Generated by Code IQ · v1.0

memU
Knowledge Tutorial

memU is a framework that provides AI agents with long-term memory by organizing information into a hierarchical structure (Resources, Items, Categories) rather than a simple list of vectors. Acting as a central brain, it manages the digestion of raw data into structured facts and the retrieval of relevant context using a modular, pipeline-based workflow engine.

7
Chapters
-
Subsystems
Rabbit Holes
▶ Start Reading ⎇ View on GitHub
System Architecture

How the pieces fit

memU is organized as connected concepts and components. Start broad, then drill down chapter by chapter.

⚙️
Hierarchical Data Model (The Memory File System)
Hierarchical Data Model (The Memory File System)
⚙️
MemoryService (The Central Brain)
MemoryService (The Central Brain)
⚙️
Memorize Pipeline (The Digestion System)
Memorize Pipeline (The Digestion System)
⚙️
Retrieve Pipeline (The Recall System)
Retrieve Pipeline (The Recall System)
⚙️
Storage Layer (The Filing Cabinet)
Storage Layer (The Filing Cabinet)
⚙️
Workflow Pipeline Engine (The Assembly Line)
Workflow Pipeline Engine (The Assembly Line)
⚙️
LLM Client Wrapper (The Translator)
LLM Client Wrapper (The Translator)
memU — bash
open tutorial
◆ Scanning numbered chapters
◆ Building navigation and Mermaid diagrams
◆ Generating chapter and subsystem pages
✓ 7 chapter pages built
✓ Theme toggle enabled
Repository Overview

Intro and Architecture Diagram

memU is a framework that provides AI agents with long-term memory by organizing information into a hierarchical structure (Resources, Items, Categories) rather than a simple list of vectors. Acting as a central brain, it manages the digestion of raw data into structured facts and the retrieval of relevant context using a modular, pipeline-based workflow engine.

Source Repository: https://github.com/NevaMind-AI/memU

flowchart TD A0["MemoryService (The Central Brain)"] A1["Hierarchical Data Model (The Memory File System)"] A2["Memorize Pipeline (The Digestion System)"] A3["Retrieve Pipeline (The Recall System)"] A4["Workflow Pipeline Engine (The Assembly Line)"] A5["Storage Layer (The Filing Cabinet)"] A6["LLM Client Wrapper (The Translator)"] A0 -->|"Orchestrates execution via"| A4 A0 -->|"Runs ingestion workflow"| A2 A0 -->|"Runs retrieval workflow"| A3 A0 -->|"Initializes and configures"| A5 A0 -->|"Configures and wraps"| A6 A2 -->|"Calls for extraction"| A6 A3 -->|"Calls for ranking/reasoning"| A6 A2 -->|"Persists extracted data"| A5 A3 -->|"Queries stored data"| A5 A5 -->|"Stores and retrieves instan..."| A1
Tutorial Chapters

All 7 chapters

Follow sequentially or jump to any topic. Start with Hierarchical Data Model (The Memory File System).

About This Project

Generated by Code IQ

This tutorial was automatically generated by Code IQ and rendered with the shared tutorial site builder. It can be produced for any repository tutorial folder that follows the numbered markdown chapter layout.

View Code IQ ↗
python build_site.py '/home/runner/work/Code-IQ/Code-IQ/output/memU'

// → 7 chapters
// → source: NevaMind-AI/memU