skills.rest
Mohabsmar
MohabsmarCOMMUNITY
Explore all skills by this author →
GitHub

elite-longterm-memory

Implement layered memory with LanceDB, Git-notes, and Write-Ahead Logging.

Updated Mar 29, 2026
Search Tags:#memory#ai-agent#lancedb#vector-search#long-term-memory#wal#git-notes
One-click install
npx skills add https://github.com/Mohabsmar/VoiceDev-2.0 --skill elite-longterm-memory-mohabsmar
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: elite-longterm-memory
Source: https://github.com/Mohabsmar/VoiceDev-2.0/tree/main/skills/elite-longterm-memory
Command: npx skills add https://github.com/Mohabsmar/VoiceDev-2.0 --skill elite-longterm-memory-mohabsmar

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Persistent context loss is a critical bottleneck for AI agents. Elite Longterm Memory provides a layered memory system to keep context across sessions and tasks.

Core Features & Use Cases

  • WAL protocol for durable decisions via write-ahead logging.
  • LanceDB-based vector recall for semantic search and auto-recall across memories.
  • Git-Notes knowledge graph for structured decisions and context retention.
  • MEMORY.md archive with daily logs and optional cloud backup for long-term knowledge.
  • Mem0 auto-extraction integration to reduce token load.
  • OpenClaw integration guidance for agent prompts and memory instructions.

Quick Start

Run the elite-longterm-memory init command in your project directory to initialize the memory system.

Frequently Asked Questions about elite-longterm-memory

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

FAQPage Schema
How do I add long-term memory to an AI agent to prevent context loss between sessions?▼

Long-term memory for AI agents uses a layered system applying hot RAM, LanceDB vector recall, and Git-notes to maintain persistent context and durable decisions, preventing context loss across sessions and tasks.

What is the best way to implement semantic recall for an autonomous AI workflow?▼

The best way to implement semantic recall for AI agents is using LanceDB-based vector recall, which enables semantic search and auto-recall across stored memories to retrieve relevant past context automatically.

How does write-ahead logging work for durable AI agent decisions?▼

Write-ahead logging for AI agent decisions works by applying a WAL protocol to log operations before execution, ensuring that durable decisions and context are safely retained even if the agent process crashes.

Can I use LanceDB and Git-notes together for AI agent memory and context retention?▼

Yes, LanceDB and Git-notes can be used together. LanceDB handles vector recall for semantic search while Git-notes provides a knowledge graph memory store for structured decisions and durable context retention.

Do I need a vector database to maintain persistent context for AI agents?▼

You need a vector database like LanceDB for semantic recall, but persistent context also relies on hot RAM for active state, Git-notes for structured knowledge, and a MEMORY.md archive for long-term logs.

Are there limitations to using a MEMORY.md archive for long-term AI knowledge?▼

A MEMORY.md archive stores long-term knowledge via daily logs, but maintaining it requires token management strategies like Mem0 auto-extraction to reduce load, alongside optional cloud backup for durability.

Related Skills

Explore More Software Engineering Skills→
alexanderopalexanderop

using-git-worktrees

Create isolated git worktrees for feature branches with safety checks.

Community
Advanced
kcleto-aikcleto-ai
41

gos-handoff

Update MEMORY.md, write daily logs, and capture durable decisions for Claude Code sessions.

Community
Advanced
wewetv1987-cellwewetv1987-cell

elite-longterm-memory

Preserve AI agent context and decisions across sessions with file-based memory.

Community
Advanced
darblexdarblex

elite-longterm-memory

Manage AI agent memory with RAM, vector search, and knowledge graphs.

Community
Advanced