Google opens Workspace to AI agents with new CLI that connects OpenClaw to Gmail and Drive

Google's new command line tool can plug OpenClaw into your Workspace data

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.

Google makes Gmail, Drive, and Docs 'agent-ready' for OpenClaw

Google appears to be positioning its Workspace ecosystem for an agent-ready future where AI tools manage daily productivity tasks. Google has quietly released a command-line interface for Workplace that paves the way for agentic AI tools like OpenClaw to tap into your core Google apps and data. Published on GitHub just a few days ago, the Google Workspace CLI makes it much easier for AI agents to connect to Gmail, Google Drive, Google Docs, and other key Google Workspace services. The Google Workspace CLI documentation includes specific instructions for OpenClaw integration, meaning Google is looking to grease the wheels for OpenClaw users who want to give their AI agents full access to their Workspace documents. Aside from OpenClaw, the Google Workspace CLI includes provisions for MCP (Model Context Protocol) integrations, making it easier for MCP-compatible apps (like the Claude Desktop app, VS Code, and the Gemini CLI) to connect to Google Workspace. OpenClaw and other agentic AI tools have already been able to integrate with Google Workplace apps, but they've had to jump through several hoops to do so, including juggling multiple APIs for Gmail, Google Drive, and other Google services. It's doable, but it's also a royal pain. The Google Workspace CLI makes integrations for OpenClaw and other agentic AI tools more streamlined, while also demonstrating how Google is prepping its core services for the post-OpenClaw era. It's worth noting that the Google Workspace CLI comes from Google's collection of "developer samples" for Google Workspace APIs, meaning its intended primarily for developers rather than everyday consumers. And while the CLI does appear to come from Google itself and not a third party, it's "not an officially supported Google product," the repo documentation warns. In other words, those looking to incorporate the Google Workspace CLI into their own products must do so at their own risk, at least for now. Still, the arrival of the Google Workspace CLI shows how Google is getting its core services "agent-ready" in the wake of OpenClaw's smashing success. OpenClaw is, of course, the personal AI assistant that went viral in late January. (Honestly, saying that OpenClaw "went viral" is hugely underselling its success, given that it changed the AI agent game practically overnight.) AI agents existed well before OpenClaw, but the tool -- an open-source side project from an Australian developer who was recently scooped up by OpenAI -- was the first of its kind to truly break into the mainstream. Among OpenClaw's key features is that its users can chat with it via common social messaging apps like WhatsApp, Telegram, and Discord. While OpenClaw still isn't quite ready for general use (as some of its users have learned the hard way), it points the way to an agentic AI future where everyday users are deploying teams of AI agents to manage their email, organize their documents, take notes in meetings, and even build new tools and functionality all on their own. Clearly, Google has seen the future as well, and the Google Workspace CLI is one of the ways in which it's getting itself ready.

Google opens the door to AI claws in new Workspace release

OpenClaw and other AI agents now have an official means to integrate with Google Workspace. Credit: Thomas Fuller/SOPA Images/LightRocket via Getty Images OpenClaw has taken the AI industry by storm over the past few months, inspiring a new AI term for personal AI agents -- claws. It's now so popular that even Google can't ignore it. If you're a Google Workspace user, Google has now released a command-line interface (CLI) that officially gives developers a way to integrate third-party AI agents like OpenClaw into the Workspace platform. This means that OpenClaw and other AI assistants can connect to a user's Google Workspace services such as Gmail and Google Drive. Google published the Google Workspace CLI on Github just days ago alongside specific documentation on how to integrate OpenClaw. The documentation also includes guidance on how to connect MCP (Model Context Protocol) compatible apps such as the Claude Desktop app and the Gemini CLI. As PCWorld noted, OpenClaw and similar claws could already connect to Google Workspace. However, this involved workarounds and the use of multiple APIs to integrate AI assistants into Google's services and platforms. While the Google CLI is an official Google release, the company shared that it's "not an officially supported Google product" and is more for developer use than the average Google user. Still, this is a notable move from Google. It's a first step in Google basically embracing claws and giving developers a legitimate way to integrate them into their Google Workspace account. OpenClaw went viral earlier this year and basically became the standard-bearer for agentic AI tools. Last month, OpenAI hired OpenClaw's founder Peter Steinberger, who joined the company with a goal "to build an agent that even my mum can use."

Google has quietly made Gmail, Docs, and other Workspace apps work better with OpenClaw

* Google has published "one CLI for all of Google Workspace" * There's even a set of instructions specifically for OpenClaw * It's "not an officially supported Google product..." for now Google has published a command-line interface (CLI) to GitHub which effectively allows AI agents to connect more easily with Google Workspace apps like Gmail, Google Drive and Docs/Sheets/Slides. The change clearly acknowledges the rise in personal AI assistants, like OpenClaw, which are able to take action autonomously on the user's behalf. Google even included a specific set of instructions for integrating with OpenClaw, which has gained traction on social media in recent weeks. Google opens Workspace up to OpenClaw and other AI agents The company describes the launch as "one CLI for all of Google Workspace - built for humans and AI agents." "Drive, Gmail, Calendar, and every Workspace API," Google added, promising "40+ agent skills included." Because the tool also supports MCP integrations (an open standard established by Claude-maker Anthropic), it means that other apps like Claude Desktop can also access Workspace's data and information. Although AI integrations were previously available via multiple APIs, the CLI definitely streamlines the process as we start to see a shift in how humans and AI agents interact with apps and data. There's one big catch, though. Google says this is "not an officially supported Google product," so it should be used at the risk of the individual who chooses to do so. Still, willingness to open up agentic AI access to its own apps is a big move for Google, indicative of a willingness to cooperate with third-party systems rather than keeping users locked closely into its own ecosystem. As for OpenClaw, it "will live in a foundation as an open source project" and will also get OpenAI support following OpenAI's acquisition of OpenClaw founder Peter Steinberger. Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews, and opinion in your feeds. Make sure to click the Follow button! And of course you can also follow TechRadar on TikTok for news, reviews, unboxings in video form, and get regular updates from us on WhatsApp too.

Google Workspace CLI brings Gmail, Docs, Sheets and more into a common interface for AI agents

What's old is new: the command line -- the original, clunky non-graphical interface for interacting with and controlling PCs, where the user just typed in raw commands in code -- has become one of the most important interfaces in agentic AI. That shift has been driven in part by the rise of coding-native tools such as Claude Code and Kilo CLI, which have helped establish a model where AI agents do not just answer questions in chat windows but execute real tasks through a shared, scriptable interface already familiar to developers -- and which can still be found on virtually all PCs. For developers, the appeal is practical: the CLI is inspectable, composable and easier to control than a patchwork of custom app integrations. Now, Google Workspace -- the umbrella term for Google's suite of enterprise cloud apps including Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin -- is moving into that pattern with a new CLI that lets them access these applications and the data within them directly, without relying on third-party connectors. The project, , describes itself as "one CLI for all of Google Workspace -- built for humans and AI agents," with structured JSON output and agent-oriented workflows included. In an X post yesterday, Google Cloud director Addy Osmani introduced the Google Workspace CLI as "built for humans and agents," adding that it covers "Google Drive, Gmail, Calendar, and every Workspace API." While not officially supported by Google, other posts cast the release as a broader turning point for automation and agent access to enterprise productivity software. Now, instead of having to set up third-party connectors like Zapier to access data and use AI agents to automate work across the Google Workspace suite of apps, enterprise developers (or indie devs and users, for that matter) can easily install the open source (Apache 2.0) Google Workspace CLI from Github and begin setting up automated agentic workflows directly in terminal, asking their AI model to sort email, respond, edit docs and files, and more. Why the CLI model is gaining traction For enterprise developers, the importance of the release is not that Google suddenly made Workspace programmable. Workspace APIs have long been available. What changes here is the interface. Instead of forcing teams to build and maintain separate wrappers around individual APIs, the CLI offers a unified command surface with structured output. Installation is straightforward -- -- and the repo says the package includes prebuilt binaries, with releases also available through GitHub. The repo also says reads Google's Discovery Service at runtime and dynamically builds its command surface, allowing new Workspace API methods to appear without waiting for a manually maintained static tool definition to catch up. For teams building agents or internal automation, that is a meaningful operational advantage. It reduces glue code, lowers maintenance overhead and makes Workspace easier to treat as a programmable runtime rather than a collection of separate SaaS applications. What developers and enterprises actually get The CLI is designed for both direct human use and agent-driven workflows. For developers working in the terminal, the README highlights features such as per-resource help, dry-run previews, schema inspection and auto-pagination. For agents, the value is clearer still: structured JSON output, reusable commands and built-in skills that let models interact with Workspace data and actions without a custom integration layer. That creates immediate utility for internal enterprise workflows. Teams can use the tool to list Drive files, create spreadsheets, inspect request and response schemas, send Chat messages and paginate through large result sets from the terminal. The README also says the repo ships more than 100 agent skills, including helpers and curated recipes for Gmail, Drive, Docs, Calendar and Sheets. That matters because Workspace remains one of the most common systems of record for day-to-day business work. Email, calendars, internal docs, spreadsheets and shared files are often where operational context lives. A CLI that exposes those surfaces through a common, agent-friendly interface makes it easier to build assistants that retrieve information, trigger actions and automate repetitive processes with less bespoke plumbing. The important caveat: visible, but not officially supported The social-media response has been enthusiastic, but enterprises should read the repo carefully before treating the project as a formal Google platform commitment. The README explicitly says: "This is not an officially supported Google product". It also says the project is under active development and warns users to expect breaking changes as it moves toward v1.0. That does not diminish the technical relevance of the release. It does, however, shape how enterprise teams should think about adoption. Today, this looks more like a promising developer tool with strong momentum than a production platform that large organizations should standardize on immediately. This is a cleaner interface, not a governance bypass The other key point is that the CLI does not bypass the underlying controls that govern Workspace access. The documentation says users still need a Google Cloud project for OAuth credentials and a Google account with Workspace access. It also outlines multiple authentication patterns for local development, CI and service accounts, along with instructions for enabling APIs and handling setup issues. For enterprises, that is the right way to interpret the tool. It is not magic access to Gmail, Docs or Sheets. It is a more usable abstraction over the same permissions, scopes and admin controls companies already manage. Not a rejection of MCP, but a broader agent interface strategy Some of the early commentary around the tool frames it as a cleaner alternative to Model Context Protocol (MCP)-heavy setups, arguing that CLI-driven execution can avoid wasting context window on large tool definitions. There is some logic to that argument, especially for agent systems that can call shell commands directly and parse JSON responses. But the repo itself presents a more nuanced picture. It includes a Gemini CLI extension that gives Gemini agents access to commands and Workspace agent skills after terminal authentication. It also includes an MCP server mode through , exposing Workspace APIs as structured tools for MCP-compatible clients including Claude Desktop, Gemini CLI and VS Code. The strategic takeaway is not that Google Workspace is choosing CLI instead of MCP. It is that the CLI is emerging as the base interface, with MCP available where it makes sense. What enterprises should do now The right near-term move for enterprises is not broad rollout. It is targeted evaluation. Developer productivity, platform engineering and IT automation teams should test the tool in a sandboxed Workspace environment and identify a narrow set of high-friction use cases where a CLI-first approach could reduce integration work. File discovery, spreadsheet updates, document generation, calendar operations and internal reporting are natural starting points. Security and identity teams should review authentication patterns early and determine how tightly permissions, scopes and service-account usage can be constrained and monitored. AI platform teams, meanwhile, should compare direct CLI execution against MCP-based approaches in real workflows, focusing on reliability, prompt overhead and operational simplicity. The broader trend is clear. As agentic software matures, the command line is becoming a common control plane for both developers and AI systems. Google Workspace's new CLI does not change enterprise automation overnight. But it does make one of the most widely used productivity stacks easier to access through the interface that agent builders increasingly prefer.

Google apps just got a lot easier to use with OpenClaw

When not writing, Dave enjoys spending time with his family, running, playing the guitar, camping, and serving in his community. His favorite place is the Blue Ridge Mountains, and one day he hopes to retire there (hopefully his fear of heights will have retired by then, too!). Summary Google released Workspace CLI on GitHub to give AI agents easier access to Docs, Drive, Gmail, and more. The tool offers 100+ Agent Skills to simplify agent actions across Workspace apps. Although the tool was published by Google, the company cautions it's not an officially supported product, so use it at your own risk. Google has published a new command-line interface for Google Workspace apps. Google Workspace CLI hit GitHub on March 2 and has already racked up nearly 14,000 stars. The tool is designed to make it easier for AI agents like OpenClaw to interface with Google apps like Docs, Drive, and Gmail. What you need to know about Google Workspace CLI AI integrations galore Google describes the release as "built for humans and AI agents," but while humans can use the tools, it's pretty clear the intended audience is AI. There are explicit instructions for integrating with OpenClaw, the viral and highly useful AI agent, but the tool also supports MCP (Model Context Protocol) integrations. MCP helps standardize how AI agents interact with apps, and means that the Google Workspace CLI supports other AI agents beyond OpenClaw, such as Claude Desktop. Now, yes, it's true that OpenClaw has already been able to interact with Google Workspace. However, up until now, this has been done through complicated API calls. This CLI interface will drastically simplify how OpenClaw and other agents interact with Google Workspace. The tool includes over 100 Agent Skills, along with curated recipes for Google apps like Gmail, Drive, and Docs. Although it was published by Google, the company does caution that the tool is "not an officially supported Google product." This basically means you use it at your own risk. While the risk is probably pretty small, definitely keep in mind that if something goes wrong, you're likely on your own. What can the Google Workspace CLI tool do? Simplified commands for a ton of tasks Google's CLI tool includes over 100 Agent Skills that let tools like OpenClaw easily tap into Google apps. Some highlights include: gws-drive-upload: Upload a file with automatic metadata to Google Drive. gws-gmail-send: Send an email in Gmail. gws-calendar-insert: Create a new calendar event. recipe-label-and-archive-emails: Apply Gmail labels to emails and then archive them. recipe-block-focus-time: Create recurring blocks for focused work on Google Calendar. As mentioned above, while you can use these commands directly to interact with your Google apps, they're really meant to make it easier for agents like OpenClaw. So you'd tell OpenClaw to perform a task, and it would use these commands in the background to get things done. Google says there are skills to cover every supported API. Supported apps include Google Drive, Sheets, Docs, Gmail, Calendar, Tasks, Classroom, Keep Notes, and Meet. A sign of the times This release is kind of a big deal -- it underscores how seriously companies are taking agentic AI. It's not a small thing for a major company like Google to build a tool specifically to make its apps easier to access with agents. Taken with other recent announcements, such as the launch of Microsoft's Copilot Tasks agent and OpenClaw's creator joining OpenAI, it's easy to see the coming shift towards more powerful (and useful) agentic AI.