adk-python/docs/guides at main · google/adk-python

GitHub

ADK Developer Guides

This directory contains specific developer guides for the ADK Python implementation. For the official ADK documentation, visit

adk.dev

.

Index

Agents

Creating Agents with Configurations

- Building and wiring multi-agent graphs from external YAML configuration files.

LlmAgent Single-Turn Mode

- Guide on using LlmAgent in single-turn mode.

LlmAgent Task Mode

- Guide on using LlmAgent in task mode.

ManagedAgent

- Guide on using ManagedAgent with server-side tools.

RemoteA2aAgent Task Mode

- Guide on using RemoteA2aAgent in task mode.

Apps

App

- The top-level container binding a root agent to app-wide plugins and configuration.

Artifacts

BaseArtifactService

- Storing binary payloads outside the conversation history, with versioning and user-scoped filenames.

Auth

AuthConfig and authenticated tools

- Declaring the credentials a tool needs, and the pause-for-consent handshake.

Code Executors

BaseCodeExecutor

- Executing model-generated code safely across local, container, GKE, and managed sandbox backends.

Events

Event and NodeInfo

- Understanding Event and NodeInfo in workflows.

RequestInput

- How to use RequestInput for human-in-the-loop interactions.

Flows

Live model callbacks

- Inspecting or blocking content on a live bidirectional session.

Integrations

Model Armor

- Screening user input and model output with Google Cloud Model Armor.

Labs

AntigravityAgent

- Runs a Google Antigravity SDK agent as an ADK agent node.

Live

LiveRequestQueue

- Streaming content, realtime audio, and stream control signals to live agents.

Memory

BaseMemoryService

- Storing finished sessions and recalling them from later conversations.

Models

BaseLlm and LLMRegistry

- The model interface, how a model name resolves to an implementation, and how to plug in your own.

Planners

BasePlanner

- Guiding model execution with structured planning instructions, thinking configurations, and Plan-Re-Act thought tagging.

Plugins

ReflectAndRetryModelPlugin

- Self-healing, concurrent-safe error recovery for model failures.

ReflectAndRetryToolPlugin

- Self-healing, concurrent-safe error recovery for tool failures.

Runners

Runner and InMemoryRunner

- Managing session lifecycles, state resolution, and streaming agent execution events.

Runner Live Streaming

- Real-time bidirectional audio/text streaming and non-blocking background tool execution with Gemini Multimodal Live API.

Sessions

Session and BaseSessionService

- The session lifecycle, state scoping, and choosing a session service.

State

- Session state and the app:, user:, and temp: prefixes that decide what is shared and what is stored.

Tools

Node as tool

- Exposing workflows and deterministic nodes as agent tools with isolated runtime branching and resume support.

to_mcp_server

- Expose an ADK agent as an MCP server so any MCP host can drive it as a single tool (the MCP counterpart of to_a2a).

Workflows

Workflow

- Graph-based orchestration of complex, multi-step agent interactions.

Workflow Graphs

- Understanding nodes, edges, and graph structures in workflows.

Function Nodes

- Wrapping Python functions and generators as workflow nodes.

JoinNode

- Synchronizing parallel execution paths in workflows.

RetryConfig

- Configuring retry policies for resilient workflow nodes.

ParallelWorker

- Processing lists of items concurrently in workflows.

Dynamic Nodes

- Scheduling and executing nodes dynamically at runtime.