Gemini CLI vs Goose: pricing, features and which to choose

Gemini CLI is Google's open source terminal agent for developers, students, researchers, and technical users who prefer a shell over a browser or IDE. Google launched it on June 25, 2025, connecting the client to Gemini Code Assist technology. The Apache License 2.0 covers the client, which supports coding, content generation, problem solving, research, and task management. A session begins with the gemini command and a prompt that can reference files in the working directory. The agent can read and edit files, run shell commands, fetch web content, and use Google Search grounding. Its repository reported more than 107,000 stars, 14,000 forks, and hundreds of contributors in October 2026. Google also reported millions of users in its May 2026 transition announcement.

Gemini CLI supports persistent project instructions through GEMINI.md files, while checkpointing and chat history help users resume work. Model Context Protocol support connects local or remote tools, and extensions add services including databases, BigQuery, Cloud Run, and security analysis. Headless mode accepts positional prompts and returns text, JSON, or streaming JSON for scripts and automation. Approval controls allow users to review commands and edits before execution. Gemini CLI launched with Gemini 2.5 Pro and a 1 million token context window. Google later added Gemini 2.5 Flash Lite, prompt completion, structured JSON output, improved editing, citations, database extensions, and broader MCP handling. In February 2026, Google announced Gemini 3.1 Pro preview support. The repository advertises Gemini 3 models and weekly stable and preview channels.

Claude Code is a direct alternative for developers committed to Anthropic models and its paid workflow. OpenAI Codex CLI fits teams already using Codex models or ChatGPT. Gemini CLI differs through Gemini models, Google Search grounding, MCP support, and Google Cloud integrations. It has no standalone subscription, although paid API and cloud routes require separate credential, quota, and billing administration. The client is Apache License 2.0 software, but that license does not cover Google's models or services. Choose Gemini CLI if you need Google's terminal tools, Search grounding, MCP, or Cloud integrations through an enterprise or paid API route. Choose Claude Code for Anthropic's workflow, or OpenAI Codex CLI for Codex and ChatGPT users. Gemini CLI is best for Google focused teams that want an inspectable terminal client.

Goose is Block’s open source terminal AI agent for developers and technical teams. Launched on January 28, 2025, it began with software engineering work such as code migrations, dependency installation, test execution, and file changes, then expanded toward research, writing, automation, and data analysis. The project uses the Apache License 2.0, allowing commercial use, modification, and distribution subject to its terms. Goose runs on the user’s machine through desktop applications for macOS, Linux, and Windows, plus a terminal client and API. Users can edit files, execute commands, and run tests. The project is active, costs $0, and does not include model usage. Block reported that about 12 specialists built the original system over nine months.

A Goose session starts in the desktop app or CLI after the user selects a language model provider. Goose sends the request and tool descriptions to that model, executes returned tool calls, and sends results back for another turn. Built in and external MCP extensions can add shell commands, file operations, web access, memory, browser automation, and application specific actions. Users can save sessions, resume them across desktop and CLI, create reusable recipes, and connect remote MCP services. Permission modes include automatic execution, approval before actions, conversation without tools, and smart approval. Permissions can also be set for each extension with allow, deny, or approval behavior. Goose supports hosted providers and local Ollama models.

Goose fits developers automating code changes, tests, shell workflows, and repeatable MCP recipes, along with teams requiring Apache licensed software, local execution, provider choice, and configurable permissions. It is less suitable for people seeking a zero setup hosted coding assistant, teams unable to review commands and extension permissions, or users wanting one bill that includes model usage. Continue and Gemini CLI are closer terminal alternatives, while Claude Code and Cursor offer more managed coding experiences. Compared with Gemini CLI, Goose puts more emphasis on model independence, local deployment, desktop and CLI access, MCP extensions, and configurable autonomy. Choose Goose when those priorities matter more than bundled inference and simpler onboarding. Developers and technical teams wanting local, open source agentic coding should pick Goose.