A simple but full-featured CLI powered by Deno for chatting with LLMs. A few hundred lines of TypeScript in a single file.
Thanks to Justin Bennett for the
script
that inspired this as well as the idea of piping markdown output to
glow.
https://gist.github.com/david-crespo/a2bf06be5db310db967b2e35f6140da2
No vision, no streaming responses (yet).
Set any or all of these, depending on which models you want to use. It is often
convenient to put them in a .env file like below and call source .env.
export OPENAI_API_KEY=abc-123
export ANTHROPIC_API_KEY=def-456
export GEMINI_API_KEY=ghi-789The script does not automatically pick up a .env file; the variables need to
be set in the environment.
- Deno (essential)
glow(terminal markdown renderer)- You can do without
glowif you like reading raw markdown or you pipe output to some other tool for rendering markdown in the terminal
- You can do without
gh(GitHub CLI, optional)- Only needed if you want to upload chats as GitHub gists
- You'll need to be logged in (
gh auth login)
Clone the repo. Then you just need a way to run main.ts and pipe the output to
glow. I use this function in my .zprofile:
function ai() {
source ~/path/to/.env
~/repos/llm-cli/main.ts "$@"
}The "$@:" means pipe all command-line arguments to ai straight to main.ts.
You'll need to chmod +x the script in order to be able to execute it directly like above.
Otherwise, you could run it with deno run path/to/main.ts, but that is less convenient
because you'll have to set all the permissions I've set in the shebang line.
This is mostly for me (though I'd be thrilled if people find it useful), so I'm not really interested in changes that make this tool more general-purpose unless a) I want to use them, b) they don't make the interface any more complicated. The open issues include features I'd be interested in adding.