googleworkspace / cli

One CLI for all of Google Workspace — built for humans and AI agents. Drive, Gmail, Calendar, and every Workspace API. Zero boilerplate. Structured JSON output. 40+ agent skills included.

[!NOTE] This is not an officially supported Google product.

⬇️ Download the latest release for your OS (opens in a new tab)

gws doesn’t ship a static list of commands. It reads Google’s own Discovery Service (opens in a new tab) at runtime and builds its entire command surface dynamically. When Google Workspace adds an API endpoint or method, gws picks it up automatically.

[!IMPORTANT] This project is under active development. Expect breaking changes as we march toward v1.0.

Contents

• Prerequisites
• Installation
• Quick Start
• Why gws?
• Authentication
• AI Agent Skills
• Advanced Usage
• Environment Variables
• Exit Codes
• Architecture
• Troubleshooting
• Development

Prerequisites

• Node.js 18+ — for npm install (or download a pre-built binary from GitHub Releases (opens in a new tab))
• A Google Cloud project — required for OAuth credentials. You can create one via the Google Cloud Console (opens in a new tab) or with the gcloud CLI (opens in a new tab) or with the gws auth setup command.
• A Google account with access to Google Workspace

Installation

The recommended way to install gws is to download the pre-built binary for your OS and architecture from the GitHub Releases (opens in a new tab) page. Extract the archive and place the gws binary in your $PATH.

For convenience, you can also use npm to automate downloading the appropriate binary from GitHub Releases:

npm install -g @googleworkspace/cli

Or build from source:

cargo install --git https://github.com/googleworkspace/cli --locked

A Nix flake is also available at github:googleworkspace/cli

nix run github:googleworkspace/cli

On macOS and Linux, you can also install via Homebrew (opens in a new tab):

brew install googleworkspace-cli

Quick Start

gws auth setup     # walks you through Google Cloud project config
gws auth login     # subsequent OAuth login
gws drive files list --params '{"pageSize": 5}'

Why gws?

For humans — stop writing curl calls against REST docs. gws gives you --help on every resource, --dry-run to preview requests, and auto‑pagination.

For AI agents — every response is structured JSON. Pair it with the included agent skills and your LLM can manage Workspace without custom tooling.

# List the 10 most recent files
gws drive files list --params '{"pageSize": 10}'

# Create a spreadsheet
gws sheets spreadsheets create --json '{"properties": {"title": "Q1 Budget"}}'

# Send a Chat message
gws chat spaces messages create \
  --params '{"parent": "spaces/xyz"}' \
  --json '{"text": "Deploy complete."}' \
  --dry-run

# Introspect any method's request/response schema
gws schema drive.files.list

# Stream paginated results as NDJSON
gws drive files list --params '{"pageSize": 100}' --page-all | jq -r '.files[].name'

Authentication

The CLI supports multiple auth workflows so it works on your laptop, in CI, and on a server.

Which setup should I use?

Interactive (local desktop)

Credentials are encrypted at rest (AES-256-GCM) with the key stored in your OS keyring (or ~/.config/gws/.encryption_key when GOOGLE_WORKSPACE_CLI_KEYRING_BACKEND=file).

gws auth setup       # one-time: creates a Cloud project, enables APIs, logs you in
gws auth login       # subsequent scope selection and login

gws auth setup requires the gcloud CLI (opens in a new tab). If you don’t have gcloud, use the manual setup below instead.

[!WARNING] Scope limits in testing mode: If your OAuth app is unverified (testing mode), Google limits consent to ~25 scopes. The recommended scope preset includes 85+ scopes and will fail for unverified apps (especially for @gmail.com accounts). Choose individual services instead to filter the scope picker:

bashCopy

gws auth login -s drive,gmail,sheets

Manual OAuth setup (Google Cloud Console)

Use this when gws auth setup cannot automate project/client creation, or when you want explicit control.

1. Open Google Cloud Console in the target project:
   • OAuth consent screen: https://console.cloud.google.com/apis/credentials/consent?project=<PROJECT_ID>
   • Credentials: https://console.cloud.google.com/apis/credentials?project=<PROJECT_ID>
2. Configure OAuth branding/audience if prompted:
   • App type: External (testing mode is fine)
3. Add your account under Test users
4. Create an OAuth client:
   • Type: Desktop app
5. Download the client JSON and save it to:
   • ~/.config/gws/client_secret.json

[!IMPORTANT] You must add yourself as a test user. In the OAuth consent screen, click Test users → Add users and enter your Google account email. Without this, login will fail with a generic “Access blocked” error.

Then run:

gws auth login

Browser-assisted auth (human or agent)

You can complete OAuth either manually or with browser automation.

• Human flow: run gws auth login, open the printed URL, approve scopes.
• Agent-assisted flow: the agent opens the URL, selects account, handles consent prompts, and returns control once the localhost callback succeeds.

If consent shows “Google hasn’t verified this app” (testing mode), click Continue. If scope checkboxes appear, select required scopes (or Select all) before continuing.

Headless / CI (export flow)

1. Complete interactive auth on a machine with a browser.
2. Export credentials:

   bashCopy

   gws auth export --unmasked > credentials.json

3. On the headless machine:

   bashCopy

   export GOOGLE_WORKSPACE_CLI_CREDENTIALS_FILE=/path/to/credentials.json
   gws drive files list   # just works

Service Account (server-to-server)

Point to your key file; no login needed.

export GOOGLE_WORKSPACE_CLI_CREDENTIALS_FILE=/path/to/service-account.json
gws drive files list

Pre-obtained Access Token

Useful when another tool (e.g. gcloud) already mints tokens for your environment.

export GOOGLE_WORKSPACE_CLI_TOKEN=$(gcloud auth print-access-token)

Precedence

Environment variables can also live in a .env file.

AI Agent Skills

The repo ships 100+ Agent Skills (SKILL.md files) — one for every supported API, plus higher-level helpers for common workflows and 50 curated recipes for Gmail, Drive, Docs, Calendar, and Sheets. See the full Skills Index (opens in a new tab) for the complete list.

# Install all skills at once
npx skills add https://github.com/googleworkspace/cli

# Or pick only what you need
npx skills add https://github.com/googleworkspace/cli/tree/main/skills/gws-drive
npx skills add https://github.com/googleworkspace/cli/tree/main/skills/gws-gmail

# Symlink all skills (stays in sync with repo)
ln -s $(pwd)/skills/gws-* ~/.openclaw/skills/

# Or copy specific skills
cp -r skills/gws-drive skills/gws-gmail ~/.openclaw/skills/

The gws-shared skill includes an install block so OpenClaw auto-installs the CLI via npm if gws isn’t on PATH.

Gemini CLI Extension

1. Authenticate the CLI first:

   bashCopy

   gws auth setup

2. Install the extension into the Gemini CLI:

   bashCopy

   gemini extensions install https://github.com/googleworkspace/cli

Installing this extension gives your Gemini CLI agent direct access to all gws commands and Google Workspace agent skills. Because gws handles its own authentication securely, you simply need to authenticate your terminal once prior to using the agent, and the extension will automatically inherit your credentials.

Advanced Usage

Multipart Uploads

gws drive files create --json '{"name": "report.pdf"}' --upload ./report.pdf

Pagination

Google Sheets — Shell Escaping

Sheets ranges use ! which bash interprets as history expansion. Always wrap values in single quotes:

# Read cells A1:C10 from "Sheet1"
gws sheets spreadsheets values get \
  --params '{"spreadsheetId": "SPREADSHEET_ID", "range": "Sheet1!A1:C10"}'

# Append rows
gws sheets spreadsheets values append \
  --params '{"spreadsheetId": "ID", "range": "Sheet1!A1", "valueInputOption": "USER_ENTERED"}' \
  --json '{"values": [["Name", "Score"], ["Alice", 95]]}'

Helper Commands

Some services ship hand-crafted helper commands alongside the auto-generated Discovery surface. Helper commands are prefixed with + so they are visually distinct and never collide with Discovery-generated method names.

Time-aware helpers (+agenda, +standup-report, +weekly-digest, +meeting-prep) automatically use your Google account timezone (fetched from Calendar Settings API and cached for 24 hours). Override with --timezone/--tz on +agenda, or set the --timezone flag for explicit control.

Run gws <service> --help to see both Discovery methods and helper commands together.

gws gmail --help      # shows +send, +reply, +reply-all, +forward, +triage, +watch …
gws calendar --help   # shows +insert, +agenda …
gws drive --help      # shows +upload …

Full helper reference:

Examples:

# Send an email
gws gmail +send --to alice@example.com --subject "Hello" --body "Hi there"

# Reply to a message
gws gmail +reply --message-id MESSAGE_ID --body "Thanks!"

# Append a row to a spreadsheet
gws sheets +append --spreadsheet SPREADSHEET_ID --values "Alice,95"

# Show today's calendar agenda
gws calendar +agenda

# Upload a file to Drive
gws drive +upload ./report.pdf --name "Q1 Report"

# Morning standup summary
gws workflow +standup-report

# Show today's agenda in a specific timezone
gws calendar +agenda --today --timezone America/New_York

Model Armor (Response Sanitization)

Integrate Google Cloud Model Armor (opens in a new tab) to scan API responses for prompt injection before they reach your agent.

gws gmail users messages get --params '...' \
  --sanitize "projects/P/locations/L/templates/T"

Environment Variables

All variables are optional. See .env.example (opens in a new tab) for a copy-paste template.

Environment variables can also be set in a .env file (loaded via dotenvy (opens in a new tab)).

Exit Codes

gws uses structured exit codes so scripts can branch on the failure type without parsing error output.

gws drive files list --params '{"fileId": "bad"}'
echo $?   # 1 — API error

gws unknown-service files list
echo $?   # 3 — validation error (unknown service)

Architecture

gws uses a two-phase parsing strategy:

1. Read argv[1] to identify the service (e.g. drive)
2. Fetch the service’s Discovery Document (cached 24 h)
3. Build a clap::Command tree from the document’s resources and methods
4. Re-parse the remaining arguments
5. Authenticate, build the HTTP request, execute

All output — success, errors, download metadata — is structured JSON.

Troubleshooting

“Access blocked” or 403 during login

Your OAuth app is in testing mode and your account is not listed as a test user.

Fix: Open the OAuth consent screen (opens in a new tab) in your GCP project → Test users → Add users → enter your Google account email. Then retry gws auth login.

“Google hasn’t verified this app”

Expected when your app is in testing mode. Click Advanced → Go to <app name> (unsafe) to proceed. This is safe for personal use; verification is only required to publish the app to other users.

Too many scopes / consent screen error

Unverified (testing mode) apps are limited to ~25 OAuth scopes. The recommended scope preset includes many scopes and will exceed this limit.

Fix: Select only the scopes you need:

gws auth login --scopes drive,gmail,calendar

gcloud CLI not found

gws auth setup requires the gcloud CLI to automate project creation. You have three options:

1. Install gcloud (opens in a new tab) and use gcloud directly.
2. Re-run gws auth setup which wraps gcloud calls.
3. Skip gcloud entirely — set up OAuth credentials manually in the Cloud Console

redirect_uri_mismatch

The OAuth client was not created as a Desktop app type. In the Credentials (opens in a new tab) page, delete the existing client, create a new one with type Desktop app, and download the new JSON.

API not enabled — accessNotConfigured

If a required Google API is not enabled for your GCP project, you will see a 403 error with reason accessNotConfigured:

{
  "error": {
    "code": 403,
    "message": "Gmail API has not been used in project 549352339482 ...",
    "reason": "accessNotConfigured",
    "enable_url": "https://console.developers.google.com/apis/api/gmail.googleapis.com/overview?project=549352339482"
  }
}

gws also prints an actionable hint to stderr:

💡 API not enabled for your GCP project.
   Enable it at: https://console.developers.google.com/apis/api/gmail.googleapis.com/overview?project=549352339482
   After enabling, wait a few seconds and retry your command.

Steps to fix:

1. Click the enable_url link (or copy it from the enable_url JSON field).
2. In the GCP Console, click Enable.
3. Wait ~10 seconds, then retry your gws command.

[!TIP] You can also run gws auth setup which walks you through enabling all required APIs for your project automatically.

Development

cargo build                       # dev build
cargo clippy -- -D warnings       # lint
cargo test                        # unit tests
./scripts/coverage.sh             # HTML coverage report → target/llvm-cov/html/

License

Apache-2.0

Disclaimer

[!CAUTION] This is not an officially supported Google product.