I have a use case somewhat similar to this where I need to convert the content of PDFs in a non standard format to a specific YAML format. I currently use Haiku for this and am pleased with the accuracy/speed (I haven't tried scanned PDFs yet tho) however I've been thinking about fine tuning a small Qwen model for just this task. I can't yet justify the effort to investigate it but I imagine it could work out.
In my use case for small models I typically only generate a max of 100 tokens per API call, with the prompt processing taking up the majority of the wait time from the user perspective. I found OAI's models to be quite poor at this and made the switch to Anthropic's API just for this.
I've found Haiku to be a pretty fast at PP, but would be willing to investigate using another provider if they offer faster speeds.
My situation was nowhere similar to yours or OP’s, but back when I was dealing with depression a church group I was volunteering with was one of the main factors in my recovery. I met people that really helped me change for the better and helped give me at least a temporary purpose in life.
There were some days when I didn’t want to do anything, but due to my obligations as a formal member of the group I had to show up. This really helped me since it really forced me to get out and actually do something and not doomscroll YouTube Shorts.
I don’t want to make this specific to any religion or belief system, but in my experience groups centered around a place of worship and focused on service are some of the best ways to create social bonds as an adult. There are also other men’s groups that aren’t religious that fit this: Lions Club, Rotary Club, Veterans Outposts.
Yesterday I test ran Qwen3.5-35B-A3B on my MBP M3 Pro with 36GB via LM Studio and OpenCode. I didn’t have it write code but instead use Rodney (thanks for making it btw!) to take screenshots and write documentation using them. Overall I was pretty impressed at how well it handled the harness and completed the task locally. In the past I would’ve had Haiku do this, but I might switch to doing it locally from now on.
Right now I have to wait 10 minutes at a time for the 2+ hour long transcriptions I've uploaded to Voxstral to process. The speed up here could be immense and worthwhile to so many customers of these products.
This is pretty awesome, and at a $3 price point is an auto purchase for me!
As someone else said though, hardware keyboard support on iOS is something that I would really want as I regularly use ShellFish on my iPhone with a USB-C keyboard.
Something that actually matters more to me is font support. I use nerd fonts for my zsh prompt, so an app that doesn't support them is a hard sell. Are custom fonts supported, or at least on the roadmap?
Additionally I just want clarification on your business model. Once I pay now I will get all future updates for free or might I have to pay for them?
EDIT: (Since Ghostty supports it) Does this also support showing images in the terminal via the kitty protocol?
I thought that project got turned into the animated film that got released not too long back? I got the impression JMS was done with B5 after he went back to focusing on comics again with his run on Captain America.
The animated film was said to be a side-by-side project from different budgets (WB Animation versus The CW/WB Television Studios).
I think at this point JMS is trying to keep a diverse income and still do comics as well as TV projects. Even during Sense8, with its Netflix-sized budget, he had comics irons in the fire.
It wasn't conscious or intentional. JMS only realized the connection halfway through writing it.
"It was only when I was about halfway into the act that I thought, "Oh, crud, this is the same area Canticle explored." And for several days I set it aside and strongly considered dropping it, or changing the venue (at one point considered setting it in the ruins of a university, but I couldn't make that work realistically...who'd be supporting a university in the ruins of a major nuclear war? Who'd have the *resources* I needed? The church, or what would at least LOOK like the church. My sense of backstory here is that the Anla-shok moved in and started little "abbeys" all over the place, using the church as cover, but rarely actually a part of it, which was why they had not gotten their recognition, and would never get it. Rome probably didn't even know about them, or knew them only distantly.)
Anyway...at the end of the day, I decided to leave it as it was, since I'd gotten there on an independent road, we'd already had a number of monks on B5, and there's been a LOT of theocratic science fiction written beyond Canticle...Gather Darkness, aspects of Foundation, others." -- Lurker's Guide
I’ve been SSHing into my dev server off of my phone to run Claude Code while commuting, so this is a product that I would love to switch to. I can’t use the Claude iOS app due to the testing set up I have. That said I do have a couple of questions:
- Is it possible to completely disable or not use the remote sandbox features? I would never use them and would prefer my code stays on my device.
- For those of us that are using subscriptions, does it show our remaining usage? I would hate to run out of tokens in the middle of a session.
- One feature of the CC TUI I sorely missed on mobile is the ability to look up and directly reference files via “@“. Is any functionality like this planned?
- (This likely won’t affect my decision to use the service as I’ll just put it on a company card.) $20 per month for a service that runs CC on a remote machine in a convenient matter is steep but doable. Asking that same amount for a running code on my own server seems a bit unjustified, especially since this is pricier than the cost of a Claude pro subscription. Are there any plans to offer a cheaper tier for those of us that just want to run this on our own machines?
Is it possible to completely disable or not use the remote sandbox features? I would never use them and would prefer my code stays on my device.
Yes, the remote sandbox feature is disabled by default, and you have to manually enable it for the syncing to start.
For those of us that are using subscriptions, does it show our remaining usage? I would hate to run out of tokens in the middle of a session.
Currently Omnara doesn't show your usage limits, you would have to check that at claude.ai. I'll look into add that though.
One feature of the CC TUI I sorely missed on mobile is the ability to look up and directly reference files via “@“. Is any functionality like this planned?
Yes, this exists in Omnara already!
Are there any plans to offer a cheaper tier for those of us that just want to run this on our own machines?
That's a good idea, we'll think about doing this where we don't offer sandbox + voice, and just have the messaging service.
Just tried out Handy. This is much better and lightweight UI than the previous solutions I've tried out! I know it wasn't you intention, but thank you for the recommendation!
That said, I now agree with your original statement and really want Voxtral support...
Handy is awesome! and easy to fork. I highly recommend building it from source and submitting PRs if there are any features you want. The author is highly responsive and open to vibe-coded PRs as long as you do a good job. (Obviously you should read the code and stand by it before you submit a PR, but I just mean he doesn't flatly reject all AI code like some other projects do.) I submitted a PR recently to add an onboarding flow to Macs that just got merged, so now I'm hooked
reply