export

Exports all project memories from Mem0 to a portable Markdown file.

Updated Jun 29, 2026
One-click install
npx skills add https://github.com/nhatnguyen1122/Agent-Memory-Eval --skill export-nhatnguyen1122
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: export
Source: https://github.com/nhatnguyen1122/Agent-Memory-Eval/tree/main/mem0/integrations/mem0-plugin/skills/export
Command: npx skills add https://github.com/nhatnguyen1122/Agent-Memory-Eval --skill export-nhatnguyen1122

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Backing up or migrating Mem0 project memories requires manually querying the API and formatting results, which is error-prone and tedious when moving between projects or archiving state. ## Core Features & Use Cases - Full Memory Export: Fetches all memories for the active user and project with automatic pagination handling. - Portable Markdown Format: Writes each memory as a YAML-frontmatter block with id, timestamps, type, confidence, branch, files, and categories. - Use Case: Before cleaning up a project or switching teams, run the export to produce a dated file like mem0-export-myproject-2024-06-01.md that can be shared with teammates or re-imported later. ## Quick Start Export all memories for my current Mem0 project to a Markdown backup file.

Frequently Asked Questions about export

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I export Mem0 memories to a file?

Run the export skill, which fetches all memories for the active user and project via get_memories and writes them to a Markdown file named mem0-export-<project_id>-<date>.md in the current working directory.

How to back up Mem0 project memories before cleanup?

Use the export skill to create a dated Markdown backup containing every memory as a YAML-frontmatter block. The file preserves ids, timestamps, types, confidence, branches, files, and categories for later restoration or review.

What format does the Mem0 memory export use?

Each memory is written as a Markdown block with YAML frontmatter containing id, created_at, type, confidence, branch, files, and categories, followed by the memory content. Missing fields are written as empty strings.

Does the export handle large numbers of memories?

Yes, the export fetches memories with page_size 200 and automatically continues fetching pages when the response contains a next cursor or the count equals the page size, until all memories are retrieved.

Why does the export say no memories found?

This happens when get_memories returns zero results or an error for the resolved user_id and project_id. Check the MEM0_USER_ID and MEM0_PROJECT_ID environment variables to confirm the correct identity is being used.