How to Run an AI Cloud Drive Agent with OE Runtime

List, organise, and analyse your Google Drive files automatically. OE Runtime connects directly to Drive, inventories your files, identifies what is unorganised, and recommends a folder structure — all from a single YAML file.

What You Need

• Node.js 18+ installed, or the OE Runtime binary from openenthrium.com/runtime
• An API key from OpenAI, Anthropic, or any supported LLM provider
• Google Drive OAuth credentials — create a project at Google Cloud Console and enable the Drive API
• A text editor — nothing else

Create the Project Folder

Create a folder called cloud-drives/ and add these two files:

The Skill Files

Create SKILL.md inside a cloud-drives/ directory. This is the portable skill — it follows the agentskills.io format and runs unchanged on Claude, Cursor, Windsurf, or OE Runtime:

---
name: cloud-drives
description: Read, write, and organize files in Google Drive
license: Apache-2.0
metadata:
  author: Open Enthrium
  version: "1.0"
---

You are a file organization agent with access to Google Drive.
Help find, list, organize, and summarize files and folders.
Always confirm before making any write or delete operations.
Complete all steps fully before writing your report.

## Step 1: List Files
Call the Google Drive connector:
GET /files with params:
{
  "orderBy": "modifiedTime desc",
  "pageSize": "20",
  "fields": "files(id,name,mimeType,size,modifiedTime,parents)"
}
Note each file's name, type, size, and last modified date.

## Step 2: Identify Unorganized Files
From the listed files, identify any files sitting loose in the root that could be moved into folders.
Group them by type (documents, spreadsheets, images, PDFs, other).

## Step 3: Report
Produce a Drive summary:
- Total files and folders found
- Breakdown by file type
- List of files that are unorganized in root
- Recommended folder structure to organize them

Create agent.yaml in the same directory to wire the skill to your connector:

name: Drive Manager
description: Read, write, and organize files in Google Drive
connectors:
  - connection_name: My Google Drive
    connection_type: google-drive
skills:
  - path: ./
    trigger_type: auto

The Config File

Create oe-config.json in the same directory:

{
  "llm": {
    "provider": "openai",
    "model": "gpt-4o",
    "apiKey": "YOUR_OPENAI_API_KEY"
  },
  "server": {
    "enabled": false,
    "port": 3333,
    "apiKey": "your-secret-api-key"
  },
  "connectors": [
    {
      "connection_name": "My Google Drive",
      "connection_type": "google-drive",
      "bearerToken": "YOUR_GOOGLE_ACCESS_TOKEN",
      "baseUrl": "https://www.googleapis.com/drive/v3"
    }
  ]
}

How to Get Your Bearer Token

1. Go to Google Cloud Console → create a new project or select an existing one
2. Go to APIs & Services → Library → search for Google Drive API → click Enable
3. Go to APIs & Services → Credentials → Create Credentials → OAuth 2.0 Client ID
4. Set Application type to Desktop app → click Create → note your Client ID and Client Secret
5. Open the Google OAuth 2.0 Playground
6. Click the ⚙️ gear icon (top right) → enable Use your own OAuth credentials → paste your Client ID and Client Secret
7. In Step 1, find Drive API v3 → select scope https://www.googleapis.com/auth/drive → click Authorize APIs
8. Sign in with your Google account and allow access
9. In Step 2, click Exchange authorization code for tokens
10. Copy the Access Token and paste it as bearerToken in your oe-config.json

Download OE Runtime

Run the Agent

From the parent folder containing your skill directory:

1 npx recommended

npx -y @openenthrium/oe-runtime@latest ./cloud-drives

2 Windows

oe-runtime-win.exe ./cloud-drives

3 macOS

chmod +x oe-runtime-macos
./oe-runtime-macos ./cloud-drives

First run blocked? System Settings → Privacy & Security → Allow Anyway.

4 Linux

chmod +x oe-runtime-linux
./oe-runtime-linux ./cloud-drives

5 API Server integration

Add a "server" block to oe-config.json, then start with --serve:

{
  "llm": { ... },
  "server": { "enabled": true, "port": 3333, "apiKey": "your-secret-key" },
  "connectors": [ ... ]
}

npx -y @openenthrium/oe-runtime@latest --serve --config oe-config.json

Run with inline YAML:

curl -X POST http://localhost:3333/run \
  -H "Content-Type: application/json" \
  -H "X-API-Key: your-secret-key" \
  -d '{"yaml": "...", "params": {}}'

Or run from a file on the server:

curl -X POST http://localhost:3333/run-file \
  -H "Content-Type: application/json" \
  -H "X-API-Key: your-secret-key" \
  -d '{"file": "/path/to/agent.yaml", "params": {}}'

Use Cases

• Drive cleanup automation — Automatically inventory your Google Drive root and identify files that are sitting loose without any folder structure. The agent groups them by type and recommends a logical folder hierarchy so you can organise years of accumulated files in minutes.
• Document discovery — Search across hundreds of Drive files to locate a specific document, contract, or report without manually scrolling through folders. The agent reads file names, types, and modification dates to surface exactly what you need.
• Team Drive auditing — List and analyse the contents of a shared team Drive to understand what files exist, how large they are, and when they were last updated. Useful for IT teams managing storage quotas or preparing for data migrations.
• Knowledge base maintenance — Regularly audit your company knowledge base in Drive to identify outdated documents, duplicate files, and missing categories. The agent surfaces files that have not been modified in over 90 days as candidates for archiving or deletion.
• Onboarding document delivery — Locate and summarise the most relevant onboarding guides, policies, and wikis for new team members from a shared Drive. The agent reads the content and delivers a personalised summary without the new hire needing Drive access initially.
• Contract management — Scan a contracts folder to list all agreements, their file dates, and sizes so you can track what is on file. Combine with the OCR agent to extract expiry dates and key clauses from each document automatically.
• Automated backup reporting — Run the agent on a schedule to verify that expected backup files are present in a designated Drive folder. If files are missing or older than expected, the agent flags them in a report for review.
• Storage cost management — Identify the largest files consuming Drive storage and flag them for review or compression. For teams on paid Google Workspace plans, regular storage audits can significantly reduce monthly costs.