Core · AI System Designsenior

Long-Term Memory System

Components

Drag onto the canvas, or click to add.Tap to add to the canvas.

Utilities

Text Box

Group / Container

Circle

Diamond

Divider Line

Heading

Recommended

Client / User

Agent Loop

LLM / Model

Embedding Model

Vector Store

Working Memory

Long-Term Memory

PII Filter / Redactor

Entry & gateway

Client / User

LLM Gateway

API Gateway

Orchestration

Orchestrator / Planner

Agent / Worker

Agent Loop

Models

LLM / Model

Model Router

Embedding Model

STT / TTS

Retrieval / RAG

Retriever

Reranker

Vector Store

Knowledge Source

Tools & execution

Tool / Function

MCP Server

Code Sandbox

Browser / Computer Env

External API

Memory & state

Working Memory

Long-Term Memory

Cache (semantic/prompt)

Safety & eval

Guardrail / Classifier

PII Filter / Redactor

Eval / Judge

Observability / Tracing

Infra & data

Database / State

Queue / Event Bus

Human

Human-in-the-Loop

Drag or click a component on the leftTap Components to add your first piece

connect · iterate · submit for review

// brief

Long-Term Memory System

Give an agent persistent memory across sessions — deciding what to remember, keeping it consistent, and forgetting.

Key Requirements

01Salience: extract durable facts, do not store every turn
02Memory typing (episodic/semantic) and relevance-triggered recall
03Update vs append — overwrite changed preferences, avoid contradictions
04Consolidation/decay to bound growth; privacy & deletion
05Defense against memory poisoning

Rubric must-haves

0/2

Has a long-term memory store
Has a model step that extracts what to remember

These checks are the structure score, 30% of your total. They update as you draw.

Practise it like the real round

45-minute timer paced through requirements, design and deep dive. The follow-up questions stay hidden until the last phase, and solution hints are off.

AI Review

0/5

Review me as:

Build your design, then submit for an AI-powered review with dimension scores, strengths, gaps, and actionable suggestions.

Try designing your solution first before viewing hints.

Comments (0)

Loading comments...