​
1. Introduction

This guide explains how to integrate Chronologue with Google Calendar using the official Google Calendar API. By exporting memory traces as .ics files and syncing them via OAuth 2.0, users can schedule agent-generated events directly to their calendar.

Chronologue supports end-to-end export of calendar_event memory traces into .ics format and subsequent push to the authenticated user’s Google Calendar.

​
2. Prerequisites

Before beginning integration, ensure you have:

  • A Google Account
  • Python 3.8+
  • google-auth, google-api-python-client, and ics installed
  • A Chronologue memory trace with scheduled_for, duration_minutes, and title

​
3. Google Cloud Setup

​
Step 1: Create Google Cloud Project

  1. Visit: https://console.cloud.google.com/
  2. Create a new project
  3. Navigate to APIs & Services → Library
  4. Enable Google Calendar API

​
Step 2: Configure OAuth 2.0 Credentials

  1. Go to APIs & Services → Credentials
  2. Click + CREATE CREDENTIALS → OAuth client ID
  3. If prompted, configure the consent screen:
    • Type: External
    • App Name: Chronologue Calendar
    • Add developer contact
  4. Application Type: Desktop App
  5. Name it: Chronologue Local Calendar Access
  6. Click Create and download the JSON credentials

​
4. Project Configuration

  1. Place your downloaded file in your project as:
    calendar/credentials.json

  2. Add to .gitignore:

calendar/credentials.json  
calendar/token.json
  1. Ensure you have the following packages installed:

pip install google-api-python-client google-auth google-auth-oauthlib ics

​
5. Run the Sync Script

From the root of your Chronologue repo:

python modules/calendar_io/sync_google_json.py

On first run:

  • A browser window will open for OAuth authentication
  • A token.json file will be saved for reuse

​
6. Sync Script Overview

​
authenticate_google()

  • Authenticates user via OAuth
  • Loads token if available, otherwise runs InstalledAppFlow
  • Saves new token for future runs

​
convert_json_folder_to_ics(input_dir, output_dir)

  • Iterates over memory traces (*.json)
  • Parses title, scheduled_for, duration_minutes
  • Generates .ics VEVENT blocks

Example:

input_dir = Path("data/conversation/raw")  
output_dir = Path("data/conversation/processed")  
convert_json_folder_to_ics(input_dir, output_dir)

​
parse_ics_and_sync(ics_path, service)

  • Reads .ics files
  • Constructs Google Calendar event payloads
  • Pushes events via:

service.events().insert(calendarId=“primary”, body=payload).execute()

​
7. Event Format Mapping

Memory Trace FieldCalendar Field
titlesummary
scheduled_forstart.dateTime
duration_minutesend.dateTime
content + chat_urldescription
location (optional)location
uid or task_idid (custom UID)

​
8. Example Memory Trace

{
  "type": "calendar_event",
  "title": "Deep Work Block",
  "scheduled_for": "2025-05-12T09:00:00Z",
  "duration_minutes": 120,
  "task_id": "deepwork-20250512",
  "content": "Work on CUDA kernel development and testing.",
  "chat_url": "https://chat.openai.com/share/example-link"
}

This becomes:

BEGIN:VEVENT  
UID:deepwork-20250512  
DTSTAMP:20250511T220000Z  
DTSTART:20250512T090000Z  
DTEND:20250512T110000Z  
SUMMARY:Deep Work Block  
DESCRIPTION:Work on CUDA kernel development.  
Chat log: https://chat.openai.com/share/example-link  
STATUS:CONFIRMED  
END:VEVENT

​
9. Security Best Practices

  • Never commit credentials.json or token.json
  • Use .env or secrets manager in production
  • Rotate OAuth credentials periodically
  • Limit scope of calendar permissions to only what’s required
  • Authentication and Headers
  • Calendar Event Schema
  • MemPort Context Export

Chronologue’s Google Calendar integration bridges structured memory planning with real-world scheduling. With OAuth authentication, .ics generation, and sync scripts, you can schedule agent-generated tasks across your time horizon—automatically and transparently.