Gemini CLI
Gemini CLI is Google's open-source AI agent for the terminal. It gives you direct access to Gemini models from the command line and can read and edit your codebase, run shell commands, fetch web pages and ground answers with Google Search, all inside an interactive session.
It is aimed at developers who spend most of their day in a terminal. Typical uses include asking questions about and refactoring a large codebase, debugging with natural-language explanations of errors, automating repository chores such as querying pull requests or working through a complex rebase, and running it non-interactively in scripts. A companion GitHub Action brings the same agent into pull-request reviews and issue triage, and MCP servers extend it with custom tools.
Getting started: run it instantly with `npx @google/gemini-cli`, or install it with `npm install -g @google/gemini-cli` or Homebrew. On first launch you can sign in with a Google account, which includes a free tier (60 requests per minute and 1,000 per day), or use a Gemini API key or Vertex AI for more control and enterprise setups. A GEMINI.md file in your project tailors its behaviour.
Features
Why choose it
Trade-offs
Maintenance check
- Last commit
- 2026-10-23
- Commits, last 90 days
- 100+
- Releases, last 90 days
- 30
- Latest release
- v0.67.0-nightly.20261024.gcd1b45c2d (2026-10-24)
- Open issues
- 762
- Recent issues with at least one comment
- 13/21
Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.
Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.
Most discussed open issues
- #16750 "Allow for session" only allows once for shell commands that include a path159 comments · 2026-01-15
- #24937 Tracking: 429 / Capacity Issues131 comments · 2026-04-08
- #19532 Add gemini-3.1-pro-preview127 comments · 2026-02-19
- #23316 Long-Context & Complex Reasoning Coding Evaluation Dataset80 comments · 2026-03-20
- #23331 GSoC Behavioral evals, Quality, and the OSS Community83 comments · 2026-03-21
Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.
Who it fits
- You want an Apache-2.0 terminal coding and task agent from Google with a generous free tier using a personal Google account.
- You want built-in file editing, shell execution, Google Search grounding, MCP server support, and a GitHub Action for CI.
- You want to switch freely between Claude, OpenAI, DeepSeek, and local Ollama models inside the same terminal agent; Open Interpreter supports any OpenAI-compatible provider.
- You prefer a graphical desktop workspace over a command-line interface; AionUi or Cherry Studio provide GUI clients.
How it differs
vs Open Interpreter★ 68.7kGemini CLI is Google's official terminal agent built around Gemini models (with a free Google-account tier and Google Search grounding). Open Interpreter is a Rust-based terminal coding agent that works with any model provider and emulates multiple agent harnesses (Claude Code, Qwen Code, SWE-agent).
Compatibility
Quick start
Use cases
Alternatives
Comments
No comments yet. Be the first!