Google has published new command line tools on GitHub that simplify the use of Gmail, Drive, and other Workspace services for AI agents. This tool bundles various Google Workspace APIs into one interface.
The Next Web reported. This tool is called gws and provides access to virtually the entire Google Workspace ecosystem via the command line. Developers can use it to control Gmail, Google Drive, Calendar, Docs, Sheets, Slides, and more. GWS allows you to use these services through a single interface, whereas previously you had to deal with multiple APIs separately.
For AI agents, this means obvious simplifications. Until now, agents had to combine different APIs, each with its own authentication and structure, to search for emails, retrieve documents from Drive, and schedule events on calendars. New tools integrate these interactions and provide results in a structured JSON format, a format that AI systems can easily process.
What’s remarkable about this architecture is that the tool does not include a fixed set of commands. Instead, gws retrieves information from Google’s Discovery service while it is running. A function is dynamically generated based on this. When Google adds new API functionality, it automatically appears in the CLI without any updates. This is an important advantage for systems that need to function autonomously for long periods of time.
Predefined agent skills
In addition to basic access, the repository includes a set of predefined workflows that automate common workspace actions. These so-called agent skills allow you to control tasks such as uploading files to Drive, editing spreadsheets, and scheduling calendar events directly from the agent framework.
This document mentions OpenClaw, an open source platform for AI agents that gained a lot of attention in early 2026. The project was started in late 2025 by Austrian developer Peter Steinberger and quickly grew into a popular platform for autonomous agents. Shortly after, OpenAI announced that Steinberger would be joining the company to work on a new generation of personal AI agents.
It’s impressive that Google mentions OpenClaw in the new tool’s documentation, but it’s unclear whether this is an intentional strategic move. What is clear is that Google is building the infrastructure to connect to a growing ecosystem around AI agents.
The CLI also acts as a server for the Model Context Protocol, an open standard that allows AI systems to use external tools. This protocol was developed by Anthropic and is currently supported by various development platforms. By making Workspace features available through this protocol, a variety of AI clients can communicate directly with Google Workspace.
This positions Google Workspace as a platform where autonomous AI systems can be accessed, regardless of the model or framework behind them. The development is part of a broader trend in which technology companies are building infrastructure that provides AI agents with access to business software and data.
Tech giants focus on AI agents
Microsoft is focusing on Copilot functionality within its productivity software, and OpenAI is working on a system to control personal agents. Meanwhile, Google is developing its own agent ecosystem around Gemini and building tools to enable integration with external agent frameworks.
Google presents the gws repository as a developer sample and not as an officially supported product. This means there are no guarantees regarding stability or long-term support. This is typically not a big issue in experiments, but organizations that want to give agents access to business data may want to consider this limitation.
Despite this warning, the repository received thousands of stars on GitHub shortly after publication. This suggests that developers using AI agents are quickly realizing the importance of such infrastructure. While the AI industry often focuses on models and chat interfaces, the next stage of competition seems increasingly to be about systems that provide access to data and business software.
