skills.rest
optimaxin
optimaxinCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

V3 Memory Unification

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

Updated Jul 16, 2026
Search Tags:#semantic search#embeddings#multi-agent#agentdb#vector search#hnsw#memory migration
One-click install
npx skills add https://github.com/optimaxin/Tredev_Gems --skill v3-memory-unification-optimaxin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: V3 Memory Unification
Source: https://github.com/optimaxin/Tredev_Gems/tree/main/.claude/skills/v3-memory-unification
Command: npx skills add https://github.com/optimaxin/Tredev_Gems --skill v3-memory-unification-optimaxin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Fragmented memory systems (SQLite, Markdown, distributed stores) create inconsistent query interfaces and slow retrieval. This Skill unifies 6+ legacy memory backends into a single AgentDB service with HNSW vector indexing for semantic search. ## Core Features & Use Cases - Unified Memory Service: Implements a single IMemoryBackend interface routing queries to AgentDB or the HNSW index based on query type. - HNSW Vector Search: Configures approximate nearest-neighbor indexing with tunable parameters (efConstruction, M) targeting 150x-12,500x search speedups. - Data Migration: Provides phased migration patterns for moving SQLite records and Markdown files into AgentDB with generated embeddings. - Use Case: A multi-agent system storing learning patterns across separate SQLite and Markdown backends can migrate both into AgentDB, then run semantic queries across all agents' memories through one interface. ## Quick Start Ask the agent to design an AgentDB unification strategy and migrate the existing SQLite and Markdown memory backends into a unified HNSW-indexed store.

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 data to AgentDB?▼

Read all entries from the SQLite backend, generate an embedding for each entry's content, then store the entry with its embedding into AgentDB. The migration runs as a loop over existing records, preserving metadata while adding vector representations.

What is HNSW indexing and why use it for memory search?▼

HNSW (Hierarchical Navigable Small World) is an approximate nearest-neighbor index for vector search. It enables semantic queries over memory embeddings with 150x-12,500x speedups compared to brute-force search, using parameters like efConstruction and M to tune accuracy versus speed.

Can Markdown files be used as a memory backend?▼

Yes, Markdown files can be migrated into AgentDB by reading each file, generating an embedding of its content, and storing it with metadata referencing the original file path. After migration, the files become semantically searchable.

Does the unified memory service support backward compatibility?▼

Yes, the UnifiedMemoryService implements the IMemoryBackend interface, so existing code calling legacy memory systems continues to work. Non-semantic queries route directly to AgentDB while semantic queries use the HNSW index.

What are the limitations of HNSW vector search?▼

HNSW provides approximate rather than exact nearest-neighbor results, so recall depends on index parameters like efConstruction and M. It also requires generating embeddings for all stored content, adding upfront computation during migration and indexing.

Related Skills

Explore More Software Engineering Skills→
Synaptic-Labs-AISynaptic-Labs-AI
71

pact-memory

Store and retrieve structured memories in a SQLite-backed store for PACT agents.

Official
Advanced
BURHANDEV-ENTERPRISEBURHANDEV-ENTERPRISE

V3 Memory Unification

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

Official
Advanced
acarmonagacarmonag
2

V3 Memory Unification

Consolidate fragmented memory backends into a unified AgentDB with HNSW indexing.

Community
Advanced
mahg-esmahg-es
3

vector-search

Configure HNSW/IVF indices and perform ANN search with vector embeddings.

Official
Advanced