Development · Developer Tools
llm-gemini is a plugin extending the LLM command-line tool created by Simon Willison. It adds support for Google's Gemini family of models via the Google AI API, letting you use Gemini directly from the terminal and through the LLM library's Python API. The project is open source (Apache-2.0), written in Python and published on PyPI as the llm-gemini package.
Installation is a single command: llm install llm-gemini. The API key is set via llm keys set gemini or the LLM_GEMINI_KEY environment variable (a key from Google AI Studio). The plugin supports interactive chat (llm chat), multimodal input (images, audio, video — files and URLs), YouTube video processing, JSON and structured output (schemas), server-side code execution, Google Search grounding, URL context fetching and embedding models, plus a command listing all available Gemini models.
The project is authored and maintained by Simon Willison. It requires Python 3.10 or newer, an internet connection and a Google AI API key. The latest version is 0.33 (August 2026).
An API Library is a software package that exposes programmatic interfaces for communicating with a device, service, or system. In robotics it typically forms a lightweight integration layer built on top of the manufacturer's official API or an open-source project, abstracting low-level protocol details and providing language-native bindings (Python, C++, Java, etc.).
A CLI Tool (Command-Line Interface Tool) is a program run from a terminal or shell, used for administration, integration, configuration, testing, and diagnostics of robotic devices and software systems. CLI tools are common in robotics workflows for flashing firmware, configuring network settings, running diagnostics, launching processes, and automating repetitive tasks in CI/CD pipelines.
A Developer Tool is software designed to support the development workflow, including configuration, debugging, testing, monitoring, validation, and integration of robotic and embedded systems. Examples include IDE plugins, visual debuggers, log analysers, hardware-in-the-loop (HIL) test harnesses, and code-generation utilities specific to robotics platforms.
Widely used within Simon Willison's LLM tool ecosystem — for experimentation, scripting and data pipelines that use Gemini models from the command line.
github.com/simonw/llm-gemini ~454★, ~57 forks (August 2026). PyPI llm-gemini: ~82k downloads/month (~23.7k/week). Actively developed — latest version 0.33 (August 13, 2026).
Ubuntu 24.04 LTS 'Noble Numbat' — supported until April 2029. The host for ROS 2 Jazzy.
Requires Python 3.10+, an internet connection and a Google AI API key (Google AI Studio). Model computation runs on Google's side.
License family: Permissive
No version history.
