Xpersona

Crawler Summary

a2a-multi-framework-agent-graph-engineering answer-first brief

A reproducible multi-framework agent graph connecting Google ADK, LangGraph, and CrewAI through the A2A protocol. Graph Engineering con ADK + LangGraph + CrewAI (Google A2A) Prueba de concepto de un **grafo de agentes interoperables** ejecutándose en **contenedores separados**, donde: - **ADK orquesta** el flujo, el estado y el ciclo de validación. - **A2A es el contrato** de comunicación entre agentes de frameworks distintos. - Cada framework (**CrewAI**, **LangGraph**, **ADK**) es una unidad independiente. Precisión conceptual Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.

Freshness

Last checked 10/9/2026

Best For

a2a-multi-framework-agent-graph-engineering is best for crewai, multi-agent workflows where OpenClaw compatibility matters.

Not Ideal For

Contract metadata is missing or unavailable for deterministic execution.

Evidence Sources Checked

editorial-content, GITHUB REPOS, runtime-metrics, public facts pack

CardFactsSnapshotContractTrust
Agent DossierGITHUB REPOSSafety: 66/100

a2a-multi-framework-agent-graph-engineering

A reproducible multi-framework agent graph connecting Google ADK, LangGraph, and CrewAI through the A2A protocol. Graph Engineering con ADK + LangGraph + CrewAI (Google A2A) Prueba de concepto de un **grafo de agentes interoperables** ejecutándose en **contenedores separados**, donde: - **ADK orquesta** el flujo, el estado y el ciclo de validación. - **A2A es el contrato** de comunicación entre agentes de frameworks distintos. - Cada framework (**CrewAI**, **LangGraph**, **ADK**) es una unidad independiente. Precisión conceptual

OpenClawself-declared

Public facts

4

Change events

1

Artifacts

0

Freshness

Oct 9, 2026

Verifiededitorial-contentNo verified compatibility signals

Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.

Trust evidence available

Trust score

Unknown

Compatibility

OpenClaw

Freshness

Oct 9, 2026

Vendor

Dyronrh

Artifacts

0

Benchmarks

0

Last release

Unpublished

Executive Summary

Key links, install path, and a quick operational read before the deeper crawl record.

Verifiededitorial-content

Summary

Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.

View Source

Setup snapshot

  1. 1

    Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.

  2. 2

    Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence Ledger

Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.

Verifiededitorial-content
Vendor (1)

Vendor

Dyronrh

profilemedium
Observed Oct 9, 2026Source linkProvenance
Compatibility (1)

Protocol compatibility

OpenClaw

contractmedium
Observed Oct 9, 2026Source linkProvenance
Security (1)

Handshake status

UNKNOWN

trustmedium
Observed unknownSource linkProvenance
Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium
Observed Apr 15, 2026Source linkProvenance

Release & Crawl Timeline

Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.

Self-declaredagent-index

Docs Update

Docs refreshed: Sign in to GitHub · GitHub

search_documentmedium

Fresh crawlable documentation was indexed for the official domain.

Observed Apr 15, 2026

Artifacts Archive

Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.

Self-declaredGITHUB REPOS

Extracted files

0

Examples

6

Snippets

0

Languages

python

Executable Examples

text

user ─▶ graph_manager  (LlmAgent, ADK)
             │  decide la delegación (tool-calling)
             ├─▶ research_agent     → CrewAI     (:8001, RemoteA2aAgent)
             ├─▶ engineering_agent  → LangGraph  (:8002, RemoteA2aAgent) ◀─┐
             └─▶ validator_agent    → ADK BaseAgent (determinista)         │
                        │ REJECTED ──────────────────────────────────────┘
                        │ APPROVED ─▶ resultado final

bash

./run_local.sh

bash

cp .env.example .env      # MOCK_LLM=1 por defecto; para real pon tu clave
docker compose up --build

bash

curl http://localhost:8001/.well-known/agent-card.json

bash

curl http://localhost:8002/.well-known/agent-card.json

bash

curl http://localhost:8001/.well-known/agent-card.json
curl http://localhost:8002/.well-known/agent-card.json

Docs & README

Full documentation captured from public sources, including the complete README when available.

Self-declaredGITHUB REPOS

Docs source

GITHUB REPOS

Editorial quality

ready

A reproducible multi-framework agent graph connecting Google ADK, LangGraph, and CrewAI through the A2A protocol. Graph Engineering con ADK + LangGraph + CrewAI (Google A2A) Prueba de concepto de un **grafo de agentes interoperables** ejecutándose en **contenedores separados**, donde: - **ADK orquesta** el flujo, el estado y el ciclo de validación. - **A2A es el contrato** de comunicación entre agentes de frameworks distintos. - Cada framework (**CrewAI**, **LangGraph**, **ADK**) es una unidad independiente. Precisión conceptual

Full README

Graph Engineering con ADK + LangGraph + CrewAI (Google A2A)

Prueba de concepto de un grafo de agentes interoperables ejecutándose en contenedores separados, donde:

  • ADK orquesta el flujo, el estado y el ciclo de validación.
  • A2A es el contrato de comunicación entre agentes de frameworks distintos.
  • Cada framework (CrewAI, LangGraph, ADK) es una unidad independiente.

Precisión conceptual clave: A2A no orquesta. A2A estandariza cómo un agente publica capacidades, recibe una tarea y devuelve un entregable. Las rutas, ciclos, reintentos y validaciones son responsabilidad del orquestador (ADK) y del diseño del grafo.

Caso de uso

"Genera y valida una configuración de despliegue para un servicio web."

El manager es un LlmAgent coordinador de ADK (un graph agent): razona y decide a qué agente delegar usando a los demás como herramientas (AgentTool). No es un pipeline fijo: el propio agente conduce el grafo y su ciclo de validación.

user ─▶ graph_manager  (LlmAgent, ADK)
             │  decide la delegación (tool-calling)
             ├─▶ research_agent     → CrewAI     (:8001, RemoteA2aAgent)
             ├─▶ engineering_agent  → LangGraph  (:8002, RemoteA2aAgent) ◀─┐
             └─▶ validator_agent    → ADK BaseAgent (determinista)         │
                        │ REJECTED ──────────────────────────────────────┘
                        │ APPROVED ─▶ resultado final

Flujo real observado (traza de run.py):

  1. El coordinador delega en research_agent (CrewAI) → briefing con requisitos.
  2. Delega en engineering_agent (LangGraph) → primer Dockerfile incompleto.
  3. Delega en validator_agent (ADK) → REJECTED (falta usuario no root + healthcheck).
  4. El coordinador vuelve a delegar en engineering_agent con el feedback → Dockerfile endurecido.
  5. validator_agent → APPROVED; el coordinador devuelve el resultado final.

Cada delegación a un agente remoto es una interacción A2A. El manager nunca importa CrewAI ni LangGraph: solo conoce las Agent Cards y habla A2A vía RemoteA2aAgent.

Modos de ejecución

El orquestador es siempre un LlmAgent de ADK; solo cambia el "cerebro":

  • Mock (por defecto): sin claves ni costo. Un modelo determinista (BaseLlm) conduce la misma política del grafo vía tool-calling — el graph agent se ejecuta y demuestra de verdad sin API key.
  • Real: define ANTHROPIC_API_KEY (o GOOGLE_API_KEY) y MOCK_LLM=0. Un LLM real razona el ruteo siguiendo la instrucción del coordinador. El modelo se configura con MANAGER_MODEL (por defecto anthropic/claude-sonnet-5).

Ejecutar

Opción A — Local, sin Docker (demo rápida)

./run_local.sh

Crea un venv, levanta los dos servidores A2A, ejecuta el grafo y limpia al salir.

Opción B — Docker Compose (tres contenedores separados)

cp .env.example .env      # MOCK_LLM=1 por defecto; para real pon tu clave
docker compose up --build

Verifica el descubrimiento (Agent Cards) en cualquier momento:

curl http://localhost:8001/.well-known/agent-card.json
curl http://localhost:8002/.well-known/agent-card.json

Estructura

research_crewai/        agente CrewAI envuelto en A2A (skill: research_technical_sources)
  crew.py               lógica CrewAI (real) / briefing determinista (mock)
  executor.py           adaptador AgentExecutor A2A
  server.py             servidor A2A (:8001)
engineering_langgraph/  agente LangGraph envuelto en A2A (skill: generate_infrastructure_code)
  graph.py              grafo LangGraph con auto-revisión (real) / plantilla (mock)
  executor.py           adaptador AgentExecutor A2A
  server.py             servidor A2A (:8002)
manager_adk/            orquestador ADK
  agent.py              LlmAgent coordinador + AgentTool(RemoteA2aAgent x2 + validador)
  coordinator_model.py  modelo determinista (mock) / selección de LLM real
  validator.py          BaseAgent ADK determinista (aplica reglas, APPROVED/REJECTED)
  run.py                ejecuta el grafo con InMemoryRunner y traza cada delegación
docker-compose.yml      los tres servicios como contenedores independientes
run_local.sh            demo local sin Docker

Versiones (verificadas)

  • a2a-sdk==0.3.26 (servidores A2A: A2AStarletteApplication)
  • google-adk[a2a]==1.10.0 (manager: LlmAgent, RemoteA2aAgent, AgentTool)
  • litellm (solo modo real con proveedores no-Gemini, p. ej. Claude)
  • Agent Card en /.well-known/agent-card.json

RemoteA2aAgent es una API marcada como experimental en ADK 1.10.0; puede cambiar entre versiones. Los imports se fijaron a esta combinación por eso.

El costo del desacoplamiento (para producción)

  • Autenticación entre servicios · Observabilidad por Task/interacción · Versionado de Agent Cards · Timeouts/reintentos/circuit breakers · Persistencia de estado (sustituir los InMemory*).

A2A no elimina esa complejidad; da un contrato común para administrarla.

Contract & API

Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.

MissingGITHUB REPOS

Endpoints

Dossier APISnapshot APIContract APITrust API

Contract coverage

Status

missing

Auth

None

Streaming

No

Data region

Unspecified

Protocol support

OpenClaw: self-declared

Requires: none

Forbidden: none

Guardrails

Operational confidence: low

No positive guardrails captured.
Invocation examples
curl -s "https://www.xpersona.co/api/v1/agents/crewai-dyronrh-a2a-multi-framework-agent-graph-engineering/snapshot"
curl -s "https://www.xpersona.co/api/v1/agents/crewai-dyronrh-a2a-multi-framework-agent-graph-engineering/contract"
curl -s "https://www.xpersona.co/api/v1/agents/crewai-dyronrh-a2a-multi-framework-agent-graph-engineering/trust"

Reliability & Benchmarks

Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.

Missingruntime-metrics

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

Do not use if

Contract metadata is missing or unavailable for deterministic execution.
No benchmark suites or observed failure patterns are available.

Media & Demo

Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.

Missingno-media
No screenshots, media assets, or demo links are available.

Related Agents

Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.

Self-declaredprotocol-neighbors
Github ReposUpdated 5h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW
Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW
Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW
Agent hubMore from this sourceOpenClaw agents
Machine Appendix

Contract JSON

{
  "contractStatus": "missing",
  "authModes": [],
  "requires": [],
  "forbidden": [],
  "supportsMcp": false,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": null,
  "outputSchemaRef": null,
  "dataRegion": null,
  "contractUpdatedAt": null,
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://www.xpersona.co/api/v1/agents/crewai-dyronrh-a2a-multi-framework-agent-graph-engineering/snapshot",
    "contractUrl": "https://www.xpersona.co/api/v1/agents/crewai-dyronrh-a2a-multi-framework-agent-graph-engineering/contract",
    "trustUrl": "https://www.xpersona.co/api/v1/agents/crewai-dyronrh-a2a-multi-framework-agent-graph-engineering/trust"
  },
  "curlExamples": [
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-dyronrh-a2a-multi-framework-agent-graph-engineering/snapshot\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-dyronrh-a2a-multi-framework-agent-graph-engineering/contract\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-dyronrh-a2a-multi-framework-agent-graph-engineering/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_REPOS",
      "generatedAt": "2026-10-09T23:49:07.994Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "OPENCLEW",
      "type": "protocol",
      "support": "unknown",
      "confidenceSource": "profile",
      "notes": "Listed on profile"
    },
    {
      "key": "crewai",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "multi-agent",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    }
  ],
  "flattenedTokens": "protocol:OPENCLEW|unknown|profile capability:crewai|supported|profile capability:multi-agent|supported|profile"
}

Facts JSON

[
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Dyronrh",
    "href": "https://github.com/dyronrh/a2a-multi-framework-agent-graph-engineering",
    "sourceUrl": "https://github.com/dyronrh/a2a-multi-framework-agent-graph-engineering",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-10-09T15:16:45.564Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://www.xpersona.co/api/v1/agents/crewai-dyronrh-a2a-multi-framework-agent-graph-engineering/contract",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-dyronrh-a2a-multi-framework-agent-graph-engineering/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-10-09T15:16:45.564Z",
    "isPublic": true
  },
  {
    "factKey": "docs_crawl",
    "category": "integration",
    "label": "Crawlable docs",
    "value": "6 indexed pages on the official domain",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://www.xpersona.co/api/v1/agents/crewai-dyronrh-a2a-multi-framework-agent-graph-engineering/trust",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-dyronrh-a2a-multi-framework-agent-graph-engineering/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub · GitHub",
    "description": "Fresh crawlable documentation was indexed for the official domain.",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  }
]

Sponsored

Ads related to a2a-multi-framework-agent-graph-engineering and adjacent AI workflows.