Data export, retention, and GDPR compliance for Granola. Use when managing data exports, configuring retention policies, or ensuring regulatory compliance. Trigger with phrases like "granola export", "granola data", "granola GDPR", "granola retention", "granola compliance".
npxskills add jeremylongshore/claude-code-plugins-plus-skills--skill granola-data-handlingLoading…
Manage data lifecycle for Granola meeting data: export, retention policies, GDPR/CCPA compliance, and long-term archival. Covers individual data rights, organizational policies, and automated archival workflows.
| Data Type | What It Contains | Sensitivity | Storage |
|---|---|---|---|
| Meeting Notes | Your typed notes + AI-enhanced output | Medium | Granola cloud + local cache |
| Transcripts | Full text transcription of audio | High (verbatim speech) | Granola cloud + local cache |
| Audio | Raw meeting audio | Critical | Deleted after transcription (not stored) |
| Attendee Info | Names, emails from calendar events | PII |
| Granola cloud (People & Companies) |
| Calendar Metadata | Event titles, times, attendee lists | Low-Medium | Synced from Google/Outlook |
Key fact: Granola does not store raw audio after transcription. This is a significant privacy advantage — there is no audio file to leak, export, or subpoena.
Individual note export:
Important limitation: Granola does not currently support bulk export, PDF export, or structured file download (JSON/CSV). The available options are:
Workaround for bulk access — local cache:
#!/usr/bin/env python3
"""Export Granola meetings from local cache to Markdown files."""
import json
from pathlib import Path
from datetime import datetime
CACHE_PATH = Path.home() / "Library/Application Support/Granola/cache-v3.json"
OUTPUT_DIR = Path.home() / "Desktop/granola-export"
OUTPUT_DIR.mkdir(exist_ok=True)
def export_from_cache():
raw = json.loads(CACHE_PATH.read_text())
state = json.loads(raw) if isinstance(raw, str) else raw
data = state.get("state", state)
docs = data.get("documents", {})
exported = 0
for doc_id, doc in docs.items():
title = doc.get("title", "Untitled").replace("/", "-")
created = doc.get("created_at", "unknown")[:10]
content = doc.get("last_viewed_panel", {})
# Extract text from ProseMirror content (simplified)
text_parts = []
if isinstance(content, dict):
for node in content.get("content", []):
if node.get("type") == "paragraph":
for child in node.get("content", []):
text_parts.append(child.get("text", ""))
elif node.get("type") == "heading":
level = node.get("attrs", {}).get("level", 1)
prefix = "#" * level
for child in node.get("content", []):
text_parts.append(f"\n{prefix} {child.get('text', '')}\n")
filename = f"{created}_{title[:60]}.md"
filepath = OUTPUT_DIR / filename
filepath.write_text(f"# {title}\n\nDate: {created}\n\n{''.join(text_parts)}")
exported += 1
print(f"Exported {exported} meetings to {OUTPUT_DIR}")
export_from_cache()
Enterprise API export:
# List all accessible notes (Enterprise plan required)
curl -s "https://api.granola.ai/v0/notes" \
-H "Authorization: Bearer $GRANOLA_API_KEY" \
-H "Content-Type: application/json" | python3 -c "
import json, sys
notes = json.load(sys.stdin).get('notes', [])
for note in notes[:10]:
print(f\"{note.get('id', 'N/A')}: {note.get('title', 'Untitled')} ({note.get('created_at', 'N/A')})\")
print(f'Total accessible notes: {len(notes)}')
"
Settings > Data Retention (Business/Enterprise):
| Data Type | Recommended Retention | Rationale |
|---|---|---|
| Meeting notes | 1-2 years | Long-term reference value |
| Transcripts | 90 days | Storage efficiency, lower PII risk |
| Audio | Deleted after processing | Granola default, not configurable |
| Attendee info | Retained with notes | Needed for People & Companies CRM |
Per-workspace overrides (Enterprise):
Required controls:
| GDPR Right | Granola Implementation |
|---|---|
| Right of Access (Art. 15) | Export user's data via Settings > Data > Export or Enterprise API |
| Right to Erasure (Art. 17) | Delete individual notes; request account deletion from Granola |
| Right to Data Portability (Art. 20) | Copy notes as text, or use local cache export |
| Right to Object (Art. 21) | AI training opt-out (Business/Enterprise) |
| Lawful Basis | Consent (recording notice) or Legitimate Interest (employer's business ops) |
Subject Access Request (SAR) handling:
## SAR Response Procedure
1. Receive SAR from data subject (30-day response deadline)
2. Verify identity of the requester
3. Search Granola for all notes containing the requester
- People view: search by name/email
- Enterprise API: query notes by attendee email
4. Export relevant notes (copy as text)
5. Redact third-party PII from the export
6. Deliver export to requester within 30 days
7. Document the SAR and response in compliance log
Data Processing Agreement:
For California consumer data:
For long-term retention beyond Granola:
# Monthly archival via Zapier
Trigger: Schedule by Zapier — 1st of month
Step 1 — Granola: List notes from past month
(via Enterprise API or folder trigger accumulation)
Step 2 — Google Drive: Create folder
Name: "Meeting Archives / YYYY-MM"
Step 3 — Google Drive: Upload files
Content: Note markdown for each meeting
Step 4 — Slack: Notify admin
Message: "Monthly meeting archive created: X notes archived"
Alternative: local cache backup
# Backup local cache monthly
BACKUP_DIR="$HOME/backups/granola"
mkdir -p "$BACKUP_DIR"
cp "$HOME/Library/Application Support/Granola/cache-v3.json" \
"$BACKUP_DIR/cache-v3-$(date +%Y%m%d).json"
echo "Granola cache backed up"
| Error | Cause | Fix |
|---|---|---|
| Cannot export notes | No bulk export feature | Use local cache export script or Enterprise API |
| SAR deadline at risk | No process owner | Assign dedicated compliance contact |
| Retention policy not applied | Enterprise feature required | Upgrade to Enterprise, or manually manage |
| Archive missing notes | Cache didn't contain all notes | Use Enterprise API for complete workspace data |
| Deletion incomplete | Backup retention period | Allow 30 days for Granola to purge from all backups |
Proceed to granola-enterprise-rbac for role-based access control configuration.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).