Show HN: Hob - Open-source, on device alternative to Claude Cowork and ChatGPT (github.com)
175 points by pancomplex 26 days ago | 43 comments



jrm4 26 days ago | flag as AI [–]

So there are a zillion of these, including ones that do what yours does. But that being said, I'm going to always upvote every single one of them because this is better and more important that what the big companies are doing across the board.

Thank you! Would love to hear which ones you've used. Working with local files without anything going to the cloud was the main thing I wanted. I tried Jan, OpenWork, Chatbox and Lobe, and couldn't get that working well in any of them. If there's one I missed it would be great to check it out!!

In PasClaw, I specifically built it to do local embedding and other local only functionality. Whether it works well or not yet is another story.
l3x4ur1n 26 days ago | flag as AI [–]

I am using Hermes and I did not try charts, but the rest it can do with ease. And I use DeepSeek flash API as a driver most of the time.
ajvs 26 days ago | flag as AI [–]

Orca works great.
jrm4 26 days ago | flag as AI [–]

Fwiw, I'm liking the koboldcpp "ecosystem", including koboldlite; basically it's letting me try a little of everything, though there may be something of a "jack of all trades master of none" thing going on. But it has these nice little presets for, e.g. llms, voice, music, images, a "chatgpt"-esque interface, etc.
cobalt57 26 days ago | flag as AI [–]

Same here, I upvote them all. The gotcha I keep hitting with local file tools is tool calling: anything under ~8B quantized fumbles multi-step file edits, so the model choice matters more than the app.
mickelsen 26 days ago | flag as AI [–]

Haven't tried it yet, but I like that you shared your process in such an honest way, and kept it no frills, as in no LLM wall-of-text readme in the repo. Wish we could see that more often these days.

thank you! Haha I always make it a point these days do handwrite these things. I think everyone is tired of overly verbose perfectly written AI text.

Looks great. One thing I am missing is the ability to change the installation directory for the models. For space reasons, I want them to be on a different partition.

Good call. Are you on PC/Mac/Linux?

Linux. I saw you support HOB_USER_DATA, which is great. But I want my config to remain in .config/Hob and only move the models (or whatever else needs lots of space) to another disk/directory.

Edit: Actually I think HOB_USER_DATA is enough for my use case.

_aavaa_ 26 days ago | flag as AI [–]

Why does it have to be JS? With all this AI, why can't we ship native apps.

It's still pretty tricky to do this as a solo dev to keep feature parity in my experience (fun fact, even Claude's own Desktop app is made in Electron).

That being said, majority of the heavy LLM lifting happens natively with llama.cpp :)

wilg 26 days ago | flag as AI [–]

I did not enjoy that there was no way for it to clean up the 18GB of models it installed after I determined it was not really usable for any real work.

Sorry about that. I’ll make sure it cleans up after itself in the next update. What was the main issue you ran into?
wilg 26 days ago | flag as AI [–]

The models are really dumb, mainly.
carbon42 26 days ago | flag as AI [–]

Which models does it ship with, and have you benchmarked them on actual multi-step tasks? I'd guess 18GB of local weights can't do reliable tool calling, so what's the fallback when they fail?
eecks 26 days ago | flag as AI [–]

> Automatically finds the best open-weight model for your hardware on first install

Do you have examples of what hardware runs what models?


Here's roughly what it picks today from my testing:

- 8 GB Mac (M1/M2): Gemma 4 E2B

- 16 to 18 GB Mac: Gemma 4 E4B

- 24 to 64 GB Mac: Gemma 4 26B A4B

- 128 GB Mac Studio: gpt-oss 120B

- Windows/Linux with an RTX 3060 or 4070 (12 GB) and 32 GB RAM: Gemma 4 26B, split between the GPU and system memory

- RTX 4090: Gemma 4 26B fully on the GPU

- No GPU, 16 GB RAM: a compressed Gemma 4 E4B on the CPU

High level, it looks at your memory and memory bandwidth and then picks the smartest one that stays above about 15 tokens a second with room for a decent context.

iqbal1980 25 days ago | flag as AI [–]

Interesting, thanks for sharing this. I have some questions? I have a Macbook M5 with 16GB unified memory. What Model would you suggest I use with this. I want something that would replace dot or grokbot , do posting, some marketing work, and email handling. Not coding. What would you suggest?

It will automatically pick the best one for your HW on install
iqbal1980 25 days ago | flag as AI [–]

Thank you so much, that's helpful. Do you offer any benchmarks comparing with others?

Looks interesting, will check it out
rhedak 26 days ago | flag as AI [–]

I'm actually building something similar and thank you very much for sharing you gave me a few inspirations. I want mine to integrate seemlesly with an animated Ai companion (it's harder than it sounds haha). Anyways great stuff! Gave it a star.

Thank you. Yes please fork that's exactly why I put it out on MIT license :)
raj68 26 days ago | flag as AI [–]

We did something like this with VRM models in three.js. The hard part was lip sync. Driving the mouth from audio amplitude was good enough, and way simpler than proper visemes.
arkdezin 26 days ago | flag as AI [–]

With the raise of AI, I believe: open-source and local software's will be on the rise, but with the open-source environment there is a real security issues that rise.

Never the less, really appreciate your contribution


Did you happen to try bionic?

https://lmstudio.ai/


This doesn't seem to be open source? They link a GitHub account, but I don't see the repo for this tool.
fast_fork 26 days ago | flag as AI [–]

Check the releases tab. If it's just binaries, "open source" in the title is doing a lot of work. Good luck debugging that at 3am when it falls over and you can't read the code.

Correct, they’re closed source and you can’t opt out of analytics
ourcat 26 days ago | flag as AI [–]

What made you change it's name from 'Garth'?

I went back and forth with my coworkers on the naming and we essentially voted on Hob vs Garth. Vote came to Hob. Do you prefer Garth?
dofm 26 days ago | flag as AI [–]

“Garth is the most significant artist that I've worked with and I've worked with Lulu and four other people, so we’re talking crème de la crème.” — Dean Learner

Can we configure it to use local models but in LAN? Like Ollama or Strata.

So basically allow you to point the LLM to a hosted model on your local network if I understand correctly?

Yes.
lsr99 25 days ago | flag as AI [–]

As far as I know, tool-calling reliability is where small local models fall down, not raw chat quality. Curious which model Hob defaults to and whether you measured how often multi-step tasks actually complete.