Awesome Graph Engineering · Guía abierta

Diseña la organización, no solo el agente.

Una guía seleccionada para diseñar organizaciones de agentes de IA como grafos programables: roles, topologías, traspasos, grafos de trabajo, verificación, fiabilidad y observabilidad.

Explorar el atlas Ver en GitHub

Aquí, los nodos del grafo son agentes de IA, no entidades de datos. ¿Buscas bases de datos de grafos, GNN, grafos de conocimiento o GraphRAG? Consulta la guía de límites.

A graph of specialized AI agents connected by explicit handoffs and an evidence gate.

Focus the graph, then use arrow keys to orbit, plus or minus to zoom, and zero to reset. Hold Alt while scrolling to zoom without trapping normal page scrolling.

Working definition · emerging practice

Graph engineering en 30 segundos

Graph engineering es la práctica de especificar, ejecutar, observar y evolucionar un sistema de agentes estructurado como grafo: sus roles e instancias de ejecución, los contratos que los conectan, el estado y los artefactos compartidos y la evidencia con la que se juzga su comportamiento colectivo. Un sistema que califica ejecuta al menos dos instancias de agentes responsables por separado; pueden compartir rol o modelo. Cada agente puede contener un bucle local; las pruebas, auditorías, decisiones humanas y anclajes al mundo real pueden actuar como controles no agentes. El grafo debe condicionar materialmente la ejecución y seguir siendo inspeccionable.

  1. 01

    Node

    A bounded role specification or an accountable agentic runtime instance; only runtime instances satisfy plural agency.

  2. 02

    Edge

    A designed dependency: what crosses, in what shape, under which condition.

  3. 03

    Org graph

    The stable topology of roles, ownership, and standing relationships.

  4. 04

    Work graph

    The task-specific structure created, routed, and revised for one objective.

  5. 05

    Gate

    An independent test, audit, human decision, or real-world anchor that controls an edge.

El término es emergente y polisémico, por lo que el alcance se limita a una capa práctica de ingeniería presente en la orquestación de agentes, los sistemas multiagente y los flujos de trabajo duraderos; no es un estándar industrial.

Leer la definición y el alcance completos

The core model

Two graphs. One system.

A stable organization of agents executes ephemeral work. These are complementary analytical views—not proposed universal standards or necessarily separate runtime objects.

Drag or use arrows · Alt-scroll or +/− to zoom
Switch between a stable organization graph and an ephemeral work graph.

Use the Org graph and Work graph buttons to change the model. Focus the graph, then use arrow keys to orbit, plus or minus to zoom, and zero to reset.

Agent persistent role Edge contract explicit handoff Evidence gate quality or policy check

A practical taxonomy

Nine layers from roles to evolution

Start with roles, topology, and handoffs. Add state, gates, and operations only as real failure modes earn the complexity.

Before you add a second agent

Does this job need a graph?

Graphs add coordination cost, latency, and new failure modes. They earn that overhead only when at least one condition is real.

  1. 01

    Parallelism

    Can meaningful work proceed concurrently without constant coordination?

  2. 02

    Isolation

    Must contexts, permissions, or failure domains remain separated?

  3. 03

    Specialization

    Do distinct skills, tools, models, or durable contexts pay for separate roles?

  4. 04

    Verification

    Must a producer’s output pass an independent evidence gate before it advances?

None applyBuild a better loop.

Keep the free context-sharing and lower coordination cost of one agent.

One or more applyDesign the smallest graph that earns its overhead.

Start minimal, define the edges, and require evidence before you evolve.

Guided entry points

Start where you are

Choose the question closest to the one blocking you now.

Explorar el modelo interactivo
01Loop builderI have one agent that works. Now what?

Decide whether a second role earns its place and draw the first edge.

 02ArchitectWhich topology and framework?

Match the shape of the graph to the shape of the task.

 03OperatorMake the graph survivable.

Design retries, evidence gates, budgets, tracing, and escalation.

 04ResearcherWhat does the evidence say?

Read the foundations, benchmarks, topology studies, and critiques.

Searchable resource directory

The graph engineering atlas

Search the field by design layer, resource type, and source/evidence label. Every result maps back to the README and open dataset.

Loading resources…

    Open data

    Use the field guide as data.

    Every resource ships as CSV and JSONL, mapped to a design layer and checked against the README.

    Download CSV Download JSONL View JSON Schema Explore on Hugging Face
    Python
    import pandas as pd

url = "https://raw.githubusercontent.com/ChaoYue0307/awesome-graph-engineering/main/data/resources.csv"
resources = pd.read_csv(url)

resources.query("layer == 'Gates'").head()
    Schemalayer stringrtype stringvenue stringyear integerdescription stringevidence string

    Licencia

    Los metadatos, el esquema, los resúmenes, la documentación, el código y los recursos visuales creados para este repositorio se dedican al dominio público bajo CC0 1.0 Universal.

    Los artículos, el software, los nombres, los logotipos y demás materiales de terceros enlazados conservan sus propios derechos y licencias. CC0 no implica la renuncia a derechos de marca o patente y la obra se ofrece sin garantías. Se agradece la cita por trazabilidad académica, pero CC0 no la exige.

    Leer la licencia completa