An open-source AI agent from Google that brings Gemini into your terminal to query, edit, and automate code.
google-github-actions/run-gemini-cli
A GitHub Action that runs the Gemini CLI inside your repository to review pull requests, triage issues, and handle @gemini-cli requests.
- Stars
- 2,112
- Forks
- 288
- Open issues
- 85
- Last commit
- 2 months ago
What is it?
run-gemini-cli is a GitHub Action that runs the Gemini CLI inside GitHub workflows. It can work autonomously on scheduled or event-driven tasks, or act as an on-demand assistant when someone mentions @gemini-cli in an issue or pull request comment.
The action ships with pre-built workflows for pull request review, issue triage, a general conversational assistant, and a dispatcher that routes comment commands to the right workflow. Each workflow is meant to be copied into a repository's .github/workflows directory and customized. A GEMINI.md file in the repository provides project-specific instructions to the model.
Authentication supports a Gemini API key, Vertex AI, or Workload Identity Federation on Google Cloud, and GitHub access can use the default GITHUB_TOKEN or a custom GitHub App. Optional OpenTelemetry telemetry can be sent to a Google Cloud project.
Key features
- 01Runs automatically on events such as newly opened issues or pull requests, or on a schedule.
- 02Responds to @gemini-cli mentions in issue and pull request comments.
- 03Lets Gemini call tools such as the GitHub CLI (gh) during a task.
- 04Reads a GEMINI.md file for project-specific instructions and context.
- 05Supports Gemini API key, Vertex AI, and Workload Identity Federation authentication.
Use cases
- Automatically reviewing pull requests when they are opened.
- Triaging new GitHub issues on creation or on a nightly schedule.
- Asking Gemini to explain code, suggest changes, or write tests from an issue or PR comment.
- Sending workflow telemetry to a Google Cloud project for monitoring.
Quick start
- 1
Get a Gemini API key from Google AI Studio
- 2
Add the key as a repository secret named GEMINI_API_KEY
- 3
Start the Gemini CLI and run the setup command to create the workflows
gemini - 4
In the Gemini CLI, type /setup-github, then open a pull request or mention @gemini-cli in a comment to try it
Things to know
- Requires a Gemini API key stored as a GitHub secret, or a Google Cloud setup for Vertex AI.
- The default gemini_cli_version is latest, so the CLI behavior may change between runs unless you pin a version.
Topics
FAQ
- What is run-gemini-cli?
- A GitHub Action that runs the Gemini CLI inside your repository to review pull requests, triage issues, and handle @gemini-cli requests. run-gemini-cli is a GitHub Action that runs the Gemini CLI inside GitHub workflows. It can work autonomously on scheduled or event-driven tasks, or act as an on-demand assistant when someone mentions @gemini-cli in an issue or pull request comment.
- Is run-gemini-cli free to use? What license does it have?
- run-gemini-cli is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is run-gemini-cli still maintained?
- Updated within 6 months. The last commit to run-gemini-cli was on Aug 21, 2026.
- What can I use run-gemini-cli for?
- Automatically reviewing pull requests when they are opened. Triaging new GitHub issues on creation or on a nightly schedule. Asking Gemini to explain code, suggest changes, or write tests from an issue or PR comment. Sending workflow telemetry to a Google Cloud project for monitoring.
- How do I install run-gemini-cli?
- Get a Gemini API key from Google AI Studio Add the key as a repository secret named GEMINI_API_KEY Start the Gemini CLI and run the setup command to create the workflows: gemini In the Gemini CLI, type /setup-github, then open a pull request or mention @gemini-cli in a comment to try it
- Where can I get run-gemini-cli?
- The source code and installation instructions are on GitHub: https://github.com/google-github-actions/run-gemini-cli
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open-source AI agent that automatically reviews pull requests and offers /describe, /review, /improve and /ask commands on GitHub, GitLab, Bitbucket and Azure DevOps.
A GitHub Action that runs Claude Code on PRs and issues to answer questions, review changes, and implement code.
GitHub CLI extension that lets you write AI-powered repository automation as Markdown and runs it securely through GitHub Actions.
A modular runtime and orchestration system that coordinates AI coding agents through gated pipelines for tasks, review, shipping and docs across Claude Code, Codex, Cursor and more.
Agent-native memory infrastructure that turns LLM agent conversations and execution into persistent, structured memory for Python and TypeScript apps.