Why not telnet?
No HTTPS support
I bet someone can write an API Gateway for this...
LLM Chat via SSH
11–20 of 25 posts
Re: LLM Chat via SSH
#12Is this doing local inference? If so, what inference engine is it using?
Re: LLM Chat via SSH
#13Why not telnet?
I'd love to see an LLM outputting over a Teletype. Just tschtschtschtsch as it hammers away the paper feed.
Re: LLM Chat via SSH
#14Skimming 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
Re: LLM Chat via SSH
#15Using 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.
I mean, it's a thin wrapper around LLM APIs, so it's not surprising that most of the code is rendering. I'm not sure what you're referring to by "handling issues with rendering", though—it looks like a pretty bog standard React app. Am I missing something?
Re: LLM Chat via SSH
#16Is this doing local inference? If so, what inference engine is it using?
No, it's a thin wrapper around an API, probably OpenRouter or similar:
https://github.com/ccbikai/ssh-ai-chat/blob/master/src/ai/in...
Re: LLM Chat via SSH
#17does this project request to llm providers?
Are you serious? Yeah, its using gemini 2.5 pro without a server, sure yeah.
Re: LLM Chat via SSH
#18Re: LLM Chat via SSH
#19this 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?
Re: LLM Chat via SSH
#20Wow, that produced a flashback to using TinyFugue in the 90s.