Google announced Gemini CLI on June 25, 2025 as a free and open-source tool that brings Gemini directly into developers’ terminals.
Google says the Gemini CLI preview provides code understanding, file manipulation, command execution and dynamic troubleshooting for developers working from the command line.
Google says individual developers can use Gemini 2.5 Pro through Gemini CLI with a personal Google account at 60 model requests per minute and 1,000 model requests per day at no charge during the preview.
Google says professional developers can use a Google AI Studio key, a Vertex AI key or a Gemini Code Assist Standard or Enterprise license when they need usage-based billing, specific models or multiple simultaneous agents.
Google says Gemini CLI can ground prompts with Google Search, extend capabilities through Model Context Protocol support or bundled extensions, customize prompts and instructions, and run non-interactively inside scripts.
Google says Gemini CLI is open source under the Apache 2.0 license so developers can inspect the code, understand how it works and verify its security implications.
The Gemini CLI GitHub README describes Gemini CLI as an open-source AI agent for the terminal and lists built-in tools for Google Search grounding, file operations, shell commands and web fetching.
The Gemini CLI GitHub README lists MCP support for custom integrations, terminal-first usage, Apache 2.0 licensing, a free tier of 60 requests per minute and 1,000 requests per day with a personal Google account, and access to Gemini 3 models with a 1M-token context window.
The Gemini CLI installation documentation says most users can install Gemini CLI with npm, Homebrew on macOS or Linux, MacPorts on macOS, or Anaconda, and it says Gemini CLI comes pre-installed on Cloud Shell and Cloud Workstations.
The installation documentation says Gemini CLI can run without permanent installation through npx, and it says Gemini CLI can run inside a container for security and isolation when tools might have side effects.
