skills.rest
Tugoukezhang
TugoukezhangCOMMUNITY
Explore all skills by this author →
GitHub

elite-longterm-memory

Persist agent context across sessions using a multi-layer memory stack.

8|1|Updated Apr 13, 2026
Search Tags:#memory#ai-agent#lancedb#vector-search#long-term-memory#wal#git-notes
One-click install
npx skills add https://github.com/Tugoukezhang/workbuddy-skills --skill elite-longterm-memory-tugoukezhang
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: elite-longterm-memory
Source: https://github.com/Tugoukezhang/workbuddy-skills/tree/main/skills/elite-longterm-memory
Command: npx skills add https://github.com/Tugoukezhang/workbuddy-skills --skill elite-longterm-memory-tugoukezhang

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Eliminates context loss for AI agents by providing a durable, multi-layer memory architecture that links hot RAM, semantic recall, and long-term archives.

Core Features & Use Cases

  • Multi-layer memory stack: hot RAM (SESSION-STATE.md), warm store (LanceDB), cold store (Git-Notes), curated MEMORY.md, optional cloud backup.
  • Durable, auditable decisions and memories that survive restarts and device changes.
  • Use cases include long-running agent sessions, cross-device collaboration, and audit trails for AI decisions.

Quick Start

Initialize the memory system in your workspace to start tracking tasks, decisions, and daily logs.

Frequently Asked Questions about elite-longterm-memory

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

FAQPage Schema
How do I retain AI agent memory across sessions?▼

To retain AI agent memory across sessions, use a multi-layer memory stack linking hot RAM, LanceDB vector search, and Git-Notes archives, ensuring durable context and decision logs survive restarts.

What is the best way to implement long-term memory for an AI agent?▼

The best way to implement long-term memory is by deploying a multi-layer architecture: hot RAM for session state, LanceDB for warm vector recall, and Git-Notes for cold storage, providing fast semantic search and auditable archives.

Can I use Git-Notes to store AI agent decision logs?▼

Yes, you can use Git-Notes as a cold store to maintain durable, auditable AI agent decision logs, ensuring memories survive device changes and providing an accessible archive for cross-device synchronization.

Do I need a write-ahead log for AI agent memory persistence?▼

You need a write-ahead log (WAL) for AI agent memory persistence to guarantee durability, ensuring essential context and decision logs are not lost during restarts or unexpected interruptions before committing to long-term storage.

How does cross-device synchronization work for persistent agent context?▼

Cross-device synchronization for persistent agent context works by utilizing Git-Notes cold storage and optional cloud backup, allowing multiple devices to access and audit the same durable multi-layer memory archives.

Related Skills

Explore More Software Engineering Skills→
kaifashraffkaifashraff

elite-longterm-memory-local

Manage private on-device memory for AI agents with LanceDB and JavaScript embeddings.

Community
Advanced
aztr0nutzsaztr0nutzs
2

elite-longterm-memory

Manage multi-layered agent memory with hot RAM, LanceDB, Git-Notes, and WAL.

Community
Advanced
mindmorassmindmorass
2

qdrant-patterns

Store and retrieve documents in Qdrant for semantic search.

Community
Advanced
tiankong0101-bytetiankong0101-byte

elite-longterm-memory

Persist agent context across sessions using session state, vector search, git notes, and markdown archives.

Community
Advanced