persistence

Manage data persistence operations for the AX agent using SQLite or PostgreSQL.

5|2|Updated Feb 8, 2026
One-click install
npx skills add https://github.com/project-ax/ax --skill persistence-project-ax
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: persistence
Source: https://github.com/project-ax/ax/tree/main/.claude/skills/ax/persistence
Command: npx skills add https://github.com/project-ax/ax --skill persistence-project-ax

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the need for robust and organized data management within the AX agent, ensuring that conversation history, session data, and documents are reliably stored and retrievable.

Core Features & Use Cases

  • Unified Data Storage: Manages message queues, conversation history, session tracking, and document storage through a single StorageProvider.
  • Database Agnosticism: Supports both SQLite for local development and PostgreSQL for production environments.
  • Migration Management: Includes a system for schema migrations to ensure database consistency.
  • Use Case: When the agent needs to recall past interactions or store user-uploaded files, this Skill ensures that data is persisted efficiently and securely.

Quick Start

Use the persistence skill to ensure the conversation history is saved.

Frequently Asked Questions about persistence

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

FAQPage Schema
How do I store conversation history for an AI agent locally?

You can store conversation history locally using a SQLite-backed StorageProvider, which manages message queues and session data efficiently without requiring external database infrastructure.

Can I use PostgreSQL for agent session tracking in production?

Yes, PostgreSQL is supported for production environments, allowing the StorageProvider to handle session tracking, conversation history, and document storage with robust reliability and scale.

How do database migrations work when managing persistent agent data?

Database migrations are integrated directly into the storage system to manage schema evolution, ensuring that your database schema remains consistent and up-to-date across different environments.

What is the best way to manage message queues and document storage together?

A unified StorageProvider allows you to manage message queues, session stores, and document storage together, while also supporting standalone file and job stores for specific persistence needs.

Does this data persistence approach support both local development and production?

Yes, the storage system is database agnostic, supporting SQLite for local development and PostgreSQL for production environments to ensure seamless data management across different deployment stages.