AI product Open source
Gemini API CLI is an experimental command-line interface for the Gemini Interactions API and managed-agent platform. It can run model interactions and managed agents, generate or analyze text and media, transcribe audio or video, manage files, models, agents, environments, triggers, and webhooks, and stream results in formats including JSON, YAML, and TOON. Commands expose machine-readable usage information and request schemas, while --dry-run validates inputs and previews redacted HTTP requests without contacting the API. Authentication can use API keys, OAuth access tokens, an operating-system keychain, or a configuration file. The repository describes the CLI as beta software with possible breaking changes, generated through Speakeasy; its software is licensed under Apache 2.0, and the repository states that it is not an official Google product.
2 uses taken from transcripts — each links to the moment in the video.
An open-source command-line interface for getting started with Gemini models and testing them locally through simple CLI commands. It also supports packaging local coding-agent work into a folder and uploading it to create an agent.
A CLI for the Gemini API intended for coding agents rather than humans, letting them call models like Nano Banana and Omni to generate assets and create, iterate on and improve agents. Ships with dedicated skills for the Interactions and Agents APIs.
2 in the library.