Skip to content

Type to search titles, headings, and body text.

Graph Engineering

Build resilient systems that scale across agents

Graph Engineering transforms how distributed systems handle complexity. Instead of fragile file-based states, it uses resilient graph structures where multiple workers can coordinate safely.

86+
Pages
23+
Patterns
24+
Starter Kits
17
Learning Steps
Live Preview

See it in action

Watch Graph Engineering initialize a dual-agent memory system in real time — from project scaffolding to a fully built graph structure.

graph-lab build
graph-engineering build
initializing graph engineering environmentbuilding memory systems
src/graphs/
attempt.tsrecords all attempted operations
truth.tsholds verified facts
edges.tsconnects attempts to outcomes
lib/
reconcile.tsconsensus layer
traverse.tsgraph query engine
Memory Ready ████████████ Dual-agent capable
Graph Engineering initialized:
Build memory that more than one agent can trust.
complete · 5 files · multi-agent ready
Core Concept

Two graphs, one system

Graph Engineering separates what was attempted from what turned out to be true. Every agent reads the same verified facts — none of them replay each other's trial and error.

WORK HISTORYWhat was attemptedattempt1attempt2attempt3supersededsupersededlatest attemptreads factsFACTSWhat turned out to be trueentityServiceentityOwnerentityReceiptverified fact

Work History

Every attempt an agent makes is recorded in the work-history graph. Previous attempts are marked superseded — agents never act on stale work.

Verified Facts

The fact graph holds only what has been verified true. Every edge carries a receipt — agents can trust the data without re-verifying it themselves.

Work history records attempts. Facts record what is true. Agents read facts; they do not replay history.

How It Works

The lifecycle of a fact

A fact is not created all at once. It passes through three stages — each one adding confidence, context, and a verifiable trail. This is how raw input becomes structured, trustworthy knowledge.

Learning Path

Seventeen steps, seven parts

Master Graph Engineering through a carefully structured curriculum. Steps 1–13 build the foundation with queryable fact graphs and worker coordination. Steps 14–17 explore advanced patterns for scaling and optimization across distributed systems.

Patterns & Solutions

Core Patterns

Twenty-three battle-tested patterns covering extraction, resolution, provenance, governance, and storage. Each pattern addresses specific challenges in building reliable graph systems that scale across multiple agents.

Quick Start

Get Started

Follow four simple steps to begin your Graph Engineering journey. From initial setup to running your first starter kit, you'll have a working example in minutes.

1

Read Start here

Two or three questions about what you have already built, and it points you at the page to open first.

2

Pick a track

G1 through G4, beginner to expert. Each finishes where the next one assumes you are.

3

Install the core package

Get the foundation package that powers all Graph Engineering projects.

$ npm install @graph-engineering/core
4

Clone a starter kit

One command, no API keys, no build. Run this in your terminal:

$ npx @graph-engineering-kits/graph-kit document-to-facts
View all starter kits
graph-lab

Learn to build memory systems that scale across multiple agents using Graph Engineering.

Install

$ npm install @graph-engineering/core

Maintainers

Ayesha Khalid

Creator & Maintainer

Saram Ali

Graph Engineering Co-Author

© 2026 Graph Engineering. MIT licensed.

af5321e3synced 2026-08-08