google-github-actions/run-gemini-cli

A GitHub Action invoking the Gemini CLI.

What it solves

run-gemini-cli is a GitHub Action that integrates the Gemini CLI into development workflows. It automates routine coding tasks and provides an on-demand AI collaborator directly within GitHub repositories, reducing the manual effort required for code reviews, issue triaging, and general code analysis.

How it works

The action installs and runs the Gemini CLI within a GitHub Actions runner. It can be triggered by specific GitHub events (like opening an issue or PR) or manually via comments in issues and pull requests using the @gemini-cli handle. It leverages Gemini models' tool-calling capabilities to interact with other tools like the GitHub CLI (gh) and can be customized via a GEMINI.md file in the repository to provide project-specific context.

Who it’s for

Developers and maintainers of GitHub repositories who want to automate their maintenance tasks using Gemini AI, specifically for PR reviews, issue triage, and conversational AI assistance within their project's context.

Highlights

  • Automated Workflows: Pre-built workflows for automatic pull request reviews and issue triaging.
  • Collaborative AI: Ability to trigger AI assistance on-demand via @gemini-cli mentions in comments.
  • Tool Integration: Uses tool-calling to interact with the GitHub CLI for repository management.
  • Customizable Context: Supports a GEMINI.md file for repository-specific instructions and coding conventions.
  • Flexible Authentication: Supports Gemini API keys, Google Cloud Workload Identity Federation, and custom GitHub Apps.

Related

  • Project
    actions/ai-inference

    A GitHub Action that enables running AI inference via the GitHub Copilot CLI within automated workflows.

  • Project
    github/gh-aw

    GitHub Agentic Workflows (`gh-aw`) is a GitHub CLI extension that lets you write AI‑powered automation as Markdown files with YAML front‑matter. The tool compiles these *agentic* workflows into standard GitHub Actions workflows, running LLMs (Copilot, Claude, OpenAI, Gemini, Pi) in a sandboxed, read‑only mode. Writes are gated through a separate safe‑outputs job with scoped permissions. It’s designed for tasks like issue triage, PR review, CI failure analysis, docs updates, and repo reporting, integrating securely with existing CI/CD pipelines.

  • Project
    pullfrog/pullfrog

    A GitHub bot and Action that integrates coding agents into GitHub to automate code implementation, PR reviews, and issue management.

  • Project
    google-gemini/gemini-cli

    An open-source AI agent for the terminal that provides direct access to Gemini models for code analysis, automation, and system integration.

  • Project
    githubnext/agentics

    A collection of reusable agentic workflows for GitHub that automate repository maintenance, code review, fault analysis, and documentation updates.