atxp-memory

Back up, restore, and vector-search markdown memory files via ATXP and zvec.

10|1|Updated Sep 9, 2025
One-click install
npx skills add https://github.com/atxp-dev/cli --skill atxp-memory
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: atxp-memory
Source: https://github.com/atxp-dev/cli/tree/main/skills/atxp-memory
Command: npx skills add https://github.com/atxp-dev/cli --skill atxp-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @zvec/zvec, and includes references (resource) components.

What problem does it solve?

This Skill provides a robust solution for managing your agent's textual memories, ensuring they are backed up, restorable, and easily searchable, preventing data loss and enhancing recall.

Core Features & Use Cases

  • Cloud Backup & Restore: Securely push .md memory files to ATXP servers and pull them back to restore your workspace.
  • Local Vector Search: Index your local .md files into a zvec vector database for fast, semantic searching by natural language.
  • Use Case: After a productive session, you can push your updated SOUL.md and MEMORY.md files to the cloud. Later, if you need to recall a specific detail from past interactions, you can search your indexed memories for relevant context.

Quick Start

Use the atxp-memory skill to push your local memory files to the cloud.

Frequently Asked Questions about atxp-memory

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

FAQPage Schema
How do I back up and restore agent memory files in markdown format?

Agent memory files in markdown format can be backed up by pushing `.md` files like `SOUL.md` to ATXP cloud servers and restored by pulling them back to your local workspace.

How does local vector search work for finding past AI agent interactions?

Local vector search works by indexing `.md` files into a zvec vector database, enabling fast, semantic similarity searches by natural language to recall relevant context from past interactions.

Do I need Node.js to sync markdown memory files with cloud servers?

Yes, you need Node.js v18 or higher to sync markdown memory files with ATXP cloud servers and to utilize the optional @zvec/zvec dependency for local indexing capabilities.

Can I search my agent's markdown memories locally without a cloud connection?

Yes, you can search markdown memories locally without a cloud connection by indexing `.md` files into a zvec vector database for semantic similarity searches.

What is the best way to prevent data loss for AI agent memory files?

The best way to prevent data loss is synchronizing `.md` memory files with ATXP cloud servers for backup and restoring them later, ensuring persistent data retrieval.

Are there limitations when using zvec for local markdown indexing?

The local markdown indexing requires the optional @zvec/zvec dependency and Node.js v18 or higher, limiting vector search capabilities if these environment prerequisites are not met.