Gemini API CLI

Gemini API CLI is an open-source, experimental command-line utility that gives AI coding agents, shell scripts, and developers direct access to Google's Gemini API. Written in Go, it runs on Windows, macOS, and Linux as a standalone binary. It supports text generation, reasoning, image editing, music creation, video generation, and text-to-speech synthesis. Users can analyze PDFs, images, audio, videos, and YouTube content or generate transcripts and subtitles. The software also launches managed AI agents for asynchronous research and other complex tasks. Built-in commands manage models, uploaded files, credentials, and agent environments. Structured JSON output, dry-run validation, and automatic command discovery simplify integration with Codex, Claude Code, and other AI assistants. The project is currently in beta.