user@adk ~ $

Build agents in code, not config

Open-source Python framework. Define, test, debug, and deploy AI agents — with tools that actually work.

// install

python$ pip install google-adk
javacom.google.adk:google-adk
typescript$ npm install @google/adk
go$ go get google.golang.org/adk

// 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...

from google.adk import Agent
from google.adk.tools import google_search

agent = Agent(
  name="weather",
  model="gemini-2.5-flash",
  tools=[google_search],
)

Agent created with tool bindings

Any Model

Gemini, GPT, Claude, or open models. Run on your laptop, Cloud Run, or your own infra.

5 Lines → Production

Start with a single agent. Evolve into multi-agent graphs with deterministic control flow when you need it.

ADK 2.0 — Graphs + Code

Graph-based agents combine AI reasoning with deterministic logic. Mix LLM calls with regular code for workflows you can trust.

// dev ui

ADK Dev 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.