skills.rest
project-ax
project-axOFFICIAL
Explore all skills by this author →
GitHub

ax-provider-memory

Manage AI application memory with an embedding-based Cortex provider.

5|2|Updated Feb 8, 2026
Search Tags:#AI knowledge base#semantic search#memory management#Cortex provider#salience scoring
One-click install
npx skills add https://github.com/project-ax/ax-legacy --skill ax-provider-memory
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ax-provider-memory
Source: https://github.com/project-ax/ax-legacy/tree/main/.claude/skills/ax-provider-memory
Command: npx skills add https://github.com/project-ax/ax-legacy --skill ax-provider-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill simplifies memory management by providing an embedding-based Cortex provider with summary store, salience scoring, and LLM extraction, streamlining knowledge storage and retrieval.

Core Features & Use Cases

  • Cortex Provider: Offers embedding-based system with SQLite/PostgreSQL support for both local and k8s environments.
  • Semantic Search: Utilizes vector embeddings for similarity matching with fallback to keyword search.
  • LLM Extraction: Extracts structured knowledge items from conversations using LLMs.
  • Deduplication: Prevents duplicate entries using content hashing.
  • Use Case: Improve the searchability and maintainability of knowledge bases within an organization by leveraging the Cortex provider for memory management.

Quick Start

Implement Cortex memory logic in your project by utilizing the Cortex provider, and apply salience scoring to rank memory items effectively.

Frequently Asked Questions about ax-provider-memory

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

FAQPage Schema
How do I implement semantic search and salience scoring for an AI knowledge base?▼

Semantic search and salience scoring for an AI knowledge base are implemented using an embedding-based Cortex provider that ranks memory items and matches vector embeddings with keyword search fallback.

Does the Cortex memory provider support both local SQLite and PostgreSQL environments?▼

Yes, the Cortex memory provider supports both SQLite and PostgreSQL, enabling knowledge storage scaling from local development environments to k8s deployments.

How can I extract structured knowledge items from conversations using LLMs?▼

You can extract structured knowledge items from conversations using LLM extraction, which automatically parses dialogue to populate your memory management system with relevant data.

What is the best way to prevent duplicate entries in AI memory management?▼

The best way to prevent duplicate entries in AI memory management is applying content hashing for deduplication, ensuring your knowledge base remains clean and maintainable.

Can I use this Cortex provider for administrative workflows involving AI knowledge base maintenance?▼

Yes, this Cortex provider is specifically optimized for administrative workflows, streamlining AI knowledge base maintenance through deduplication, LLM extraction, and embedding-based retrieval.

Related Skills

Explore More Software Engineering Skills→
dmzoneilldmzoneill
2

debug-local-db

Diagnose PostgreSQL and SQLite database issues in Podman containers.

Community
Intermediate
0xUrsanomics0xUrsanomics
2

recall

Retrieve ranked context from local knowledge graphs and memory files.

Community
Advanced
kivo360kivo360
1

moai-essentials-refactor

Transform domain knowledge into vector embeddings for semantic retrieval.

Community
Intermediate
ccfccf

hybrid-search-implementation

Combine vector similarity with keyword matching for hybrid retrieval.

Community
Intermediate