V3 Memory Unification

If you're dealing with multiple memory backends scattered across SQLite, Markdown files, and various manager classes, this consolidates them into a single AgentDB layer with HNSW vector indexing. The performance claims are aggressive (150x to 12,500x faster search), but the architecture is sound: unified interface, proper migration tooling, and semantic search that actually works at scale. Most useful when you've got agent systems that need to share memory across instances or when your existing search is choking on large datasets. The SONA learning integration is a nice touch for adaptive agents. Migration looks straightforward with clear phases, though you'll want to validate those speedup numbers against your actual data before committing.

GitHub stars: 240
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add spencermarx/open-code-review --skill 'V3 Memory Unification' --agent claude-code

Installs into .claude/skills of the current project.

Files

V3 Memory Unification

What This Skill Does

Consolidates disparate memory systems into unified AgentDB backend with HNSW vector search, achieving 150x-12,500x search performance improvements while maintaining backward compatibility.

Quick Start

# Initialize memory unification
Task("Memory architecture", "Design AgentDB unification strategy", "v3-memory-specialist")

# AgentDB integration
Task("AgentDB setup", "Configure HNSW indexing and vector search", "v3-memory-specialist")

# Data migration
Task("Memory migration", "Migrate SQLite/Markdown to AgentDB", "v3-memory-specialist")