skills.rest
ricable
ricableCOMMUNITY
Explore all skills by this author →
GitHub

Claude Flow Memory

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

1|Updated Feb 8, 2026
Search Tags:#knowledge base#memory#persistence#agentdb#vector search#hnsw
One-click install
npx skills add https://github.com/ricable/cli-skills-builder --skill claude-flow-memory
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Claude Flow Memory
Source: https://github.com/ricable/cli-skills-builder/tree/main/.claude/skills/claude-flow-memory
Command: npx skills add https://github.com/ricable/cli-skills-builder --skill claude-flow-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the challenge of efficiently storing, retrieving, and searching agent memory, enabling persistent knowledge bases for AI agents.

Core Features & Use Cases

  • Persistent Memory Storage: Utilizes a hybrid SQLite and AgentDB backend for durable storage.
  • Fast Semantic Search: Implements HNSW indexing for rapid vector-based similarity searches.
  • Use Case: When an agent needs to recall past interactions, access project-specific information, or perform semantic searches across a large corpus of documents, this skill provides the necessary memory management capabilities.

Quick Start

Initialize the memory database for your agent.

Frequently Asked Questions about Claude Flow Memory

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

FAQPage Schema
How do I add persistent memory to an AI agent for recalling past interactions?▼

You can add persistent memory to an AI agent by using a hybrid SQLite and AgentDB backend, which stores durable knowledge bases and enables agents to recall past interactions and project-specific information.

How does HNSW indexing work for vector search in an agent knowledge base?▼

HNSW indexing provides fast semantic search capabilities for an agent knowledge base by organizing vector embeddings into a navigable small world graph, allowing rapid similarity searches across large document corpora.

Can I use SQLite with AgentDB for unified agent memory management?▼

Yes, you can configure a hybrid SQLite and AgentDB backend to support unified memory management, allowing you to store, retrieve, search, and configure memory backends for persistent agent knowledge.

What is the best way to perform semantic searches across a large corpus of agent documents?▼

The best way to perform semantic searches across large document corpora is to utilize a memory backend with HNSW indexing, which provides fast vector-based similarity searches for efficient information retrieval.

Do I need any external dependencies to configure an agent memory backend?▼

No external dependencies are required to configure an agent memory backend, as the system integrates directly with AgentDB and SQLite to manage storing, retrieving, and searching persistent knowledge.

Related Skills

Explore More Software Engineering Skills→
nahtonajnahtonaj

v3-memory-unification

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

Community
Advanced
qiphonqiphon
2

AgentDB Vector Search

Rank documents by vector similarity for semantic retrieval in RAG pipelines.

Community
Intermediate
SignmanalSignmanal
1

chroma

Store and query vector embeddings with metadata filtering for RAG applications.

Community
Intermediate
Fl2vioFl2vio
1

AgentDB Vector Search

Enable semantic vector search and hybrid retrieval with AgentDB.

Community
Advanced