from Hacker News

LLM Chat via SSH

by wey-gu on 6/14/25, 4:43 AM with 24 comments

• by demosthanos on 6/16/25, 2:08 PM

  Skimming the source code I got really confused to see TSX files. I'd never seen Ink (React for CLIs) before, and I like it!

  Previously discussions of Ink:

  July 2017 (129 points, 42 comments): https://news.ycombinator.com/item?id=14831961

  May 2023 (588 points, 178 comments): https://news.ycombinator.com/item?id=35863837

  Nov 2024 (164 points, 106 comments): https://news.ycombinator.com/item?id=42016639

• by amelius on 6/16/25, 12:50 PM

  I'd rather apt-get install something.

  But that seems not a possibility in the modern days of software distribution, especially with GPU-dependent stuff like LLMs.

  So yeah, I get why this exists.

• by gsibble on 6/16/25, 1:23 PM

  We made this a while ago on the web:

  https://terminal.odai.chat

• by gbacon on 6/16/25, 4:27 PM

  Wow, that produced a flashback to using TinyFugue in the 90s.

  https://tinyfugue.sourceforge.net/

  https://en.wikipedia.org/wiki/List_of_MUD_clients

• by dncornholio on 6/16/25, 1:10 PM

  Using React to render a CLI tool is something. I'm not sure how I feel about that. It feels like like 90% of the code is handling issues with rendering.

• by xigoi on 6/16/25, 9:31 PM

  It’s not clear from the README what providers it uses and why it needs your GitHub username.

• by gclawes on 6/16/25, 1:55 PM

  Is this doing local inference? If so, what inference engine is it using?

• by ryancnelson on 6/16/25, 4:19 PM

  this is neat.... whose anthropic credits am i using, though? sonnet-4 isn't cheap! would i hit a rate-limit if i used this for daily work?

• by ccbikai on 6/14/25, 10:08 AM

  I am the author, thank you for your support.

  Welcome to help maintain it with me

• by kimjune01 on 6/14/25, 5:43 AM

  hey i just tried it. it's cool! i wish it was more self aware

• by t0ny1 on 6/16/25, 1:38 PM

  does this project request to llm providers?

• by eisbaw on 6/16/25, 1:20 PM

  Why not telnet?