skills.rest
monktui
monktuiCOMMUNITY
Explore all skills by this author →
GitHub

V3 Memory Unification

Unify fragmented memory backends into a single AgentDB layer with HNSW vector search.

Updated Feb 10, 2026
Search Tags:#agentdb#vector search#data migration#hnsw indexing#memory unification#son a integration
One-click install
npx skills add https://github.com/monktui/git-review --skill v3-memory-unification-monktui
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: V3 Memory Unification
Source: https://github.com/monktui/git-review/tree/main/.claude/skills/v3-memory-unification
Command: npx skills add https://github.com/monktui/git-review --skill v3-memory-unification-monktui

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the fragmentation and slow retrieval caused by having multiple, overlapping memory backends that make cross-system search and migration costly and inconsistent.

Core Features & Use Cases

  • Unified Memory Service on AgentDB: Consolidates legacy memory systems behind a single IMemoryBackend-style interface for consistent storage and querying across agents.
  • HNSW semantic search acceleration: Enables semantic queries using HNSW vector indexing to deliver large speedups (150x–12,500x) for high-volume retrieval.
  • Hybrid migration support: Provides a migration approach for structured SQLite data and file-based Markdown content into AgentDB while preserving metadata needed for traceability and backward compatibility.
  • SONA pattern integration: Stores and retrieves learning patterns with embeddings and metadata filters to support adaptive behavior workflows.

Quick Start

Use the V3 Memory Unification skill to initialize the AgentDB unification workflow by running: Task("Memory architecture", "Design AgentDB unification strategy", "v3-memory-specialist").

Frequently Asked Questions about V3 Memory Unification

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

FAQPage Schema
How do I migrate SQLite and Markdown memory backends into a unified database?▼

Migrate SQLite and Markdown memory backends using a phased migration strategy that consolidates structured data and file-based content into AgentDB while preserving metadata for traceability and backward compatibility.

How does HNSW vector indexing accelerate semantic search for high-volume memory retrieval?▼

HNSW vector indexing accelerates semantic search by using embedding-driven queries to deliver large speedups, ranging from 150x to 12,500x, for high-volume memory retrieval across agents.

What is memory unification for cross-agent memory sharing?▼

Memory unification consolidates fragmented memory backends behind a single IMemoryBackend-style interface, enabling consistent storage, querying, and cross-agent memory sharing within AgentDB.

Can I store and retrieve SONA learning patterns using semantic queries and metadata filters?▼

Store and retrieve SONA learning patterns using embeddings and metadata filters to support adaptive behavior workflows within the unified memory service.

Does the AgentDB unification strategy align with ADR-006 and ADR-009 architecture requirements?▼

The AgentDB unification strategy requires implementing a UnifiedMemoryService with HNSW indexing and a phased migration approach consistent with ADR-006 and ADR-009 architecture requirements.

Related Skills

Explore More Software Engineering Skills→
FrekiManagarmFrekiManagarm

V3 Memory Unification

Migrate fragmented memory backends into AgentDB with HNSW vector search.

Community
Advanced
nahtonajnahtonaj

v3-memory-unification

Consolidate SQLite and Markdown memory stores into a unified AgentDB backend with HNSW indexing.

Community
Advanced
EarthmanWebEarthmanWeb
2

V3 Memory Unification

Unify multiple memory systems into a single AgentDB with HNSW indexing.

Community
Advanced
ricablericable
1

Claude Flow Memory

Manage agent memory with hybrid SQLite and AgentDB backends using HNSW indexing.

Community
Intermediate