gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
- Type
- MCP
- Transport
- stdio
- Open source
- Yes
- GitHub Stars
- ★ 105.5k
- Source
- mcp-github
- Repository
- github.com/google-gemini/gemini-cli
Overview
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal. With lightweight access, it provides the most direct path from prompt to model. It supports multiple built-in tools such as Google Search, file operations, shell commands, and web scraping, and can be extended via the MCP protocol. Ideal for developers who work in the command line.
Capabilities
- ▪Querying and editing large codebases
- ▪Generating new applications
- ▪Debugging issues and troubleshooting using natural language
- ▪Automating operational tasks
- ▪Connecting new capabilities (e.g., media generation)
- ▪Real-time information queries
Use cases
Setup
npm install -g @google/gemini-cli
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How do I install Gemini CLI?
You can install it globally via npm: npm install -g @google/gemini-cli
What authentication methods does Gemini CLI support?
Supports OAuth login using a Google account
Related skills
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
agent-skills
A React Native skill set optimized for AI coding assistants.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.