Skip to content
The Agents Index
Sign inSubmit an agent

Google Agent Development Kit (ADK)

Open-source framework for building, evaluating and deploying AI agents in Python, TypeScript, Go, Java or Kotlin.

Google's Agent Development Kit is a framework for building agents and multi-agent systems, published as libraries for Python, TypeScript, Go, Java and Kotlin. It bundles the runtime, a local developer UI, an evaluation harness and deployment commands that carry an agent from script to production.

Best for
Teams that want Google's own official, actively-developed agent SDK, especially polyglot teams (Python/Go/Java/TypeScript/Kotlin) or anyone building multi-agent systems that need to interoperate across vendors via the A2A protocol.
Not for
Teams with no Google Cloud/Gemini affinity who want the single largest third-party integration ecosystem and the longest production track record. LangChain still carries more years of battle-testing and a much larger community today.

What we checked

Pages last read
Facts checked
30 factsFrom 34 sources, read 15 September 2026
AI answers
Named in 0 of 150Our October check

How we checkEditorial policy

Visit the site CompareAlternatives

Google Agent Development Kit (ADK) in our research

All research

Study

AI Agent Pricing Index, October 2026

Pricing

Free only

17 of the 149 agents we checked are free with no paid plan.

Price checked 15 September 2026.

What we checked on Google Agent Development Kit (ADK)

YesPartlyNo

What it doesPartly

Writes code

ADK does not write application code for you, but its Visual Builder inside the local web UI generates agent projects from a graphical design with an AI assistant, and the vendor marks that builder experimental and Python-only.

The Visual Builder allows you to design, build, and test agents in a beginner-friendly graphical interface, and includes an AI-powered assistant to…

adk.dev/visual-builderChecked

What it doesPartly

Debugs and fixes

The bundled web UI and event/trace inspection let a developer diagnose why an agent failed, but landing the code fix is left to the developer or to a separate AI coding tool; ADK ships no repair agent.

The ADK web interface lets you test your agents directly in the browser. This tool provides a simple way to interactively develop and debug your…

adk.dev/runtime/web-interfaceChecked

What it doesPartly

Writes tests

What it generates are agent evaluation sets captured from real sessions, not unit tests; the evaluation tooling is documented as Python-only, so other language bindings do not get it.

Creating evalsets manually can be complex, therefore UI tools are provided to help capture relevant sessions and easily convert them into evals…

adk.dev/evaluateChecked

What it doesPartly

Reviews code

Review is not a built-in behaviour: you assemble an agent with the documented GitHub MCP toolset and your own access token, and the vendor frames reviewing changes as something the AI can help with.

Issue & PR Automation: Create, update, and manage issues and pull requests. Let AI help triage bugs, review code changes, and maintain project boards.

adk.dev/integrations/githubChecked

What it doesPartly

Whole-codebase work

The documented route across an existing repository is Agents CLI skills driving your own coding agent through an incremental migration; ADK itself carries no repository-wide refactor engine.

Instead of manually rewriting state objects, node graphs, and execution loops line by line, you can use Agents CLI to plan and execute the migration…

adk.dev/get-started/migrateChecked

What it doesYes

Ships it

Deployment is part of the framework: one command pushes an agent to Google Cloud, and the same agent can be containerised and run on infrastructure you control instead.

You can containerize and run ADK on your own infrastructure, or take advantage of our native, one-command deployment to Google Cloud.

adk.devChecked

What it doesNo

Done-for-you service

Nobody builds or runs the agent for you: this is a library you install and operate yourself, and the site's 235-page sitemap carries no services, retainer or consulting offer.

ADK is the open-source agent development framework that lets you build, debug, and deploy reliable AI agents at enterprise scale.

adk.devChecked

How much it does unattendedYes

Runs autonomously

Agents can be triggered by events, queues or a schedule and run as background processes with no person in the loop, which the vendor documents as ambient agents.

These agents can run as background processes to process data, monitor events, and respond asynchronously without human intervention.

adk.dev/runtime/ambient-agentsChecked

How much it does unattendedYes

Multi-agent

Multi-agent composition is the headline design: hierarchies of specialised agents that delegate sub-tasks, plus sequential, parallel and loop workflow agents for deterministic orchestration.

Multi-Agent System Design: Easily build applications composed of multiple, specialized agents arranged hierarchically.

adk.dev/get-started/aboutChecked

How much it does unattendedYes

Agent permissions

Autonomy is set per tool by the developer: a tool can be configured to pause and ask a human or a supervising system before it runs, though the vendor labels this confirmation feature experimental.

The Tool Confirmation feature in the Agent Development Kit (ADK) allows an ADK Tool to pause its execution and interact with a user or other system…

adk.dev/tools-custom/confirmationChecked

Which models it runs onYes

Claude

Claude is supported in Python and Java, either through the registry wrapper on Google Cloud Agent Platform or directly against Anthropic with your own API key.

You can use Anthropic's Claude models with ADK in both Python and Java. Choose the path that matches your language and backend below.

adk.dev/agents/models/anthropicChecked

Which models it runs onYes

GPT

OpenAI models reach ADK two ways: a native Go package the vendor marks experimental, and the LiteLLM connector for Python, so the path depends on your language.

You can use OpenAI models with ADK. How you connect depends on the language

adk.dev/agents/models/openaiChecked

Which models it runs onYes

Open models

Open-weight models run through LiteLLM against local hosts such as Ollama, with separate documented paths for vLLM and on-device LiteRT-LM serving.

Ollama is a tool that allows you to host and run open-source models locally. ADK integrates with Ollama-hosted models through the LiteLLM model…

adk.dev/agents/models/ollamaChecked

Which models it runs onYes

Model choice

You choose the model per agent, including a router that picks between several at runtime; Gemini is the default path but not a requirement of the framework.

Agent Development Kit (ADK) is designed for flexibility, allowing you to integrate various Large Language Models (LLMs) into your agents.

adk.dev/agents/modelsChecked

Where you use itPartly

In your editor

There is no ADK editor extension; instead Agents CLI installs ADK skills into existing AI coding environments, and a docs MCP server can be added to the same tools.

The Agents CLI tool set lets you plug ADK agent expertise into your favorite AI-coding environments including Antigravity, Claude Code, Cursor, and…

adk.dev/tutorials/coding-with-aiChecked

Where you use itYes

On the command line

A terminal surface is first-class: an interactive run command with session save, resume and replay flags in the Python CLI, and an embedded launcher for Go binaries.

ADK provides an interactive terminal interface for testing your agents. This is useful for quick testing, scripted interactions, and CI/CD pipelines.

adk.dev/runtime/command-lineChecked

Where you use itPartly

In your pipeline

The CLI is documented for scripted and CI/CD use and evaluations run headless, but nothing on the site describes ADK acting on a pull request by itself without an agent you build.

On the page: Use the Command Line, opening paragraph

adk.dev/runtime/command-lineChecked

Where you use itPartly

In a browser

The browser UI exists but you run it locally and the vendor bars it from production, so there is no hosted web application unless you deploy your own agent service.

ADK Web is not meant for use in production deployments. You should use ADK Web for development and debugging purposes only.

adk.dev/runtime/web-interfaceChecked

Whose machine it runs onYes

Self-hosted

Self-hosting is a documented first-class path: package the agent as a container and run it anywhere, including locally in Docker or Podman with no Google Cloud connection.

You can manually package your Agent into a container image and then run it in any environment that supports container images. For example you can run…

adk.dev/deployChecked

Whose machine it runs onYes

Open source

The framework is published as open source under Apache 2.0 with language bindings distributed through the usual package managers, and the docs invite outside contributions.

By contributing, you agree that your contributions will be licensed under the project's Apache 2.0 License.

adk.dev/community/contributing-guideChecked

What it costs to runPartly

How it meters

The framework meters nothing. You pay the model provider whose key you supply, plus Google Cloud's Agent Runtime beyond its no-cost tier if you deploy there.

Agent Runtime is a paid service and you may incur costs if you go above the no-cost access tier.

adk.dev/deploy/agent-runtimeChecked

What it costs to runYes

Free tier

You install it from a package manager and run it without an account, a sales call or a card; the site publishes no pricing page at all for the framework.

On the page: Homepage hero paragraph

adk.devChecked

What it costs to runYes

API access

A built-in server exposes your agents over REST for programmatic calls, and the same launcher serves the API alongside the web UI in the compiled languages.

Use the API server in ADK to expose your agents through a REST API for programmatic testing and integration.

adk.dev/runtime/api-serverChecked

What it costs to runYes

MCP server

MCP works in both directions: agents consume external MCP servers as tools, and you can wrap ADK tools in an MCP server that any other MCP client can call.

Exposing ADK Tools via an MCP Server: How to build an MCP server that wraps ADK tools, making them accessible to any MCP client.

adk.dev/mcpChecked

What it costs to runYes

Bring your own key

Inference always runs on your own credentials: the quickstart has you write your own model API key into a local env file, and the runtime is yours to host.

This project uses the Gemini API, which requires an API key. If you don't already have Gemini API key, create a key in Google AI Studio on the API…

adk.dev/get-started/pythonChecked

Buying it for a teamPartly

Admin controls

Constraints exist but they are code, not a console: a plugin registered once on the runner applies its checks globally to every agent, tool and model call, and a developer must write it.

Policy enforcement: Implement security guardrails, such as a function that checks if users are authorized to use a specific tool and prevent its…

adk.dev/pluginsChecked

Buying it for a teamPartly

Audit log

Execution is recorded in depth through built-in logging, metrics and traces, but this is telemetry about agent runs on infrastructure you own, not an administrative audit trail of who changed what.

Agent Development Kit (ADK) provides built-in observability through logging, metrics, and traces to help you monitor and debug your agents.

adk.dev/observabilityChecked

What happens to your codePartly

Opt out of training

ADK's own usage telemetry is off until you switch it on and explicitly excludes source files, prompts and credentials, but the site says nothing about what the model provider you route to may do with your data.

Data collection is OFF by default until you explicitly choose to enable it.

adk.dev/runtime/command-lineChecked

What happens to your codeYes

Data residency

Jurisdiction is whatever you choose, because you host the container: the vendor documents running it disconnected from Google Cloud entirely, and cloud deploys take an explicit region.

This is a good option if you prefer to run offline or disconnected, or otherwise in a system that has no connection to Google Cloud.

adk.dev/deployChecked

What happens to your codeYes

Getting out

Conversation data is yours on disk: sessions save to a plain JSON file and can be pointed at your own database or storage service, and no credits exist to expire.

You'll be prompted to enter a session ID, and the session will be saved to path/to/my_agent/<session_id>.session.json.

adk.dev/runtime/command-lineChecked

For AI agents

MCP server
Yes
API
Yes

Developer docs

AdvertisementReach the teams comparing AI agent frameworks here.One banner on The Agents Index's category pages and agent pages.Advertise here

Google Agent Development Kit (ADK) alternatives

All 9 alternatives

Head to headGoogle Agent Development Kit (ADK) vs Microsoft Agent Framework

Questions about Google Agent Development Kit (ADK)

How much does Google Agent Development Kit (ADK) cost?
Google Agent Development Kit (ADK) gives its price on request. From adk.dev/pricing, checked 30 October 2026.
Does Google Agent Development Kit (ADK) have an API or an MCP server?
It has an API. It has an MCP server.
Is Google Agent Development Kit (ADK) open source, and can you host it yourself?
It is open source. You can host it yourself.
What have we checked on Google Agent Development Kit (ADK)?
30 facts, under these headings: What it does, how much it does unattended, which models it runs on, where you use it, whose machine it runs on, what it costs to run, buying it for a team, what happens to your code.
How do we check Google Agent Development Kit (ADK)?
We hold 30 facts on Google Agent Development Kit (ADK), quoted from 34 pages. Facts last checked 15 September 2026. Price last checked 30 October 2026.

How we check every listing

Sources and changes

Last changed

Sources34

Written about it elsewhere6

Repository30 August 2026

Licence
Apache-2.0
Stars
21,331
Forks
3,912
Last push
30 August 2026

Is this yours?

AI assistants like ChatGPT and Claude opened The Agents Index pages 2,746 times in September. Claiming is free. You get this page's reader numbers and the verified owner mark. You confirm it with an email at adk.dev.

Claim this listingGet Featured

Report an error if a fact is wrong.