ax-persistence

Manage data persistence for AI agents with SQLite and PostgreSQL backends.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The ax-persistence Skill unit streamlines the process of managing data persistence for AI agents by providing a unified StorageProvider.

Core Features & Use Cases

  • Unified Data Persistence: Offers a unified approach to handle storage of various data types such as message queues, conversation history, session stores, document stores, file stores, job stores, and database migrations.
  • Database-Backed Storage: Leverages a shared DatabaseProvider for SQLite and PostgreSQL support.
  • Sub-Stores: Provides MessageQueueStore, ConversationStoreProvider, SessionStoreProvider, and DocumentStore for specific data needs.
  • Standalone Stores: Includes FileStore and JobStore for additional data handling.
  • Workspace Management: Offers git clone URLs for agent workspaces with support for both local and k8s deployments.

Quick Start

To enable data persistence for your AI agent, use the ax-persistence Skill to configure the StorageProvider and initialize the required databases.

Frequently Asked Questions about ax-persistence

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

FAQPage Schema
How do I manage data persistence for AI agents across multiple storage backends?

Data persistence for AI agents is managed through a unified StorageProvider that streamlines handling various data types. It supports SQLite and PostgreSQL backends, enabling consistent storage of message queues, conversation history, and document files.

What is the best way to store conversation history and session tracking for an AI agent?

Conversation history and session tracking are handled by dedicated sub-stores within a unified StorageProvider. This approach provides structured database-backed storage, ensuring conversation context and session states remain persistent across agent interactions.

Can I use PostgreSQL and SQLite for AI file management and job stores?

PostgreSQL and SQLite are supported as database backends for AI file management and job stores. The system leverages a shared DatabaseProvider to handle both structured data and background job storage seamlessly across these databases.

How do I configure git-based workspace management for AI agents?

Git-based workspace management for AI agents is configured using git clone URLs provided by the persistence system. It supports both local and k8s deployments, allowing agents to clone and manage their isolated working environments.

Does this data persistence approach support message queues and document storage?

This data persistence approach fully supports message queues and document storage through dedicated sub-stores. It provides a MessageQueueStore and DocumentStore alongside standalone FileStore and JobStore components for comprehensive data handling.