skills.rest
FrekiManagarm
FrekiManagarmCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

V3 Memory Unification

Migrates legacy memory backends into AgentDB with HNSW vector indexing.

Updated May 8, 2026
Search Tags:#semantic search#embeddings#agentdb#vector search#data migration#hnsw#memory migration
One-click install
npx skills add https://github.com/FrekiManagarm/d-chambaud --skill v3-memory-unification-frekimanagarm
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: V3 Memory Unification
Source: https://github.com/FrekiManagarm/d-chambaud/tree/main/.agents/skills/v3-memory-unification
Command: npx skills add https://github.com/FrekiManagarm/d-chambaud --skill v3-memory-unification-frekimanagarm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Agent systems often accumulate fragmented memory stores (SQLite, Markdown files, swarm-specific backends) that are slow to search and hard to share across agents. This Skill consolidates them into a single AgentDB backend with HNSW vector indexing for fast semantic retrieval. ## Core Features & Use Cases - Unified Memory Service: Implements a single IMemoryBackend interface over AgentDB, routing semantic queries through an HNSW index and structured queries through AgentDB. - Data Migration: Provides phased migration patterns for moving SQLite and Markdown memory entries into AgentDB with generated embeddings. - SONA Integration: Stores and retrieves learning patterns with reward and adaptation metadata for cross-agent learning. - Use Case: A team running multiple Claude Flow memory backends uses this Skill to migrate all entries into AgentDB, then validates the 150x-12,500x search speedup and cross-agent memory sharing. ## Quick Start Ask the agent to design an AgentDB unification strategy and migrate the existing SQLite and Markdown memory stores into it with HNSW indexing enabled.

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 dedicated phase after the AgentDB adapter is configured with HNSW indexing.

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. In this Skill it indexes memory embeddings with configurable parameters like efConstruction and M, targeting 150x-12,500x faster semantic search over large memory stores.

Can Markdown-based memory files be migrated to AgentDB?▼

Yes. The migration globs Markdown files, reads their content, generates embeddings, and stores each as a memory entry with the original file path preserved in metadata. This converts file-based memory into searchable vector entries.

Does the unified memory service keep backward compatibility?▼

Yes. The UnifiedMemoryService implements the IMemoryBackend interface, so existing callers keep working. Structured queries route to AgentDB directly while semantic queries route through the HNSW index.

What are the limitations of HNSW vector search for memory?▼

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 every entry, adding upfront migration and storage cost.

Related Skills

Explore More Software Engineering Skills→
ruvnetruvnet
70.1k

V3 Memory Unification

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

Community
Advanced
pacphipacphi
7

V3 Memory Unification

Consolidate SQLite, Markdown, and distributed memory systems into a unified AgentDB backend with HNSW indexing.

Community
Advanced
JacobJ215JacobJ215

V3 Memory Unification

Unify SQLite and Markdown memory backends into AgentDB with HNSW indexing.

Community
Advanced
JLMA-Agentic-AiJLMA-Agentic-Ai

V3 Memory Unification

Consolidate SQLite and Markdown memory backends into AgentDB with HNSW vector search.

Community
Advanced