cli
One CLI for Google Workspace built for humans and AI agents.
Query Drive, Gmail, Calendar, and Sheets with zero boilerplate and structured JSON output.
This is a command-line tool that reads Google's Discovery Service at runtime to dynamically build a command surface for all Workspace APIs. It suits developers and executive assistants looking to script workflows or feed workspace data to AI agents.
What it is
It executes API calls across Google Workspace services without requiring hardcoded static command lists. Every response outputs structured JSON, and it includes over 40 agent skills and a Gemini CLI extension for automated task execution.
Who it's for
It suits technical professionals, sysadmins, and power users comfortable with command-line tools and OAuth setup. It does not suit non-technical users who expect graphical interfaces or simple wizard-driven desktop apps.
Key features
Dynamic Command Surface
Reads Google's Discovery Service at runtime so newly added API endpoints are picked up automatically.
Structured JSON Output
Returns clean JSON for every response to integrate directly with shell scripts and AI agents.
Built-In AI Agent Skills
Includes over 100 agent skills and a Gemini CLI extension for direct workspace control by LLMs.
Multiple Auth Workflows
Supports interactive setup, manual OAuth, service accounts, and pre-obtained access tokens for CI environments.
Up and running in 3 steps
Our honest verdict
What's great
- Eliminates writing raw curl calls against Google REST documentation.
- Streams paginated results as NDJSON for easy pipeline filtering with jq.
- Provides dry-run preview capabilities for destructive API actions.
- Includes a Nix flake and pre-built binaries across multiple platforms.
Where it falls short
- Requires manual Google Cloud project configuration and OAuth consent screen setup.
- Unverified OAuth apps in testing mode hit strict scope limits for gmail.com accounts.
- Under active development with breaking changes expected before v1.0.
Pricing & license
The tool is free to use under its open-source license. The only associated cost is your time configuring a Google Cloud project and any potential Google Cloud API quota usage.
Open remote AI-training roles
873 open remote AI-training roles, updated November 15, 2026; most pay $20–$170 an hour. Zekai lists them free; the application goes to the employer’s platform.
Alternatives
Use it, or have us set it up
FAQ
Why does gws auth setup require gcloud?
It uses the gcloud CLI to automate the creation of your Google Cloud project and enable the necessary APIs.
How do I handle OAuth scope limits in testing mode?
You must select individual services using flags like -s drive,gmail,sheets rather than requesting all 85+ recommended scopes at once.
Can I use this in headless CI environments?
Yes, by exporting credentials from an authorized machine and setting the GOOGLE_WORKSPACE_CLI_CREDENTIALS_FILE environment variable.
