Awesome

gemini-cli

A command-line interface (CLI) for Google Gemini.

Google Gemini is a family of multimodal artificial intelligence (AI) large language models that have capabilities in language, audio, code and video understanding.

The current version only supports multi-turn conversations (chat), using the gemini-pro model.

Installation

Choose a binary from the releases.

Build from Source

Download and install Go.

Install the application:

go install github.com/reugn/gemini-cli/cmd/gemini@latest

See the go install instructions for more information about the command.

Usage

API key

To use gemini-cli, you'll need an API key set in the GEMINI_API_KEY environment variable. If you don't already have one, create a key in Google AI Studio.

[!NOTE] For information on the available regions for the Gemini API and Google AI Studio, see here.

System commands

The system chat message must begin with an exclamation mark and is used for internal operations. A short list of supported system commands:

Command	Description
!q	Quit the application
!p	Delete the history used as chat context by the model
!i	Toggle input mode (single-line <-> multi-line)
!m	Select generative model

CLI help

$ ./gemini -h
Gemini CLI Tool

Usage:
   [flags]

Flags:
  -f, --format         render markdown-formatted response (default true)
  -h, --help           help for this command
  -m, --model string   generative model name (default "gemini-pro")
      --multiline      read input as a multi-line string
  -s, --style string   markdown format style (ascii, dark, light, pink, notty, dracula) (default "auto")
  -t, --term string    multi-line input terminator (default "$")
  -v, --version        version for this command

License

MIT