LIVE
Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|
PluginRisingofficial publisher

Gemini CLI et Antigravity CLI extensions

Plugin : A set of capabilities installed into an AI application or a host · requires gemini-cli

Third-party extensions for Google's CLI, in transition to Antigravity CLI.

Wait and see: Google does not vet third-party extensions and the CLI is being renamed.

Official site GitHub · 108,162 ★
Overall score
6.9 /10
Security: one caveat, see the card
Utility
6.0
Reliability
10.0
Security
One caveat
Ease
5 min · Technical

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Gemini CLI is an open-source command-line agent published by Google, allowing users to interact with Gemini models directly from the terminal. It addresses the needs of developers who want to query codebases, automate tasks, or generate code without leaving their usual working environment.

In practice, the tool is installed via npm, Homebrew, or MacPorts, then launched with the gemini command. It includes built-in tools: Google Search grounding, file operations, shell command execution, and web fetching. It supports the MCP (Model Context Protocol) for connecting third-party servers, and accepts GEMINI.md context files to customize behavior per project.

The extension system allows adding third-party capabilities: over 1,800 extensions are listed on the official site, covering use cases ranging from GitHub integration to academic research. Since June 18, 2026, users on the free tier and Google One have been migrated to Antigravity CLI, a name change that directly affects these extensions.

Gemini CLI is aimed at developers comfortable with the terminal who want direct access to Gemini models for code analysis, workflow automation, or external tool integration. It is not suited for users who prefer a graphical interface or who are looking for a ready-to-use tool requiring no configuration.

What it offers

  • ·Free access to Gemini models with 60 requests per minute and 1,000 requests per day using a personal Google account.
  • ·One million token context window for analyzing large codebases or long documents.
  • ·Built-in tools: real-time Google Search grounding, file operations, shell command execution, and web fetching.
  • ·MCP (Model Context Protocol) support for connecting third-party servers and extending the tool's capabilities.
  • ·Third-party extension system with over 1,800 extensions listed, installable from public GitHub repositories.
  • ·Non-interactive mode for integrating Gemini CLI into scripts and automated workflows, with structured JSON output.
  • ·Save and resume complex sessions using the checkpointing system.
  • ·GitHub integration via an official action for code reviews, issue triage, and on-demand assistance. (paid for extended limits via Vertex AI)

In practice

Price
Free
Commercial use
Commercial use: yes
Available on
cli
Host
gemini-cli
Licence
Apache-2.0
FR interface
No

Security and data

Rating
Security: one caveat, see the card
Your data
Data with the vendor
Known incidents
Depuis le 18 juin 2026, Gemini CLI ne sert plus les abonnés Pro/Ultra ni le gratuit ; fusion dans Antigravity CLI.
Maintenance
Active
Last release
20 October 2026

Links and repository checked on 25 October 2026 · added on 1 June 2025

How to install Gemini CLI et Antigravity CLI extensions

1. Make sure Node.js is installed on your machine. 2. Install Gemini CLI globally with npm: npm install -g @google/gemini-cli (or via Homebrew on macOS/Linux: brew install gemini-cli). 3. Launch the tool with the gemini command. 4. Choose your authentication method: sign in with your Google account (free tier) or use a Gemini API key. 5. Before installing any third-party extension, read its source code on GitHub to understand the permissions it requests and the actions it may perform.
npm install -g @google/gemini-cli

In the same category

Whole category Code →