triple-memory

Coordinate LanceDB auto-recall, Git-Notes memory, and file-based workspace search for persistent context.

Updated Jan 31, 2026

Search Tags:#memory #persistence #lancedb #agent-context #git-notes-memory #workspace-search

Ready to run

npx skills add https://github.com/Lutra23/content-workflow --skill triple-memory

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: triple-memory
Source: https://github.com/Lutra23/content-workflow/tree/main/skills/triple-memory
Command: npx skills add https://github.com/Lutra23/content-workflow --skill triple-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill provides a unified memory architecture that preserves context across agent sessions by coordinating LanceDB auto-recall, Git-Notes structured memory, and file-based workspace search. It is ideal when you need persistent context, cross-session continuity, or coherent decision and task tracking across multiple memory backends.

Core Features & Use Cases

LanceDB memory: auto-recall and auto-capture for conversation memory and preferences
Git-Notes memory: structured, branch-scoped memory with entity extraction for searchable decisions
File Search: workspace-based memory indexing and quick file retrieval
Use Case: long-running agents requiring persistent context and multi-backend memory coherence across sessions

Quick Start

Start by enabling the LanceDB memory plugin, install Git-Notes memory, and set up the file search script, then initialize a session to load persistent context.

Frequently Asked Questions about triple-memory

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

FAQPage Schema

How do I maintain persistent context for AI agents across multiple sessions?▼

To maintain persistent context for AI agents across multiple sessions, you coordinate LanceDB auto-recall, Git-Notes structured memory, and file-based workspace search. This multi-backend approach preserves conversation history and coherent decision tracking over long-running workflows.

What is the best way to store branch-scoped agent memory with entity extraction?▼

The best way to store branch-scoped agent memory with entity extraction is using Git-Notes structured memory, which captures searchable decisions and context tied to specific repository branches for coherent long-running agent workflows.

How do I set up multi-backend memory for long-running agent workflows?▼

To set up multi-backend memory for long-running agent workflows, you enable the LanceDB memory plugin for auto-recall, install Git-Notes memory for branch-scoped context, and configure a file search script for workspace indexing before initializing your session.

Does LanceDB auto-recall work with file-based workspace search for agent context?▼

Yes, LanceDB auto-recall works with file-based workspace search by coordinating vector-based conversation memory alongside deterministic file retrieval. This unified architecture ensures multi-source memories are coherent across persistent agent sessions.

Can I use Git-Notes memory for structured decisions in agent sessions?▼

Yes, you can use Git-Notes memory for structured decisions in agent sessions. It provides branch-scoped memory with entity extraction, allowing you to capture and search coherent decisions across long-running persistent agent workflows.

What are the limitations of coordinating multiple memory backends for agents?▼

Coordinating multiple memory backends for agents requires managing coherence across LanceDB, Git-Notes, and file search. You must initialize sessions properly and handle plugin integration, branch-scoped memories, and deterministic file-search workflows to avoid context fragmentation.