lmcli

lmcli is a (Large) Language Model CLI.

Current features:

• Perform one-shot prompts with lmcli prompt <message>
• Manage persistent conversations with the new, reply, view, and rm sub-commands.
• Syntax highlighted output
• Tool calling, see the Tools section.

Planned features:

• Ask questions about content received on stdin
• Conversation editing

Maybe features:

• Support for additional models/APIs besides just OpenAI
• Natural language image generation, iterative editing

Tools

There are a few tools available, which must be explicitly enabled by adding the tool name to the openai.enabledTools array in config.yaml.

Note: all filesystem related tools operate relative to the current directory only. They do not accept absolute paths, and all efforts are made to ensure they cannot escape above the working directory (not quite using chroot, but in effect). Close attention must be paid to where you are running lmcli, as the model could at any time decide to use one of these tools to discover and read potentially sensitive information from your filesystem.

It's best to only have these tools enabled in config.yaml when you intend to be using them, because their descriptions (see pkg/cmd/functions.go) count towards context usage.

Available tools:

• read_dir - Read the contents of a directory
• read_file - Read the contents of a file
• write_file - Write contents to a file
• insert_file_lines - Insert lines at a position within a file. Tricky for the model to use, but can potentially save tokens.
• replace_file_lines - Remove or replace a range of lines within a file. Even trickier for the model to use.

Install

$ go install git.mlow.ca/mlow/lmcli@latest

Usage

Invoke lmcli at least once:

$ lmcli help

Edit ~/.config/lmcli/config.yaml and set openai.apiKey to your API key.

Refer back to the output of lmcli help for usage.

Enjoy!