skills.rest
dglijin-oss
dglijin-ossCOMMUNITY
Explore all skills by this author →
GitHub

elite-longterm-memory-local

Store and search memories locally using LanceDB and Ollama embeddings.

10|2|Updated Apr 3, 2026
Search Tags:#memory#ai-agent#lancedb#ollama#vector-search#long-term-memory#local-embedding
One-click install
npx skills add https://github.com/dglijin-oss/chinese-metaphysics-skills --skill elite-longterm-memory-local-dglijin-oss
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: elite-longterm-memory-local
Source: https://github.com/dglijin-oss/chinese-metaphysics-skills/tree/main/elite-longterm-memory-local
Command: npx skills add https://github.com/dglijin-oss/chinese-metaphysics-skills --skill elite-longterm-memory-local-dglijin-oss

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @lancedb/lancedb, apache-arrow, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill provides a local vector memory system, allowing for long-term memory management without relying on external APIs.

Core Features & Use Cases

  • Local Embedding: Utilizes LanceDB and Ollama for local embedding, ensuring no data leaves the user's machine.
  • Semantic Search: Allows for semantic memory search and auto-recall of related information.
  • Layered Storage: Implements a five-layered memory system (Hot RAM, Warm Store, Cold Store, Archive, Embedding) for efficient data management.
  • Privacy-First: Ensures that all data remains private and does not leave the user's machine.
  • Offline Capable: Works offline without the need for internet connectivity.
  • Use Case: Suitable for AI agents or personal digital assistants that require long-term memory retention and context awareness.

Quick Start

Initialize the memory system with node skills/elite-longterm-memory/bin/init.js, then start storing and searching memories using node skills/elite-longterm-memory/bin/memory.js.

Frequently Asked Questions about elite-longterm-memory-local

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

FAQPage Schema
How do I set up local long-term memory for an AI agent without external APIs?▼

Set up local long-term memory by initializing LanceDB for vector storage and Ollama for local embedding. This system stores and retrieves semantic context entirely on your machine, ensuring privacy and offline capability without external API calls.

What's the best way to implement semantic search and auto-recall for a personal digital assistant?▼

Implement semantic search by using LanceDB to query vector embeddings generated locally via Ollama. This enables auto-recall of contextually related information, allowing your digital assistant to retrieve relevant past interactions efficiently.

How does layered memory storage work for offline AI context retention?▼

Layered memory storage manages data across five tiers: Hot RAM, Warm Store, Cold Store, Archive, and Embedding. This architecture optimizes data retrieval and retention for AI agents, balancing speed and capacity without leaving the local machine.

Do I need an internet connection to use LanceDB and Ollama for vector search?▼

No, you do not need an internet connection. LanceDB handles vector storage and Ollama manages local embedding, making the system fully offline capable and privacy-first, ensuring no data leaves your machine during memory operations.

How do I initialize and store memories using a local vector database?▼

Initialize the vector database by running `node skills/elite-longterm-memory/bin/init.js`. Store and search memories subsequently using `node skills/elite-longterm-memory/bin/memory.js`, interacting directly with the local LanceDB and Ollama backend.

Related Skills

Explore More Software Engineering Skills→
rawvegrawveg
40

ollama

Run and interact with local AI models via the Ollama API.

Community
Advanced
Neuron-Mr-WhiteNeuron-Mr-White
56

memory

Store, retrieve, and organize persistent memories across sessions.

Community
Advanced
constructive-ioconstructive-io

pgvector-rag

Create and manage pgvector databases in PostgreSQL with Ollama for RAG pipelines.

Official
Advanced
icyzhicyzh
1

pinecone-research

Integrate Pinecone vector databases into agent workflows for persistent memory and semantic search.

Community
Intermediate