Hob

AI

local ai desktop app

SHOW HN2026

Hob

Open-source, on device alternative to Claude Cowork and ChatGPT

github.com

#local llm#on-device ai#open-weight models#offline ai assistant

177points
43comments
#343of 4,366 in 2026
Top 8%of 2026 by points

How HN took it

CuriousMostly questions and neutral comments

4 positive, 8 neutral or asking, 0 mixed, 3 critical, out of 15 comments about the project. Thread score +0.14.

Execution: 0 for, 2 againstIdea: 1 for, 0 againstDocs: 1 for, 0 againstPerformance: 0 for, 1 againstPrivacy: 1 for, 0 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Honest, handwritten, no-frills writeup and repo

    From 1 comment
    • 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…
      mickelsen on HN
  • Open source MIT with forkable code

    From 2 comments
    • 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…
      rhedak on HN
    • Thank you. Yes please fork that's exactly why I put it out on MIT license :)
      pancomplex on HN

Objections

  • Local models feel too weak to be useful

    From 2 comments
    • The models are really dumb, mainly.
      wilg on HN
    • 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.
      wilg on HN
  • Installs large model downloads with no cleanup option

    From 2 comments
    • 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.
      wilg on HN
    • Sorry about that. I’ll make sure it cleans up after itself in the next update. What was the main issue you ran into?
      pancomplex on HN
  • Electron/JS instead of native apps

    From 1 comment
    • Why does it have to be JS? With all this AI, why can't we ship native apps.
      _aavaa_ on HN

Requests

  • Let users change the model installation directory

    From 1 comment
    • 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.
      laughing_snyder on HN
  • Support local network LLM servers like Ollama

    From 2 comments
  • Benchmarks comparing models

    From 1 comment
    • Thank you so much, that's helpful. Do you offer any benchmarks comparing with others?
      iqbal1980 on HN

Questions

  • Which hardware runs which model

    From 1 comment
    • > Automatically finds the best open-weight model for your hardware on first install Do you have examples of what hardware runs what models?
      eecks on HN
  • Which model suits a 16GB M5 Mac for email and marketing

    From 1 comment
    • 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…
      iqbal1980 on HN

Alternatives named

  • Osaurus

    From 2 comments
    • Definitely check out Osaurus for macOS and Windows. Heavily privacy focused with e2ee iOS and iPadOS tethers.
      universenz on HN
    • No worries. And yes, absolutely. Even the tiniest opportunity to poke around with stuff changes my perspective dramatically. I've picked up lots of stuff this way — just being…
      dofm on HN
  • Open WebUI

    From 1 comment
    • Have you tried Open WebUI? It doesn't determine which model works best for your hardware, but it otherwise has a very large feature set with a large community, and runs offline…
      prophesi on HN
  • LM Studio

    From 2 comments
    • Did you happen to try bionic? https://lmstudio.ai/
      vorticalbox on HN
    • Shouldn’t be embarrassing to admit. It’s a huge new subject area and it’s completely exhausting to learn. I still feel like a total novice. I have an M1 Max (more memory…
      dofm on HN
  • Orca

    From 1 comment
  • Jan, OpenWork, Chatbox, Lobe

    From 1 comment
    • 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…
      pancomplex on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/50246238)