HomeProjectsArticlesPK BoardAbout
Explore Projects

Gemini CLI

Active
GitHub TypeScript Apache-2.0

Description

Gemini CLI is a terminal-based AI agent tool from Google that supports code generation, file operations, and multi-turn conversations with a free usage tier.

Key Features

  • Gemini 3 model access - 1M token context window with improved reasoning capabilities
  • Built-in tool suite - Google Search grounding, file operations, shell commands, and web fetching
  • MCP protocol extensibility - connect custom tools and services via Model Context Protocol
  • Multimodal code generation - create full apps from PDFs, images, or sketches
  • GitHub Action integration - automated PR reviews, issue triage, and @gemini-cli on-demand assistance
  • Non-interactive scripting - run in scripts with JSON or stream-json output formats

Use Cases

💡 Query, edit, and debug large codebases directly from the terminal
💡 Automate GitHub workflows like PR reviews and issue triage with natural language
💡 Build personal projects using the free tier (60 req/min, 1000 req/day)
💡 Integrate into CI/CD scripts for automated code analysis and deployment tasks
💡 Extend capabilities with MCP servers for media generation, database queries, and more

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (106.8k stars)
  • • Permissive open-source license (Apache-2.0)
  • • Responsive to issues, low backlog

Tags

coding cli agent google typescript

Categories

💻 Coding Agent

Quick Start

# Run instantly without installation
npx @google/gemini-cli

# Or install globally
npm install -g @google/gemini-cli

# Start interactive session
gemini

# Non-interactive mode: single prompt
gemini -p "Explain the architecture of this codebase"
Visit GitHub Visit Website

Related Projects

Qwen Code

27.6k · TypeScript
Active A

An open-source AI coding agent that lives in your terminal, built by Qwen team with support for code generation, editing, debugging and multi-file operations.

codingllmtypescript +2
  • · Multi-protocol multi-provider — supports OpenAI, Anthropic, Gemini-compatible APIs with Alibaba Cloud, OpenRouter and more
  • · Qwen3-Coder co-evolution — both framework and Qwen3-Coder model are open-source and ship together
  • · Built-in Skills and SubAgents — rich built-in tools for full agentic workflow with Claude Code-like experience
View full details → View on GitHub

Learn Claude Code

75.9k · Python
Active A+

A nano claude code-like agent harness built from scratch, demonstrating how to build AI coding assistants from zero to one.

codingagenttypescript +2
  • · Agent Harness architecture teaching - Systematic coverage of Tools + Knowledge + Observation + Action + Permissions five-layer architecture
  • · Build Claude Code from scratch - Implement a complete AI coding assistant in Bash, covering file ops, shell execution, and context management
  • · Harness engineering methodology - Deep exploration of the core philosophy: agency comes from training, harness comes from engineering
View full details → View on GitHub

Related Articles

AI 编程Coding AgentCLI

AI Coding Agents Deep Dive: Architecture Trade-offs from CLI to IDE-Integrated

A deep architectural comparison of seven open-source coding agents across three paradigms — CLI-first, IDE-integrated, and fully autonomous — examining context management, tool access, and autonomy levels to help you pick the right tool for each development scenario.

Read more →
Cursor开源替代AI 编程

Open-Source Cursor Alternatives in 2026: Claude Code vs Cline vs Aider vs OpenCode vs Codex CLI

A 2026 comparison of the most worthwhile open-source Cursor alternatives — Claude Code, Cline, Aider, OpenCode, Codex CLI, Gemini CLI, Continue, and more — covering IDE integration, model support, MCP compatibility, privacy, and cost, with scenario-based selection guidance.

Read more →
Google ADKGeminiVertex AI

Google ADK (Agent Development Kit) in Practice: A2A Protocol, Vertex AI Integration, and Java Dual-Language

Google ADK is Google's official agent SDK with dual-language Python and Java support and deep integration with Vertex AI and the Gemini models. This article walks through ADK's four cores — Agent, Tool, Session, and the A2A protocol — compares it with LangGraph, OpenAI Agents SDK, and Claude Agent SDK, and provides an enterprise deployment path.

Read more →