[ ABORT TO HUD ]
SEQ. 1
SEQ. 2
SEQ. 3
SEQ. 4
SEQ. 5

Google ADK Framework

🌐 A2A Protocol & Google ADK12 min110 BASE XP⌨ HANDS-ON LAB

The Agent Development Kit (ADK 2.0)

Google ADK (Agent Development Kit) 2.0 went GA on May 19, 2026 at Google I/O. It is an open-source framework for building, orchestrating, and deploying AI agents. ADK 2.0 now supports Python, TypeScript, Go, Java, and Kotlin (including Android/Gemini Nano support for on-device agents).

ADK 2.0 vs Other Frameworks

FeatureGoogle ADK 2.0LangGraphCrewAI
LanguagesPython, TS, Go, Java, KotlinPython, JSPython
Agent DefinitionCode, YAML, or Graph BuilderPython graphsPython classes
Workflow Runtime✅ Graph-based (routing, branching, loops, fan-out/fan-in)✅ Graph-basedSequential/hierarchical
Visual Builder✅ Drag-and-drop UI
A2A Support✅ Native
MCP Support✅ NativeVia pluginsVia plugins
DeploymentLocal CLI/Web UI → Cloud Run, GKE, Vertex AI, or custom infraLangServeDocker
ObservabilityOpenTelemetry nativeLangSmithCustom

What's New in ADK 2.0

  • Graph-based Workflow Runtime: First-class support for routing, branching, iterative loops, fan-out/fan-in, and native human-in-the-loop (HITL) - bringing LangGraph-level graph control into ADK.
  • Agent-as-a-Tool: Coordinator agents delegate sub-tasks to specialized subagents using them as callable tools - enabling deep hierarchical architectures.
  • Multi-Language SDK: Python, TypeScript, Go, Java, and Kotlin (with Gemini Nano on-device support for Android).
  • Enhanced State & Memory: Session persistence via Vertex AI and Firestore, with Session Rewind for time-travel debugging.
  • Visual Agent Builder: Drag-and-drop UI for composing agent hierarchies and testing in real-time.
  • Flexible Deployment: From local CLI/Web UI for development to Cloud Run, GKE, or custom infrastructure for production.
  • Code Execution Sandbox: Safely execute agent-generated code via Vertex AI sandbox.
  • Multi-Provider Models: Use Gemini, Claude, or GPT as the reasoning engine.

Bidirectional MCP & Self-Healing (v2.5–2.6, July 2026)

As of v2.5.0 (July 16, 2026), ADK agents are no longer just MCP clients - the new to_mcp_server() helper serves any ADK agent as an MCP server, so other MCP-compatible hosts (Claude Desktop, other ADK agents, custom clients) can call it like any other tool server. v2.6.0 (July 29, 2026) added ReflectAndRetryModelPlugin, which lets an agent automatically reflect on and retry a failed model call. ADK is now at v2.6.2 (August 2026) and iterating fast on production reliability.

ADK Agent Definition (Python)

from google.adk import Agent, Tool

# Define tools
search_tool = Tool(
    name="search_knowledge_base",
    description="Search internal docs",
    function=search_kb_function
)

# Create agent
agent = Agent(
    name="support_agent",
    model="gemini-3.5-flash",
    tools=[search_tool],
    instruction="You are a helpful support agent...",
    sub_agents=[billing_agent, shipping_agent]  # Hierarchy!
)

# Run
response = agent.run("What is the refund policy?")
💡 Key Insight: ADK 2.0's unique strength is the combination of a graph-based workflow runtime with native A2A + MCP support. It's the only framework with first-class graph orchestration, Agent-as-a-Tool delegation, AND cross-vendor A2A interoperability out of the box.
⌨ HANDS-ON LABScaffold & Chat with an ADK Agent
⭐ +150 XP

Google's Agent Development Kit ships a full CLI. Install it, generate an agent project, and talk to your agent from the terminal.

1Install the Google ADK package from PyPI.
2Scaffold a new agent project named my_agent.
3Start an interactive terminal chat with your agent.
lab-sandbox — simulated environment
INFINITY LAB SANDBOX v2.6 — simulated shell
Type the command for the current objective. Helpers: "hint", "solution", "clear".
$
OBJECTIVE 1 / 3 — type "hint" if stuck
SYNAPSE VERIFICATION
QUERY 1 // 4
What makes Google ADK unique among agent frameworks?
It only works with Gemini
Native support for both MCP (tools) and A2A (agent-to-agent), plus a visual builder
It's the cheapest
It requires no code