Gemini CLI Hub: Free Tier Quota, Google Sign-in, GEMINI.md and Extensions
Guide to Google's Apache-2.0 open-source terminal agent (google-gemini/gemini-cli): free quota with a personal Google account, GEMINI.md instructions, sandboxing and MCP extensions.
Key takeaways
- Gemini CLI (`google-gemini/gemini-cli`) is Apache-2.0 open source and offers a generous free tier when signing in with a personal Google account.
- Includes built-in Google Search grounding, file tools and shell execution backed by Gemini's large context window.
- Configured via hierarchical `GEMINI.md` files, `~/.gemini/settings.json`, MCP servers and Gemini CLI extensions.
- Supports `--sandbox` execution using macOS Seatbelt, Docker or Podman containers.
Key facts: pricing, models, surfaces & safety
Sign in with a personal Google account for free Code Assist quota, or connect a paid Gemini API key or Google Cloud Vertex AI project for higher rate limits and enterprise data governance.
Runs Gemini models directly through Google account login, `GEMINI_API_KEY`, or Vertex AI enterprise endpoints.
Distributed via npm (`npx @google/gemini-cli`) and runs in any terminal or integrated IDE shell.
Asks confirmation before modifying files or running shell commands by default; `--sandbox` isolates execution inside Seatbelt, Docker or Podman.
Extension points: GEMINI.md, settings.json and Extensions
Ecosystem tools integrate with Gemini CLI through three mechanisms:
GEMINI.md
Hierarchical context files loaded from `~/.gemini/GEMINI.md` and the project workspace.
~/.gemini/settings.json
Configures sandbox defaults, approval behavior and connected MCP servers.
Gemini CLI Extensions
Reusable extension packages bundling custom tools, prompts and MCP integrations.
Setup & troubleshooting guides
Gemini CLI ecosystem & extensions
Plugins, config packs, switchers and orchestration layers in the directory built for Gemini CLI, by stars; each has its own FARS review.
Multi-agent orchestration, parallel sessions & workbenches
Claude Code Skills & Plugins
A library of 362 production-ready skills, plugins, and agent skills for 13 AI coding tools, covering engineering, marketing, product, compliance, C-level advisory, and more.
Vibeyard
An IDE purpose-built for AI coding agents, making multi-session management, cost tracking, and task planning effortless.
CCManager - AI Agent Session Manager
Manage sessions for Claude Code, Gemini CLI, Codex CLI, and other AI coding assistants across Git worktrees and projects.
Parallel Code
Dispatch Claude Code, Codex, and Gemini coding agents in parallel, each isolated in its own git worktree — run ten branches in one afternoon and merge only the wins.
Cross-session memory & context tools
Plugins, routing & companion extensions
Caveman Token-Saving Toolkit
Reduce coding-agent token use by compressing what agents read and shortening what they say.
Agentic Plugin Marketplace
Composable developer-workflow plugins for multiple coding-agent harnesses.
gws for Google Workspace
A dynamic CLI for calling Google Workspace APIs with structured JSON output for scripts, operators, and AI-assisted workflows.
Plannotator
Visually annotate your coding agent's plans and diffs in the browser and send feedback back with one click.
Coucou Agent Companion
Keep coding-agent sessions and approval requests in view on your Mac, then follow them from your iPhone.
Obsidian Mind
Persistent, searchable memory for AI coding agents across sessions and repositories.
Council of High Intelligence
Put consequential decisions through independent analysis, direct challenge, and a verdict that preserves dissent.
cc-skills-golang: Agent Skills for Production-Ready Go
A curated, human-reviewed collection of Golang agentic skills covering code style, testing, security, performance, and more, ready for any compatible AI coding assistant.
CCB Multi-Agent Terminal Workspace
Coordinate multiple AI coding CLIs in visible terminal panes you can directly take over.
Designer Skills Pack
Agentic skills, commands, and plugins for design — from research to systems, UI, interaction, and delivery.
Open Computer Use (MCP desktop service)
An MCP service for running desktop Computer Use operations from AI clients.
VibeKit — Safety Layer for Coding Agents
Run Claude Code, Gemini, Codex and more in an isolated sandbox with built-in sensitive data redaction and observability.
agmsg Cross-Agent Messaging
A local SQLite message layer for coordinating CLI coding agents across tools.
COG Second Brain
A self-evolving, local-first second brain that turns daily braindumps, team intelligence, and PM workflows into verified knowledge using plain Markdown files and AI agents.
Agent Deck
One terminal TUI to run, monitor, and switch between every Claude Code, Codex, and Gemini CLI session — with forks, worktrees, cost tracking, and phone-controlled orchestration.
Chisle
Cut your AI coding agent's token bill on three axes — terser prose, YAGNI-first code, compressed tool output — without losing accuracy.
Claude Codex Settings
Battle-tested Claude Code, Codex CLI, and Cursor configs, plugins, hooks, and agents with Kimi, MiniMax, and GLM API support — fixing the failure modes of AI coding assistants.
claude-replay
Turns AI coding agent sessions into self-contained, embeddable interactive HTML replays that are easy to share.
Agent Manager
One tmux TUI that puts every AI coding agent in a single list with live status, quick prompts, and diff review.
Browse Gemini CLI skills on FollowSkills → Switching Gemini CLI between model providers? Read the CC Switch guide →
Gemini CLI comparisons & rankings
AI coding agents, ranked
Gemini CLI, Cline, OpenCode, Kilo Code, Aider, Qwen Code and more ranked by one FARS source review, with license, stars and maintenance; Claude Code and Codex CLI are listed but unscored.
View full category ranking →Open Source Coding Agents, Compared
Open source coding agents ranked by FARS review — score, trust, license, language and maintenance side by side, with what each one is and isn't good at.
12 reviewed agents comparedRelated concepts
Frequently asked questions
Does the free Gemini CLI tier train on my code?
Data terms differ between the free personal Google account tier and paid API / Vertex AI tiers. For proprietary codebases, use a paid Gemini API key or Vertex AI enterprise credentials with data-logging disabled.
How do I enable sandboxing in Gemini CLI?
Pass `-s` or `--sandbox` on startup or enable `sandbox` in `~/.gemini/settings.json` to run shell commands inside macOS Seatbelt or a Docker/Podman container.