← Back to Blog

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.

☁️
Step 1
List Files
List the 20 most recently modified files and folders with name, type, size, and last modified date.
Step 2
Identify Unorganised Files
Group loose root files by type and flag them as candidates for folder organisation.
Step 3
Report
Produce a Drive summary with file counts, type breakdown, unorganised files, and a recommended folder structure.

The Agent YAML

Create a file called agent.yaml inside a cloud-drives/ directory:

name: Drive Manager
description: Read, write, and organize files in Google Drive
instructions: |
  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.
steps:
  - name: List Files
    content: |
      List the 20 most recently modified files and folders in the root of Google Drive.
      Note each file's name, type, size, and last modified date.
  - name: Identify Unorganized Files
    content: |
      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).
  - name: Report
    content: |
      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
connectors:
  - connection_name: My Google Drive
    connection_type: google-drive

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",
      "clientId": "YOUR_GOOGLE_CLIENT_ID",
      "clientSecret": "YOUR_GOOGLE_CLIENT_SECRET",
      "refreshToken": "YOUR_GOOGLE_REFRESH_TOKEN"
    }
  ]
}

Create OAuth 2.0 credentials at console.cloud.google.com. Enable the Google Drive API, then generate a refresh token using your preferred OAuth flow.

Download OE Runtime

OE Runtime — Direct Downloads

Run the Agent

Windows

# Run the agent
oe-runtime-win.exe cloud-drives/agent.yaml --config cloud-drives/oe-config.json

macOS

# Make executable (first time only)
chmod +x oe-runtime-macos

# Run the agent
oe-runtime-macos cloud-drives/agent.yaml --config cloud-drives/oe-config.json

Linux

# Make executable (first time only)
chmod +x oe-runtime-linux

# Run the agent
oe-runtime-linux cloud-drives/agent.yaml --config cloud-drives/oe-config.json

macOS Gatekeeper: On first run, macOS may block the binary. Go to System Settings → Privacy & Security → click "Allow Anyway" next to oe-runtime-macos.

Running as an API Server

Add --serve to start OE Runtime as an HTTP server on port 3333:

oe-runtime-win.exe --serve --config cloud-drives/oe-config.json

Then send a request:

curl -X POST http://localhost:3333/run \
  -H "Content-Type: application/json" \
  -d '{"yaml": "cloud-drives/agent.yaml", "params": {}}'

Or import the Postman collection (download above) to test all endpoints visually.

Use Cases

Build your own agents with OE Runtime

Download OE Runtime and run any AI agent locally or as a server — no cloud required.

Get OE Runtime →