skills.rest
dmuhoro
dmuhoroCOMMUNITY
Explore all skills by this author →
GitHub

V3 Memory Unification

Consolidates multiple memory backends into AgentDB with HNSW vector search indexing.

Updated Mar 25, 2026
Search Tags:#semantic search#embeddings#multi-agent#agentdb#vector search#hnsw#memory migration
One-click install
npx skills add https://github.com/dmuhoro/EasyTutor --skill v3-memory-unification-dmuhoro
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: V3 Memory Unification
Source: https://github.com/dmuhoro/EasyTutor/tree/main/archive/.claude/skills/v3-memory-unification
Command: npx skills add https://github.com/dmuhoro/EasyTutor --skill v3-memory-unification-dmuhoro

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Fragmented memory systems (SQLite, Markdown, swarm memory, distributed stores) create inconsistent query interfaces and slow retrieval across agents. This Skill unifies them into a single AgentDB backend with HNSW indexing for fast semantic search. ## Core Features & Use Cases - Unified Memory Service: Implements a single IMemoryBackend interface over AgentDB, routing semantic queries through an HNSW indexer and structured queries through AgentDB. - Data Migration: Migrates entries from SQLite backends and Markdown files into AgentDB with generated embeddings and preserved metadata. - SONA Integration: Stores and retrieves learning patterns with reward and adaptation metadata for cross-agent memory sharing. - Use Case: An agent system running seven separate memory stores migrates all entries into AgentDB, then serves semantic queries through HNSW search targeting 150x-12,500x speedups and sub-100ms latency on 1M+ entries. ## Quick Start Ask the agent to design and implement the AgentDB unification strategy, migrating existing SQLite and Markdown memory stores into a single HNSW-indexed backend.

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 memory stores to AgentDB?▼

Read all entries from the SQLite backend, generate an embedding for each entry's content, then store the entry with its embedding in AgentDB. The same pattern applies to Markdown files, preserving the original file path in metadata.

What is HNSW indexing used for in agent memory systems?▼

HNSW (Hierarchical Navigable Small World) indexing accelerates approximate nearest-neighbor search over embedding vectors. In this design it targets 150x-12,500x search speedups and sub-100ms query latency across more than one million memory entries.

Does AgentDB unification keep backward compatibility with existing memory backends?▼

Yes. The UnifiedMemoryService implements the existing IMemoryBackend interface, so callers keep the same store and query contract while semantic queries route to the HNSW indexer and structured queries route to AgentDB.

How does SONA learning integrate with the unified memory store?▼

Learning patterns are stored as memory entries whose metadata includes the SONA mode, reward, and adaptation time, along with a content embedding. Similar patterns are retrieved through filtered semantic queries targeting sub-0.05ms adaptation time.

What are the limitations of HNSW-based memory search?▼

HNSW provides approximate rather than exact nearest-neighbor results, so recall depends on tuning parameters like efConstruction and M. It also requires generating embeddings for every stored entry, adding indexing overhead during migration.

Related Skills

Explore More Software Engineering Skills→
fableindigo-giffableindigo-gif

V3 Memory Unification

Consolidate memory systems into an AgentDB backend with HNSW vector indexing.

Community
Advanced
thewoolleymanthewoolleyman

V3 Memory Unification

Consolidate fragmented memory backends into a single AgentDB store with HNSW indexing.

Community
Advanced
monktuimonktui

V3 Performance Optimization

Benchmarks Flash Attention, HNSW search, and memory usage against stored baselines.

Community
Advanced
33may33may
1

V3 Memory Unification

Consolidates multiple memory backends into AgentDB with HNSW vector search indexing.

Community
Advanced