of time on a portion of tasks.

Re: Show HN: Rowboat – Open-source, local-first alternative to Claude Desktop

#118

Earlier quoted context omitted.

I've heard that refrain ("we can switch models so we won't be obsolete!") a hundred times, but it doesn't hold any water for me. OpenAI and Anthropic command such a large percentage of LLM usage that it doesn't really matter which one implements your product - either way, you're screwed. Your end users literally do not care what model you use behind the scenes or if you're using "the right tool for the job". > Claude…

Just did - asked Claude Opus 4.8 in Claude Desktop to generate an image of a horse. It drew an SVG by hand in code and said (verbatim): "I drew it by hand in code, not with an AI image generator. There's no diffusion/photo image model wired into this session." On the labs: agreed that end users don't care about the model - only that the job gets done well, which is our argument too. At any point some model is best at…

Oh snap, you're right that Claude can't generate images. All of these chat interfaces blur together in my head these days haha
Post reply on HN