AgentIndex icon
AgentIndex
ToolsCategoriesTrendingNewCompare
Submit Tool
Home/
Workflow Automation/
Gemini CLI
Gemini CLI logo

Gemini CLI

Active·★ 104.7k·Apache-2.0·Updated 2026-05-29
★ Most Popular★ Trending★ Essential

An open-source AI agent that brings the power of Gemini directly into your terminal. Supports native MCP.

Gemini CLI is Google's open-source AI agent for the terminal, providing direct access to Gemini models with a free tier of 60 requests/minute and 1,000/day. It ships with built-in tools for Google Search grounding, file operations, shell command execution, and web fetching, plus native MCP support for custom integrations. Built for developers who work primarily in the command line.

#CLI#AI Agent#Gemini#Node.js#Automation
$ Install
$ npm install -g @google/gemini-cli
↗ Visit site★ GitHub
01

Features

01Free tier: 60 req/min and 1,000 req/day with a personal Google account
02Built-in tools: Google Search grounding, file ops, shell commands, web fetch
03Native MCP support for custom tool integrations
04Access to Gemini 3 models with 1M token context window
05Open source under Apache 2.0 license
02

Compatibility

macOS
Native
Verified via docs
Linux
Supported
Verified via docs
Windows
Supported
Verified via docs
Node.js
Node.js 18+
Verified via docs
03

Quick start

1
$ npm install -g @google/gemini-cli
04

Use cases

↳Running AI-assisted development tasks directly in the terminal without switching contexts
↳Automating shell workflows with natural language instructions and real-time web grounding
↳Extending terminal AI capabilities with custom MCP servers for project-specific tools
05

Alternatives

dagster logo
dagster★ 15.6k
An orchestration platform for the development, production, and observation of data assets.
vs →
Figma-Context-MCP logo
Figma-Context-MCP★ 14.9k
MCP server to provide Figma layout information to AI coding agents like Cursor
vs →
ragflow logo
ragflow★ 81.5k
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
vs →
GitHub MCP Server logo
GitHub MCP Server★ 30.3k
GitHub's official MCP Server. Allows AI agents to interact directly with your GitHub repositories (read files, search code, issues).
vs →
Open Interpreter logo
Open Interpreter★ 63.7k
A natural language interface for computers. Lets LLMs run code (Python, Javascript, Shell, etc.) locally on your machine.
vs →
UI-TARS-desktop logo
UI-TARS-desktop★ 35.7k
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
vs →
GPT Researcher logo
GPT Researcher★ 27.4k
An LLM agent that conducts deep research (local and web) on any given topic and generates a long report with citations.
vs →
awesome-n8n-templates logo
awesome-n8n-templates★ 22.6k
Supercharge your workflow automation with this curated collection of n8n templates! Instantly connect your favorite apps-like Gmail, Telegram, Google Drive, Slack, and more-with ready-to-use, AI-powered automations. Save time, boost productivity, and unlock the true potential of n8n in just a few clicks.
vs →
See all alternatives →

Related searches

Gemini CLI AlternativesBest Workflow Automation Tools 2026Open Source Workflow AutomationGemini CLI TutorialGemini CLI Vs CompetitorsCLIAI AgentGemini

Comments

Log in to leave a comment
  • M
    Morgan AndersonMay 23, 2026

    context window handling on long conversations is better than expected. doesn't degrade noticeably on extended sessions

  • R
    Riley HarrisMay 7, 2026

    The open-source model makes it auditable and customizable, unlike the official Gemini CLI.

  • S
    Sasha ChenMay 6, 2026

    Works well for terminal-centric development workflows. Responsive and solid on Apple Silicon.

  • C
    Casey GarciaMay 4, 2026

    Open-source terminal AI agent with native MCP support — good alternative to proprietary CLI tools.

  • S
    Spencer BrownMay 4, 2026

    Not a heavy terminal user but this made me one. Ask questions, get answers, stay in the flow.

  • J
    Jamie LewisApr 9, 2026

    Runs well on Node 18 and 20. The streaming output is smooth — no janky rendering like some other CLI tools. Works behind corporate proxies with standard env vars.

  • R
    Remy KimMar 30, 2026

    Gemini directly in the terminal with MCP integration is the workflow I've been waiting for.

  • D
    Dakota ClarkMar 20, 2026

    The multimodal support in the terminal is surprisingly usable. Passing images for analysis via CLI feels natural once you get used to it.

  • R
    Riley WhiteMar 15, 2026

    for automating research tasks from scripts or CI this integrates cleanly. the JSON output mode is well-designed

  • M
    Morgan AndersonMar 12, 2026

    Native MCP support means it slots into existing agent infrastructure without adapters.

  • L
    Logan BrownFeb 4, 2026

    replaced my old shell aliases with gemini-cli for quick research tasks. the terminal-native feel is exactly right

  • K
    Kendall BrownJan 25, 2026

    Wrote a tutorial on AI-powered terminal workflows featuring Gemini CLI. The MCP integration story is the best angle for developers already in the ecosystem.

  • D
    Dylan WilsonJan 6, 2026

    Gemini CLI's native MCP support is the killer feature. Plugs directly into my existing MCP server setup without any adapter layer.

  • C
    Corey LewisJan 2, 2026

    As a solo dev, having Gemini's long context window accessible from the terminal is a genuine productivity boost. No context switching to a browser.

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
Stats
GitHub Stars★ 104.7k
Last commit1d ago
StatusActive
LicenseApache-2.0
CategoryWorkflow Automation
Trend (30d)
+4.1k↑ 4.8%
Links
Documentation↗Discussion↗Issues↗Releases↗

Deploy on DigitalOcean — Get $200 Free Credit

Ad
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
QYSGitHubBuy me a coffee ☕

Browse by Category

Code AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.