butterfish
shell-bling-ubuntu
butterfish | shell-bling-ubuntu | |
---|---|---|
6 | 7 | |
277 | 65 | |
- | - | |
8.6 | 8.1 | |
5 days ago | 2 months ago | |
Go | Shell | |
MIT License | The Unlicense |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
butterfish
-
Show HN: Inshellisense – IDE style shell autocomplete
If you're interested in GPT-powered shell autocomplete, check out https://butterfi.sh
This also enables shell-aware LLM prompting
- Butterfish – A Shell with AI Superpowers
- LLM, ttok and strip-tags–CLI tools for working with ChatGPT and other LLMs
-
Anyone using the amazing 'butterfish' chatGPt shell wrapper? And if so, how do you use the 'index' argument, that builds local embeddings? My intuition tells me it's very valuable, but I can't wrap head around how to use it. Some examples would be appreciated
the github page lists these flags:.
- Butterfish - A transparent shell wrapper with GPT
- Butterfish – Let's do useful things with LLMs from the command line
shell-bling-ubuntu
-
Ask HN: I want to learn to use the terminal, where do I start
Personally, I only really got into working at the shell once I started exploring all of the wonderful new programs that people have been writing to make it easy as pie to work with. I ended up collecting them all together into scripts I can `curl | bash` on any new Ubuntu machine: https://github.com/hiAndrewQuinn/shell-bling-ubuntu
Obviously these scripts won't work on Mac. But I do list the programs I install in it right in the README, including what I consider the "Holy Trinity": `rg` (really fast line searching), `fd` (really fast file finding), and `fzf` (best described with examples: see https://andrew-quinn.me/fzf). These all work on my wife's Mac identically to how they work on my own Linux box, and they make the experience of working at a shell much more pleasant.
Finally, install fish! https://mmazzarolo.com/blog/2023-11-16-my-fish-shell-setup-o... You can get back to Bash once you've gotten used to using the shell and find a reason to. Fish is much more pleasant, IMO, and I try to use it wherever I can these days.
-
Starship.rs: minimal, fast prompt for any shell
Yes! This is why I pair the two up in https://github.com/hiAndrewQuinn/shell-bling-ubuntu.
These context clues are especially important for newcomers to the command line. A CLI newbie who sticks with it might eventually progress to the point where they decide to ditch Starship, or to ditch fish, or to ditch both, but until they get to that point, the solid defaults and OOTB features of these two have a lot going for them.
-
Show HN: Inshellisense – IDE style shell autocomplete
Alternatively, if you simply wish to occasionally bring Copilot into your shell, you should know that Ctrl+X Ctrl+E (on bash) / Alt+E (on fish) will open your current shell line up in $EDITOR, which you may set to Vim or Neovim.
From there, :wq will drop the text back into your command line. If you have Copilot set up in either of those, then it will also work here.
I know from working on https://github.com/hiAndrewQuinn/shell-bling-ubuntu that Neovim's LazyVim setup now supports Copilot out of the box now. I never had much trouble setting up the Vim plugin either. YMMV.
-
Ask HN: How does `lnav` run its playground which you can just SSH into?
https://lnav.org/ has a feature that single handedly sold me on trying out the fantastic software: An SSH-reachable playground. It's right there above the fold on the first page: ssh://[email protected]
I want to build a similar playground for people who want to get familiar with the tools my Shell Bling Ubuntu repo provides ( https://github.com/hiAndrewQuinn/shell-bling-ubuntu ). Ideally it consists of a series of very simple tasks to get one's feet wet with each tool provided: Using fish's autocompletion, then using fzf's shell keybindings, then using rg instead of grep to search an enormous number of files for a single needle character in a million lines of wheat , and so on.
I have no clue how to do this safely. I've never seen how anyone else does it either. Can anyone provide me some pointers?
-
Cursor – The AI-First Code Editor
Alternatively, if you just want to integrate Copilot into Neovim and get on with your day, I recently discovered that the latest LazyVim integrates it as an extra.
I actually discovered this while working on Shell Bling Ubuntu, which is a couple of easy scripts to get you a bunch of modern command line tools nice and configured in one go, but you can just scroll down to "Add Copilot to Neovim" to see. It's refreshingly user friendly for NV configs.
https://github.com/hiAndrewQuinn/shell-bling-ubuntu
- GitHub - hiAndrewQuinn/shell-bling-ubuntu: A few scripts to be run on a fresh-off-the-presses Ubuntu VM, in order to get its shell nice 'n purdy.
- Show HN: 3 scripts to turn a stock Ubuntu live USB into a modern devbox
What are some alternatives?
mods - AI on the command line
inshellisense - IDE style command line auto complete
aider - aider is AI pair programming in your terminal
hishtory - Your shell history: synced, queryable, and in context
shell_gpt - A command-line productivity tool powered by AI large language models like GPT-4, will help you accomplish your tasks faster and more efficiently.
chatgpt-in-terminal - Use ChatGPT in terminal
wizapp - The Wizard's Apprentice, an AI-powered Typescript project functionality suite with CLI.
cass - A ChatGPT-powered assistant in the console
aichat - All-in-one AI-Powered CLI Chat & Copilot that integrates 10+ AI platforms, including OpenAI, Azure-OpenAI, Gemini, VertexAI, Claude, Mistral, Cohere, Ollama, Ernie, Qianwen...
bashGPT - Use ChatGPT, GPT-3 and other models from the command line.
thoughtloom - ThoughtLoom is a powerful tool designed to foster creativity and enhance productivity through the use of LLMs directly from the command line. It facilitates rapid development and integration of LLM-based tools into various workflows, empowering individuals and teams to experiment, collaborate, and ultimately streamline their daily tasks.
gptask - Command line client for ChatGPT