- Renames "server" to "core" in GitHub Actions workflow and comment posting action. - This ensures that code coverage paths and labels are accurate after the package rename. |
||
---|---|---|
.gcp | ||
.github | ||
.vscode | ||
docs | ||
eslint-rules | ||
packages | ||
scripts | ||
.gitignore | ||
.npmrc | ||
.prettierrc.json | ||
CONTRIBUTING.md | ||
Dockerfile | ||
GEMINI.md | ||
LICENSE | ||
README.md | ||
eslint.config.js | ||
package-lock.json | ||
package.json | ||
tsconfig.json |
README.md
Gemini CLI
This repository contains the Gemini CLI tool.
Quickstart
- Install Node 18+
- Set your API key:
export GEMINI_API_KEY="YOUR_API_KEY"
(Get an API key)
- For future sessions you can add this to your shell's configuration file, or use a
.env
file in your project's hierarchy
- Run with:
npx https://github.com/google-gemini/gemini-cli#early-access
- Enjoy
Examples
Once the CLI is running, you can start interacting with Gemini. Try a simple query:
> How can I build a web app?
Or ask it to perform a task using its tools:
> List files in the current directory.
API Key Setup
The Gemini CLI requires a Gemini API Key. It supports several ways to authenticate with Google's AI services. You'll need to configure one of the following methods:
-
Gemini API Key:
- Obtain your API key from Google AI Studio: https://aistudio.google.com/app/apikey
- Set the
GEMINI_API_KEY
environment variable. You can do this temporarily in your current shell session:
Or add it to yourexport GEMINI_API_KEY="YOUR_GEMINI_API_KEY"
.env
file (in project directory or user home) or shell's configuration file (like~/.bashrc
,~/.zshrc
, or~/.profile
) for persistence:
Replaceecho 'export GEMINI_API_KEY="YOUR_GEMINI_API_KEY"' >> ~/.bashrc # Or your preferred shell config file source ~/.bashrc # Reload the config
"YOUR_GEMINI_API_KEY"
with your actual key.
-
Google API Key (Vertex AI Express Mode):
- This key can be a general Google Cloud API key enabled for the Gemini API or Vertex AI.
- Set the
GOOGLE_API_KEY
andGOOGLE_GENAI_USE_VERTEXAI
environment variables:export GOOGLE_API_KEY="YOUR_GOOGLE_API_KEY" export GOOGLE_GENAI_USE_VERTEXAI=true
-
Vertex AI (Project and Location):
- Ensure you have a Google Cloud Project and have enabled the Vertex AI API.
- Set up Application Default Credentials (ADC). For more details, refer to the official Google Cloud ADC documentation:
gcloud auth application-default login
- Set the
GOOGLE_CLOUD_PROJECT
,GOOGLE_CLOUD_LOCATION
, andGOOGLE_GENAI_USE_VERTEXAI
environment variables:export GOOGLE_CLOUD_PROJECT="YOUR_PROJECT_ID" export GOOGLE_CLOUD_LOCATION="YOUR_PROJECT_LOCATION" # e.g., us-central1 export GOOGLE_GENAI_USE_VERTEXAI=true
Next Steps
Congratulations! You've successfully set up and run the Gemini CLI.
- If you're interested in contributing or building from source, check CONTRIBUTING
- Explore the CLI Commands to learn about all available functionalities.
- If you encounter any issues, check the Troubleshooting Guide.
- For more comprehensive documentation, please see the full documentation here.