Top AI Product

We track trending AI tools across Product Hunt, Hacker News, GitHub, and more  — then write honest, opinionated takes on the ones that actually matter. No press releases, no sponsored content. Just real picks, published daily.  Subscribe to stay ahead without drowning in hype.


Google Workspace CLI: Google Finally Built the One Tool Every Developer Wanted

So Google just dropped an official CLI for the entire Workspace suite, and honestly, it’s about time. The [Google Workspace CLI](https://github.com/googleworkspace/cli) — or `gws` as you’ll be typing a lot — gives you command-line access to Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and basically every Workspace API that exists. It shot straight to [#1 on Hacker News](https://news.ycombinator.com/item?id=47255881) with 571 points, and the discussion thread is worth reading if you care about where AI-agent tooling is headed.

What makes this genuinely interesting isn’t just “another CLI wrapper.” The tool is written in Rust, distributed via npm (`npm i -g @googleworkspace/cli`), and here’s the clever part — it doesn’t ship a static list of commands. Instead, it reads Google’s Discovery Service at runtime and builds its entire command surface dynamically. When Google adds a new API endpoint, `gws` picks it up automatically. No update needed on your end.

But the real headline is the AI agent story. The CLI ships with 40+ agent skills and supports MCP (Model Context Protocol), meaning you can point Claude Desktop or Gemini CLI at it and let your AI assistant directly operate on your Google Workspace. Run `gws mcp` and it spins up a stdio-based MCP server exposing structured tools. As [Guillermo Rauch put it on X](https://x.com/rauchg/status/2029356560494018956), “2026 is the year of Skills & CLIs” — and this release really drives that point home.

There’s also a neat git-like pull/push workflow for editing Sheets, Docs, and Slides. You `pull` a Google Sheet and it converts into a local folder with a `.tsv` file and a `formula.json`. Edit those locally (or let an agent edit them), then `push` the changes back. It’s the kind of workflow that makes you wonder why it didn’t exist five years ago.

The project is still pre-v1.0 so expect some rough edges and breaking changes. But this is Google officially embracing the agent ecosystem — not a side project from some 20% time experiment, but a proper tool with MCP support, structured output, and a clear vision for how AI agents should interact with enterprise software. If you work with Google Workspace APIs in any capacity, this one’s worth installing today.


Discover more from Top AI Product

Subscribe to get the latest posts sent to your email.



Leave a comment