Gemini CLI
Google's open-source terminal agent on Gemini models: code work, shell, web search and MCP
- 108,601 ★ on the repository
- Last commit
- Apache-2.0
Broad access
Why this level
- The agent runs shell commands and edits files
- Code and prompts are sent to Google models
- Requires a Google account or API key
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add cli/gemini-cliDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewBroad accessThe tool can change data, run commands or handle secrets.
- The agent runs shell commands and edits files
- Code and prompts are sent to Google models
- Requires a Google account or API key
This is third-party code. Review the repository files before installing.
What it does
Gemini CLI is a terminal agent that reads and edits codebases, runs shell commands, fetches web pages and uses Google Search grounding for current data. It supports MCP servers, GEMINI.md context files, session checkpoints and a non-interactive mode with JSON output for scripts. A separate GitHub Action handles PR reviews and issue triage. The repository also ships skills such as code-reviewer.
Who it is for. Developers who work in the terminal with Gemini models via a paid API key, Vertex AI or an enterprise license.
Good fit when
- You need to understand a large codebase with long context
- You want to automate tasks in scripts via gemini -p with JSON output
- You need PR reviews and issue triage in GitHub Actions
- You connect your own MCP servers to the agent
Not a fit when
- Your network cannot reach Google services
- Company policy forbids sending code to external models
Example request
Explain the architecture of this repository and find where authorization errors are handledLimitations
Since June 18, 2026 Gemini CLI works only with paid Gemini API keys, Vertex AI and enterprise licenses: Google moved free users and AI Pro and Ultra subscribers to Antigravity CLI. Preview and nightly builds may contain regressions.
How to disable. Remove the package with npm uninstall -g @google/gemini-cli or via brew, depending on how you installed it.
FAQ
Can I try it without installing?
Yes, the README suggests running npx @google/gemini-cli.
What release channels exist?
preview ships on Tuesdays, stable follows a week after preview, and nightly ships daily.
Discussion
No questions or reviews yet.
Related
CLI toolsGoogle's CLI and skill set that helps a coding agent build, evaluate and deploy agents on Google Cloud with ADK and Gemini Enterprise
Google's terminal AI agent: edits code across files, runs commands and keeps session history, started with the agy command
Delegating to an intern: Google's Antigravity CLI (agy) with a fast Gemini model for Claude Code, Codex, Pi and OpenCode. Code and tasks go to Google
A terminal workspace where several CLI agents like Codex, Claude and Gemini exchange messages and work on one task under human oversight
Magpie
magpie
Magpie — an app and local gateway that connect any model to Claude Code, Codex, Gemini CLI and OpenCode and switch them from the menu bar
Gemma Skills
gemma-skills
Official Google Gemma skill: building applications on Gemma and a reference on models, the gemma-dev skill installs through npx
README in short
Gemini CLI is Google's open-source terminal AI agent under Apache 2.0. The README covers installation via npx, npm, Homebrew, MacPorts and conda, release channels and three auth options. Features include codebase work, multimodal input, MCP, Google Search grounding, checkpoints and context files. GitHub integration via the Gemini CLI GitHub Action is described separately.
README badge
Original SKILL.md
---
name: code-reviewer
description:
Use this skill to review code. It supports both local changes (staged or working tree)
and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability,
and adherence to project standards.
---
# Code Reviewer
This skill guides the agent in conducting professional and thorough code reviews for both local development and remote Pull Requests.
## Workflow
### 1. Determine Review Target
* **Remote PR**: If the user provides a PR number or URL (e.g., "Review PR #123"), target that remote PR.
* **Local Changes**: If no specific PR is mentioned, or if the user asks to "review my changes", target the current local file system states (staged and unstaged changes).
### 2. Preparation
#### For Remote PRs:
1. **Checkout**: Use the GitHub CLI to checkout the PR.
```bash
gh pr checkout <PR_NUMBER>
```
2. **Preflight**: Execute the project's standard verification suite to catch automated failures early.
```bash
npm run preflight
```
3. **Context**: Read the PR description and any existing comments to understand the goal and history.
#### For Local Changes:
1. **Identify Changes**:
* Check status: `git status`
* Read diffs: `git diff` (working tree) and/or `git diff --staged` (staged).
2. **Preflight (Optional)**: If the changes are substantial, ask the user if they want to run `npm run preflight` before reviewing.
### 3. In-Depth Analysis
Analyze the code changes based on the following pillars:
* **Correctness**: Does the code achieve its stated purpose without bugs or logical errors?
* **Maintainability**: Is the code clean, well-structured, and easy to understand and modify in the future? Consider factors like code clarity, modularity, and adherence to established design patterns.
* **Readability**: Is the code well-commented (where necessary) and consistently formatted according to our project's coding style guidelines?