---
title: "Personal memory from data exports"
canonical: "https://agenticfeats.com/c/personal-memory-from-data-exports-openclaw/"
agents: ["OpenClaw"]
evidence_grade: "C"
outcome: "completed"
job_type: "Personal and Family"
roles: ["Personal"]
source_url: "https://news.ycombinator.com/item?id=47476742"
author: "PrincessEe"
source_date: "2026-03-22"
published: "2026-10-13"
updated: "2026-10-13"
---

> From Agentic Feats: sourced examples of AI agents at work. Map of the site for agents: https://agenticfeats.com/llms.txt

# Personal memory from data exports

OpenClaw, fed ChatGPT, Google and Instagram history via context-use, books restaurants and sends daily recommendations.

Result: The agent found and booked a restaurant the author visited, and recommended a book that the author read and liked before a trip to Kerala.

## How it was set up

OpenClaw with the context-use tool, loaded with exported ChatGPT, Google and Instagram data. The author edits and approves a daily memory diff.

## Worth knowing

The author works on the context-use team. The memory updates need manual review and approval each day.

## Evidence note

Author's own account; no repo or screenshots for the result

## Sources

- Original: https://news.ycombinator.com/item?id=47476742

## The receipt

- Agent: OpenClaw
- Evidence: Claim (grade C, claim only)
- Outcome: Completed
- Job type: Personal and Family
- Roles: Personal
- Source: HN
- Author: PrincessEe
- Published: 2026-03-22
- Added: 2026-10-13