This repository contains GHCCLI, an enhanced command-line AI workflow tool that connects to your tools, understands your code and accelerates your workflows. GHCCLI is built on top of the Gemini CLI with additional customizations and features.
With GHCCLI you can:
- Query and edit large codebases.
- Generate new apps from PDFs or sketches, using multimodal AI capabilities.
- Automate operational tasks, like querying pull requests or handling complex rebases.
- Use tools and MCP servers to connect new capabilities, including media generation tools
- Ground your queries with integrated search capabilities.
- Access multiple AI providers including Gemini, GitHub Copilot, and OpenAI.
You have multiple options to install GHCCLI.
-
Prerequisites: Ensure you have Node.js version 20 or higher installed.
-
Install from source: Clone and build the CLI:
git clone https://github.com/plusplusoneplusplus/ghccli.git cd ghccli npm install npm run build
Then, run the CLI from the project directory:
npm start
Or install it globally:
npm install -g . ghccli
-
Prerequisites: Ensure you have Homebrew installed.
-
Install the CLI: Execute the following command in your terminal:
brew install ghccli
Then, run the CLI from anywhere:
ghccli
For the original Gemini CLI functionality:
npx https://github.com/google-gemini/gemini-cli
- Pick a color theme
- Authenticate: When prompted, choose your preferred AI provider and sign in. GHCCLI supports multiple authentication methods including Google accounts, GitHub Copilot, and OpenAI.
You are now ready to use GHCCLI!
The Gemini API provides a free tier with 100 requests per day using Gemini 2.5 Pro, control over which model you use, and access to higher rate limits (with a paid plan):
-
Generate a key from Google AI Studio.
-
Set it as an environment variable in your terminal. Replace
YOUR_API_KEY
with your generated key.export GEMINI_API_KEY="YOUR_API_KEY"
-
(Optionally) Upgrade your Gemini API project to a paid plan on the API key page (will automatically unlock Tier 1 rate limits)
The Vertex AI API provides a free tier using express mode for Gemini 2.5 Pro, control over which model you use, and access to higher rate limits with a billing account:
-
Generate a key from Google Cloud.
-
Set it as an environment variable in your terminal. Replace
YOUR_API_KEY
with your generated key and set GOOGLE_GENAI_USE_VERTEXAI to trueexport GOOGLE_API_KEY="YOUR_API_KEY" export GOOGLE_GENAI_USE_VERTEXAI=true
-
(Optionally) Add a billing account on your project to get access to higher usage limits
The GitHub Copilot integration provides access to GPT-4 and other models through your GitHub Copilot subscription:
-
Prerequisites: You need an active GitHub Copilot subscription (individual, business, or enterprise).
-
Authentication: The CLI will guide you through GitHub's OAuth flow:
- Just select "GitHub Copilot" in the authentication menu
- The CLI will display a device code and verification URL
- Visit the URL and enter the code to authorize
Connect directly to OpenAI's API or OpenAI-compatible APIs:
-
Prerequisites: You need an OpenAI API key from your OpenAI account.
-
Configuration: Set the required environment variables:
# Required: Your OpenAI API key export OPENAI_API_KEY="sk-your-openai-api-key" # Optional: Custom base URL (defaults to OpenAI) export OPENAI_BASE_URL="https://api.openai.com/v1" # Optional: Default model (defaults to gpt-4o) export OPENAI_MODEL="gpt-4"
-
Authentication: Select "OpenAI" in the authentication menu when starting the CLI.
For other authentication methods, including Google Workspace accounts, see the authentication guide.
Once the CLI is running, you can start interacting with AI from your shell.
You can start a project from a new directory:
cd new-project/
ghccli
> Write me a Discord bot that answers questions using a FAQ.md file I will provide
Or work with an existing project:
git clone https://github.com/plusplusoneplusplus/ghccli
cd ghccli
ghccli
> Give me a summary of all of the changes that went in yesterday
- Learn how to contribute to or build from the source.
- Explore the available CLI Commands.
- If you encounter any issues, review the troubleshooting guide.
- For more comprehensive documentation, see the full documentation.
- Take a look at some popular tasks for more inspiration.
- Check out our Official Roadmap
Head over to the troubleshooting guide if you're having issues.
Start by cd
ing into an existing or newly-cloned repository and running ghccli
.
> Describe the main pieces of this system's architecture.
> What security mechanisms are in place?
> Provide a step-by-step dev onboarding doc for developers new to the codebase.
> Summarize this codebase and highlight the most interesting patterns or techniques I could learn from.
> Identify potential areas for improvement or refactoring in this codebase, highlighting parts that appear fragile, complex, or hard to maintain.
> Which parts of this codebase might be challenging to scale or debug?
> Generate a README section for the [module name] module explaining what it does and how to use it.
> What kind of error handling and logging strategies does the project use?
> Which tools, libraries, and dependencies are used in this project?
> Implement a first draft for GitHub issue #123.
> Help me migrate this codebase to the latest version of Java. Start with a plan.
Use MCP servers to integrate your local system tools with your enterprise collaboration suite.
> Make me a slide deck showing the git history from the last 7 days, grouped by feature and team member.
> Make a full-screen web app for a wall display to show our most interacted-with GitHub issues.
> Convert all the images in this directory to png, and rename them to use dates from the exif data.
> Organize my PDF invoices by month of expenditure.
Head over to the Uninstall guide for uninstallation instructions.
For details on the terms of service and privacy notice applicable to your use of GHCCLI, see the Terms of Service and Privacy Notice.
Please see our security disclosure process. All security advisories are managed on Github.
GHCCLI is built on top of the excellent Gemini CLI project by Google. We extend our gratitude to the original authors and contributors.