Credit: Google

The command line is hot again. For some people, command lines were never not hot, of course, but it’s becoming more common now in the age of AI. Google launched a Gemini command line tool last year, and now it has a new AI-centric command line option for cloud products. The new Google Workspace CLI bundles the company’s existing cloud APIs into a package that makes it easy to integrate with a variety of AI tools, including OpenClaw. How do you know this setup won’t blow up and delete all your data? That’s the fun part—you don’t.

There are some important caveats with the Workspace tool. While this new GitHub project is from Google, it’s “not an officially supported Google product.” So you’re on your own if you choose to use it. The company notes that functionality may change dramatically as Google Workspace CLI continues to evolve, and that could break workflows you’ve created in the meantime.

For people who are interested in tinkering with AI automations and don’t mind the inherent risks, Google Workspace CLI has a lot to offer even at this early stage. It includes the APIs for every Workspace product, including Gmail, Drive, and Calendar. It’s designed for use by humans and AI agents, but like everything else Google does now, there’s a clear emphasis on AI.

The tool supports structured JSON outputs, and there are more than 40 agent skills included, says Google Cloud director Addy Osmani. The focus of Workspace CLI seems to be on agentic systems that can create command line inputs and directly parse JSON outputs. The integrated tools can load and create Drive files, send emails, create and edit Calendar appointments, send chat messages, and much more.

The Git suggests Google sees CLI as a cleaner alternative to Model Context Protocol (MCP) setups, which can require a lot of development overhead to connect AI applications. The new CLI does have an MCP server option to connect bots like Claude and Gemini CLI, though.

The claw is coming

The upshot is that connecting AI agents to Google’s cloud is getting easier. Google Workspace CLI should be much quicker to set up, with fewer points of failure and lower API usage than non-CLI methods. It even has dedicated support for OpenClaw, the agentic AI platform that turns LLMs loose on your data and tasks.

OpenClaw has gained enormous traction in recent weeks, allowing users to construct powerful agentic workflows by chatting with the bot via their favorite apps. Of course, empowering generative AI to do things like that comes with risks. The bot can hallucinate and wreck all that data you’ve told it to manage. It’s also vulnerable to security issues like prompt injection attacks, which can trick the robot into disclosing sensitive data.

You can use Google Workspace CLI without diving into the uncertainties of OpenClaw. All you need to get started is a Google account with Workspace access, OAuth credentials for a Google Cloud project, and Node.js. For teams that need to access multiple Workspace APIs, the release of Google Workspace CLI could be a big relief, even if it’s not an official product just yet.