Gemini CLI

TODO

Open-source AI agent that allows to use Google Gemini from a terminal.
Can read and edit files, execute shell commands, and search the web.

TL;DR
Further readings
1. Sources

TL;DR

Ships with a generous free tier, built-in Google Search capabilities, a 1M token context window.
Supports conversation checkpointing.

Only allows using Google's Gemini models (Flash and Pro).
Model selection depends on authentication method.

Free tier with Google account.
Enterprise pricing through Vertex AI.
Usage-based billing available via API key.

Setup

# Install.
brew install 'gemini-cli'
npm install -g '@google/gemini-cli'
port install 'gemini-cli'

# Run without installation.
docker run --rm -it 'us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.1.1'
npx '@google/gemini-cli'

# Configure API keys.
export GEMINI_API_KEY="YOUR_GEMINI_API_KEY"

Usage

# Show version.
gemini --version

# Start.
gemini

# Run inside a container.
# If installed locally.
gemini --sandbox -y -p "your prompt here"

# Headless mode.
gemini -p "What is fine tuning?"
echo "What is fine tuning?" | gemini

1.8 KiB Raw Blame History

Gemini CLI

TL;DR

Further readings

Sources

1.8 KiB

Raw Blame History