V3 Memory Unification

Unify multiple memory systems into a single AgentDB-backed backend.

2|Updated Jul 26, 2019
One-click install
npx skills add https://github.com/qiphon/learn --skill v3-memory-unification-qiphon
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: V3 Memory Unification
Source: https://github.com/qiphon/learn/tree/main/.opencode/skills/v3-memory-unification
Command: npx skills add https://github.com/qiphon/learn --skill v3-memory-unification-qiphon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill consolidates multiple memory systems into a single, scalable AgentDB-backed backend with fast HNSW vector search, reducing fragmentation and enabling cross-agent memory sharing.

Core Features & Use Cases

  • Unified Memory Backend: Centralizes memory storage and retrieval across legacy systems with backward-compatible interfaces.
  • HNSW Powered Search: Provides high-speed semantic search over memory entries using HNSW indexing.
  • Migration & Integration: Supports migrating from SQLite/Markdown memories and integrating with SONA learning patterns.

Quick Start

Enable the unified memory workflow by wiring the AgentDB adapter, HNSW indexer, and migrator, then migrate existing memories to the unified 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 consolidate multiple memory backends into a single unified system?

To consolidate multiple memory backends, you can use a UnifiedMemoryService coordinating an AgentDBAdapter, an HNSWIndexer, and a DataMigrator. This centralizes memory storage and retrieval, reducing fragmentation and enabling cross-agent memory sharing.

Can I migrate memory data from SQLite and Markdown files to a unified backend?

Yes, you can migrate memory data from SQLite and Markdown files. The DataMigrator component supports SQLite and Markdown data migrations, transferring existing memories into the unified AgentDB-backed backend with backward-compatible interfaces.

What is the best way to enable high-speed semantic search over memory entries?

The best way to enable high-speed semantic search over memory entries is using HNSW indexing. The HNSWIndexer component provides HNSW powered search, allowing fast vector search across the consolidated memory entries in the AgentDB backend.

Does migrating memory systems with this approach maintain backward compatibility?

Migrating memory systems with this approach maintains backward compatibility. The unified memory backend centralizes memory storage and retrieval across legacy systems using backward-compatible interfaces, ensuring existing integrations continue to function.

How many memory backends can be unified during a memory consolidation migration?

You can unify six or more memory backends during a memory consolidation migration. The UnifiedMemoryService coordinates the migration and search across these backends, applying a unified query interface to the consolidated AgentDB backend.