Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claudia – Desktop companion for Claude code

claudiacode.com

Post reply on HN
Print view View original

231–240 of 245 posts

Re: Claudia – Desktop companion for Claude code

#231

Post by anoek »

alphazard wrote: post #11

Does this sandbox the agents? All I want is a way to keep the agents from writing to and reading from arbitrary places on the filesystem. I want that enforced using operating system primitives rather than a pinky promise with an LLM. It already worries me that the Cursor agents occasionally try to perform operations with full absolute paths, which they wouldn't be able to know if they were properly sandboxed to the c…

I wrote https://github.com/anoek/sandbox for that exact purpose, it uses overlayfs to protect your system from LLMs making unwanted changes and optionally masks out places you don't want it to be able to read from.

Re: Claudia – Desktop companion for Claude code

#233

Post by unethical_ban »

omneity wrote: post #163
mikestaas wrote: post #123

Earlier quoted context omitted.

Roo code in vs code, and qwen coder in lm studio is a decent local only combo.

Strongly seconding Roo Code. I am using it in VSCodium and it's the perfect partner for a fully local coding workflow (nearly 100% open-source too so no vendor is going to pry it from my hand, "ever"). Qwen Coder 30B is my main driver in this configuration and in my experience is quite capable. It runs at 80 tok/s on my M3 Max and I'm able to use it for about 30-50% of my coding tasks, the most menial ones. I am expl…

Thanks to both for recommending roo, it is the closest I've gotten. I still can't get it to work the way I expect.

When I use qwen coder 30B directly to create a small demo web page, it gives me apl the files and filenames. When I do the same thing in roo chat (set to coder) and it runs around in circles, doesn't build multiple files and eventually crashes out.

Re: Claudia – Desktop companion for Claude code

#234

Post by Uehreka »

dostick wrote: post #170

The desktop companion is not the problem that needs to be solved. It seems that every developer who successfully used CC and go on to create some tool for it is doing it for the wrong reasons or because they have to do just something. CC development is not just development, not all types of development. it’s frontend JS based , and it’s backend development. Only those scenarios work. Try creating native desktop or mo…

> CC development is not just development, not all types of development. it’s frontend JS based , and it’s backend development. Only those scenarios work.

> Try creating native desktop or mobile app and it’s like a swamp of trial and error.

I had it build an Android app and embedded code for a BLE peripheral at the same time, tailing the logs from each to debug issues. It worked great.

I generally avoid stating in concrete terms what Claude Code “can’t” do. Especially since it keeps getting new built-in features (like the ability to background shell processes and then tail their logs later) that often fix issues people talk about having had a month ago.

Re: Claudia – Desktop companion for Claude code

#235

Post by belter »

andreashaerter wrote: post #225

Trademark action incoming in 3, 2, 1, ... and deservedly so. They even copied their graphic language. "Claudia" closely resembles "Claude," especially in the software/AI space. * IR: https://register.dpma.de/DPMAregister/marke/registerIR?AKZ=1... * EU: https://register.dpma.de/DPMAregister/marke/registerHABM?AKZ... Edit: And the "getAsterisk" organization at https://github.com/getAsterisk/claudia and https://asterisk…

McDonalds v McDowells all over again: https://www.youtube.com/shorts/afXxlaUShPA

Re: Claudia – Desktop companion for Claude code

#236

Post by rovr138 »

CjHuber wrote: post #217
commandar wrote: post #29

On the one hand, it's good that we're seeing a lot of exploration in this space. On the other, the trend seems to be everyone developing a million disparate tools that largely replicate the same functionality with the primary variation being greater-or-lesser lock-in to a particular set of services. This is about the third tool this week I've taken a quick look at and thought "I don't see what this offers me that I d…

I mean technically you can use Claude Code Router and then use any LLM with Claudia

Have you tried claude code router? Looking at all the options, trying to see what would be a good configuration example.

Re: Claudia – Desktop companion for Claude code

#237

Post by lexarflash8g »

I use WARP.dev CLI terminal that works as a coding agent and has all the models not just from Anthropic and works very similarly to all the CLI Coding Agents (Claude code, Codex, Jules, etc.)

It works very fast compared to Cursor -- biggest limitation is that it doesn't have workspaces where you can get context from several repos for building your application.

MCP servers also work as well just a little more complex.

Re: Claudia – Desktop companion for Claude code

#238

Post by imuakame »

lexarflash8g wrote: post #237

I use WARP.dev CLI terminal that works as a coding agent and has all the models not just from Anthropic and works very similarly to all the CLI Coding Agents (Claude code, Codex, Jules, etc.) It works very fast compared to Cursor -- biggest limitation is that it doesn't have workspaces where you can get context from several repos for building your application. MCP servers also work as well just a little more complex.

Warp can actually index your codebases and cross-reference across indexed repos for context: https://docs.warp.dev/code/codebase-context#multi-repo-conte... For example, if you reference the example repo in your prompt, the agent will use that in what it's working on in your current repo in coming up with code diffs and running commands

Re: Claudia – Desktop companion for Claude code

#239

Post by Aeolun »

dgunay wrote: post #164
Aeolun wrote: post #143

Earlier quoted context omitted.

I think the thing is that most of the people implementing stuff for Claude have already realized it’s just the best option available for… basically everything. I’ve switched to different models before, but I always come back to Sonnet or Opus for doing anything sensible.

Claude may be arguably the best model, but why decide unilaterally for your users that they _have_ to use it? If there's no particular feature that only Claude offers, this is just needless vendor lock-in. And what happens if another lab releases a model that suddenly trounces Claude at coding? Your users will leave for an app that supports the new hotness, and you won't be able to keep them because of a short-sighte…

> Claude may be arguably the best model, but why decide unilaterally for your users that they _have_ to use it?

What a ridiculous proposition. It’s me making the app right? You getting to use it (if you want) is purely incidental. If you never use it because it doesn’t support anything but claude, that’s not something I consider a problem.

Re: Claudia – Desktop companion for Claude code

#240

Post by csabakissi »

lexarflash8g wrote: post #237

I use WARP.dev CLI terminal that works as a coding agent and has all the models not just from Anthropic and works very similarly to all the CLI Coding Agents (Claude code, Codex, Jules, etc.) It works very fast compared to Cursor -- biggest limitation is that it doesn't have workspaces where you can get context from several repos for building your application. MCP servers also work as well just a little more complex.

I simply tell Warp where to find the content. For example.. I created a Chrome extension boilerplate which sits in its own directory.

Then, when I create a new one, I tell Warp to use this folder as the boilerplate for the new one. It works perfectly.

Post reply on HN