Google Releases Open-Source Gemini CLI AI Tool for Developers
Google introduces Gemini CLI, an open-source AI command-line interface leveraging Gemini 2.5 Pro for developer workflows, now available under Apache 2.0 license.
Google has released Gemini CLI, an open-source AI command-line interface that integrates the capabilities of its Gemini 2.5 Pro model directly into developers' terminals. The tool, designed for flexibility and transparency, is available under the Apache 2.0 license, allowing developers to inspect, modify, and extend the source code.
Key Features
- Gemini 2.5 Pro support with a 1 million token context window
- Prompt grounding with Google Search for real-time web context
- Built-in Model Context Protocol (MCP) and custom system prompts (via
GEMINI.md
) - Non-interactive scripting mode for AI-powered terminal automation in CI/CD workflows
Developers can access Gemini CLI for free after authenticating with a Google account under a Gemini Code Assist license. Advanced users can also configure it with API keys from Google AI Studio or Vertex AI for higher-volume use cases.
Supported Workflows
- Writing, refactoring, and debugging code
- Automating terminal tasks and shell scripting
- Researching technical topics or documentation
- Generating structured content or markdown
- Performing local file and system-level operations
Google encourages community contributions via the Gemini CLI GitHub repository. The release reflects Google's push toward open, extensible AI tooling.
User Feedback
Initial reactions highlight areas for improvement. One developer noted:
"Tried a bit just now; for my not-too-difficult task, it firstly searched a codebase for 4 minutes, then ended up asking to explore the code in another codebase, to which all calls were commented out. Doesn't feel close to Claude Code yet."
Another user reported:
"Well, it is fine until 5 minutes into the session, when it switches the model to flash, which is entirely awful at coding."
For IDE users, Gemini Code Assist now shares agent technology with Gemini CLI, offering multi-step planning and reasoning-based code generation in VS Code for free.
Gemini CLI is available at cli.gemini.dev and requires only a Google login to start.
Related News
Lenovo Wins Frost Sullivan 2025 Asia-Pacific AI Services Leadership Award
Lenovo earns Frost Sullivan's 2025 Asia-Pacific AI Services Customer Value Leadership Recognition for its value-driven innovation and real-world AI impact.
Baidu Wenku GenFlow 2.0 Revolutionizes AI Agents with Multi-Agent Architecture
Baidu Wenku's GenFlow 2.0 introduces a multi-agent system for parallel task processing, integrating with Cangzhou OS to enhance efficiency and redefine AI workflows.
About the Author

Dr. Lisa Kim
AI Ethics Researcher
Leading expert in AI ethics and responsible AI development with 13 years of research experience. Former member of Microsoft AI Ethics Committee, now provides consulting for multiple international AI governance organizations. Regularly contributes AI ethics articles to top-tier journals like Nature and Science.