Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Crush: Glamourous AI coding agent for your favourite terminal

github.com

Post reply on HN
Print view View original

171–180 of 240 posts

Re: Crush: Glamourous AI coding agent for your favourite terminal

#171

Post by knoopx »

smokel wrote: post #63
jsnell wrote: post #59

I find it strange how most of these terminal-based AI coding agents have ended up with these attempts at making text UIs flashy. Tons of whitespace, line art, widgets, ascii art and gradients, and now apparently animations. And then what you don't get is the full suite of expected keybindings, tab completion, consistent scrollback, or even flicker-free text rendering. (At least this one seems to not be written with n…

They are easier to make than full-fledged user interfaces, so you get to see more of them.

this is debatable, a proper TUI has the same complexities as conventional UIs + legacy rendering.

Re: Crush: Glamourous AI coding agent for your favourite terminal

#172

Post by breuleux »

mccoyb wrote: post #161
breuleux wrote: post #146

Earlier quoted context omitted.

I mean a session that isn't limited to interaction with a single program. For example, if I have an agent in this paradigm, I want to easily interleave prompting with simple commands like `ls`, all in the same history. That's not what I'm getting with apps like claude code or crush. They just take over the entire terminal, and crush even quits without leaving a trace.

Thanks, thinking about this - I think there are several ways to serve this concern: one could be having an agent as a server, where "prompting" is just a command `prompt ...` sent to the agent as a server. Then you never leave your terminal. Presumably, you'd want this, but with some sort of interface _like_ these TUI systems?

> one could be having an agent as a server, where "prompting" is just a command `prompt ...` sent to the agent as a server

Yeah, I prefer something like that (which should be strictly easier to make than these elaborate TUIs). I could also be interested in a shell that supports it natively, e.g. with a syntax such as `-- this is my prompt! it's not necessary to quote stuff`. I'd also enjoy an HTML shell that can output markdown, tables and interactive plots rather than trying to bend a matrix of characters to do these things (as long as it's snappy and reliable). I haven't looked very hard, so these things might already exist.

Re: Crush: Glamourous AI coding agent for your favourite terminal

#173

Post by segmondy »

jasonm23 wrote: post #17
Aperocky wrote: post #7

The big question - which one of these new agents can consume local models to a reasonable degree? I would like to ditch the dependency on external APIs - willing to trade some performance in lieu.

Crush has an open issue (2 weeks) to add Ollama support - it's in progress.

why?

it's basic, edit the config file. I just downloaded it, ~/.cache/share/crush/providers.json add your own or edit an existing one

Edit api_endpoint, done.

Re: Crush: Glamourous AI coding agent for your favourite terminal

#174

Post by segmondy »

sharperguy wrote: post #143
Aperocky wrote: post #7

The big question - which one of these new agents can consume local models to a reasonable degree? I would like to ditch the dependency on external APIs - willing to trade some performance in lieu.

What happens if you just point it at its own source and ask it to add the feature?

it will add the feature, I saw openAI make that claim that developers are adding their own features, saw Anthrophic make the same claim, and Aider's paul often says Aider wrote most of the code. I started building my own coding CLI for the fun of it, and then I thought, why not have it start developing features, and it does too. It's as good as the model. For ish and giggles, I just downloaded crush, pointed it to a local qwen3-30b-a3b which is a very small model and had it load the code, refactor itself and point bugs. I have never used LSP, and just wanted to see how it performs compared to treesitter.

Re: Crush: Glamourous AI coding agent for your favourite terminal

#175

Post by n00bskoolbus »

rawkode wrote: post #154

How to handle an OSS dispute where you're the baddy: rebrand and hope nobody notices. Let's not forget they're the company that bought an OSS project, OpenCode, and tried to "steal" it

I'm unfamiliar with this. How would they steal it if they bought the open source project?

Re: Crush: Glamourous AI coding agent for your favourite terminal

#176

Post by segmondy »

827a wrote: post #101

One thing I'm curious about: Assuming you're using the same underlying models, and putting obvious pricing differences aside: What is the functional difference between e.g. Charm and Claude Code? And Cursor, putting aside the obvious advantages running in a GUI brings and that integration. Is there secret sauce that would make one better than the other? Available tools? The internal prompting and context engineering…

the secret sauce will be the available tools, prompting, context engineering, etc, yup whatever "agentic algorithm" has been built in.

Re: Crush: Glamourous AI coding agent for your favourite terminal

#177

Post by jemiluv8 »

Wondered how claude code would look like if it was built by the people over at charmbracelet. I suppose this is it

The terminal is so ideal for agentic coding and the more interactive the better. I personally would like to be able to enter multiline text in a more intuitive way in claude code. This nails it.

Re: Crush: Glamourous AI coding agent for your favourite terminal

#178

Post by segmondy »

Aperocky wrote: post #7

The big question - which one of these new agents can consume local models to a reasonable degree? I would like to ditch the dependency on external APIs - willing to trade some performance in lieu.

all of them, you can even use claude-code with a local model

Re: Crush: Glamourous AI coding agent for your favourite terminal

#179

Post by segmondy »

dedpool wrote: post #144

This one feels refreshing. It’s written in Go, and the TUI is pretty slick. I’ve been running Qwen Coder 3 on a GPU cluster with 2 B200s at $2 per hour, getting 320k context windows and burning through millions of tokens without paying closed labs for API calls.

how many tk/sec are you getting on that setup especially when you have 100k+ tokens?

Re: Crush: Glamourous AI coding agent for your favourite terminal

#180

Post by hollerith »

tptacek wrote: post #45

One nice thing about this is that it's early days for this, and the code is really clear and schematic, so if you ever wanted a blueprint for how to lay out an agent with tool calls and sessions and automatic summarization and persistence, save this commit link.

The commit link is https://github.com/charmbracelet/crush/releases/tag/v0.1.8
Post reply on HN