Build agents in code, not config

Open-source Python framework for AI agents. Define, test, debug, and deploy — from prototype to production.

Developer Tools

Your coding agent already knows ADK

ADK ships as a Skill and MCP server — coding agents like Claude Code and Gemini CLI can scaffold, extend, and test your agents automatically.

          
$ claude "Build me a weather agent with ADK"
⠋ Using ADK skill + MCP server...

fromgoogle.adkimport Agent
fromgoogle.adk.toolsimport google_search

agent = Agent(

          name="weather",

          model="gemini-2.5-flash",

          tools=[google_search],

        )

✓Agent created with tool bindings

Open Source

Any Model, Your Infra

Use Gemini, GPT, Claude, or open models. Run anywhere — your laptop, Cloud Run, or your own infrastructure.

Example

from google.adk \
  import Agent

agent = Agent(
  name="assistant",
  model="gemini-2.0-flash",
  instruction="You are a helpful assistant.",
  tools=[search, code_exec],
)

Progression

Single Agent

Multi-Agent

Graph Workflows

ADK 2.0

Graphs + Code

Graph-based agents combine AI reasoning with deterministic logic for workflows you can actually trust.

Install

Python

pip install google-adk

Java

com.google.adk:google-adk

TypeScript

npm install @google/adk

Go

go get google.golang.org/adk

Dev UI

Built-in Web UI

Interactive web UI for testing, debugging, and tracing your agents. See every tool call, inspect state, and iterate fast.

Eval

Go beyond vibes

ADK's eval framework tests both the final response AND the agent's trajectory — the steps it took to get there.