Google ADK (Python)

Google’s Agent Development Kit. Build agents on Gemini (and any LLM via google-genai / LiteLlm) with graph-based Workflow orchestration, MCP client + server, A2A protocol, and native GCP services (Vertex AI, Cloud Run, Agent Engine).

Install

pip install google-adk --pre

Version

v2.0.0b1 · April 2026 · Python 3.10+

Best for

GCP-native workloads, Gemini-first agents, Vertex AI Agent Engine.

Zero → Hero

1 · Introduction What ADK is, why Google built it · 10 min

2 · Core fundamentals Install, auth, first agent · 25 min

3 · Agents LlmAgent, Parallel, Loop, Sequential · 25 min

4 · Workflows Graph orchestration with @node · 30 min

5 · Tools FunctionTool, AgentTool, built-ins · 30 min

6 · Callbacks & plugins Interception points · 20 min

7 · Runner & sessions App, Runner, session services · 25 min

8 · Memory & artifacts Long-term memory + file storage · 20 min

9 · MCP & A2A Tool servers + agent handoff · 20 min

10 · Structured output Pydantic validation · 15 min

11 · Advanced Python Complex patterns, customisation · 30 min

12 · IAM & security IAM roles, workload identity · 20 min

13 · Production Deployment, scaling, monitoring · 30 min

Jump to a topic

LlmAgent

Workflow graphs

Tools & built-ins

Callbacks & plugins

Runner & sessions

Memory & artifacts

MCP & A2A

IAM examples

Advanced Python

Reference

Agents LlmAgent, Parallel, Loop, Sequential (deprecated).

Workflows Workflow, @node, Edge, JoinNode.

Tools FunctionTool, AgentTool, Gemini built-ins, MCP.

Callbacks & plugins All 11 plugin hooks + agent callbacks.

Runner & sessions Runner, App, session services, RunConfig.

Memory & artifacts MemoryService + ArtifactService implementations.

MCP & A2A McpToolset, RemoteA2aAgent, to_a2a().

Comprehensive guide Single-page technical reference.

Advanced Python

IAM examples

Recipes

Diagrams

Production guide

What’s new in v2.0 (April 2026)

Workflow graph orchestration — SequentialAgent / ParallelAgent / LoopAgent are now @deprecated in favour of Workflow with edges, routing maps, and @node.
Plugins — runner-wide interception via BasePlugin with 11 hooks. GlobalInstructionPlugin replaces the deprecated LlmAgent.global_instruction.
MCP client + server — full MCP support including sampling, resources, and auth schemes.
A2A protocol — to_a2a(agent) to publish; RemoteA2aAgent to consume.
Vertex AI Memory Bank + RAG — VertexAiMemoryBankService, VertexAiRagMemoryService.
Built-in code executors — BuiltInCodeExecutor, VertexAiCodeExecutor, ContainerCodeExecutor, GkeCodeExecutor, AgentEngineSandboxCodeExecutor.

Install, minimal example

import asyncio
from google.adk.agents import LlmAgent
from google.adk.runners import InMemoryRunner

agent = LlmAgent(
    name="assistant",
    model="gemini-2.5-flash",
    instruction="You are a helpful assistant.",
)

async def main():
    runner = InMemoryRunner(agent=agent, app_name="demo")
    await runner.session_service.create_session(app_name="demo", user_id="u1", session_id="s1")
    events = await runner.run_debug("What is 15 + 27?", user_id="u1", session_id="s1")
    print(events[-1].content.parts[0].text)

asyncio.run(main())

Ready? Start Zero → Hero Step 1 →

Revision history

Date	Framework version (installed)	Summary of changes	Reviewer
2026-04-22	google-adk 2.0.0b1	Added 7 topic pages: Agents, Workflows, Tools, Callbacks & Plugins, Runner & Sessions, Memory & Artifacts, MCP & A2A. Verified against installed source. Fixed errata in Advanced Python quickstart. Index rewired with new Zero → Hero and Reference grid.	Claude routine
2026-04-21	google-adk 1.31.0	Index redesigned with Zero → Hero + Jump-to-topic grid.	—
April 17, 2026	google-adk 1.31.0	A2A; MCP; expanded tools; Workload Identity.	—
November 2025	google-adk 1.18.0	Initial documented version.	—

Note: Other languages: Go · TypeScript.