Google Agent Development Kit

The Google Agent Development Kit (ADK) is an open-source framework from Google for building, evaluating, and deploying AI agents and multi-agent systems. Google announced it on April 9, 2025 at Google Cloud Next 2025 and released it under the Apache 2.0 license, first as a Python library, with Java, Go, and TypeScript implementations following over the next year.^[1] ADK is model-agnostic but is tuned for Google's Gemini models and for deployment to the Google Cloud and Vertex AI stack. It is the same framework Google uses internally to build the agents inside products such as Agentspace (later rebranded Gemini Enterprise) and its Customer Engagement Suite. ADK ships alongside a companion open protocol, the Agent2Agent (A2A) protocol, for agent-to-agent interoperability, and it supports Anthropic's Model Context Protocol for connecting agents to tools and data.^[2]

Scroll sideways for more →

Overview

ADK is a "code-first" toolkit: developers define an agent's instructions, tools, and orchestration in ordinary source code rather than through a visual builder or a long prompt. Google's stated goal was to make agent development feel more like conventional software engineering, with version control, unit testing, and continuous integration, so that teams can move from a single agent with a few tool calls to large multi-agent systems without changing frameworks. The kit is deliberately positioned for production rather than demos; the official documentation site carries the tagline "Build production agents, not prototypes."^[8]

Although ADK works with many large language models, it is optimized for Gemini and for Google Cloud. Out of the box it gives direct access to Gemini through Vertex AI or the Gemini API, native generative AI tooling such as Google Search grounding and code execution, and one-command deployment to Google's managed agent runtime. The same agent code can also run locally, in a container, or on a competing cloud, which Google emphasizes to avoid the impression of lock-in.

Features and architecture

ADK centers on composable agents. The core abstraction is an Agent (or LlmAgent) defined by a model, an instruction, a set of tools, and optionally a list of sub-agents. Key capabilities include:

• Multi-agent hierarchies. Agents can be nested into a tree of specialized sub-agents, with the parent agent delegating to children automatically based on each child's natural-language description. This LLM-driven routing lets a coordinator hand a sub-task to the right specialist without hard-coded control flow.
• A rich tool ecosystem. Tools can be plain Python or Java functions (ADK reads the docstring and signature), pre-built Google tools such as Search and code execution, OpenAPI-described REST endpoints, MCP servers, and wrappers that import tools from third-party frameworks including LangChain, LlamaIndex, and CrewAI. Enterprise connectors reach systems such as BigQuery, AlloyDB, and more than 100 application integrations.
• Streaming, including audio and video. ADK supports bidirectional streaming so an agent can hold a live, human-like conversation. Through the Gemini Live API it can stream audio and video in both directions, not just text.
• Built-in evaluation. ADK includes an evaluation harness (for example AgentEvaluator.evaluate() in Python) that scores an agent's final responses and its step-by-step trajectory against predefined test cases, runnable from the CLI, a web UI, or programmatically.^[8]
• A developer UI. A local command-line tool and a visual web UI let developers chat with an agent, inspect each step, and view execution traces while debugging. A trace view added in v1.0.0 visualizes the full sequence of agent invocations.^[15]
• Workflow orchestration. Alongside LLM-driven delegation, ADK provides deterministic workflow agents (sequential, parallel, and loop) for pipelines that must run in a fixed order. The 2.0 release in 2026 expanded this into a graph-based workflow engine with routing, fan-out and fan-in, retries, explicit state management, and human-in-the-loop steps, plus a Task API for structured agent-to-agent delegation.^[18]

Languages and ecosystem

ADK began as Python (the google-adk package, installed with pip install google-adk). Google released the Python ADK v1.0.0 as a stable, production-ready version on May 20, 2025 at Google I/O,^[3][15] and shipped a 2.0 generation at Google I/O in May 2026 (v2.0.0 reached general availability on May 19, 2026, with point releases such as v2.2.0 on June 4, 2026).^[18] The Python repository has gathered more than 20,000 stars on GitHub.^[9]

The framework then expanded to other languages with the explicit aim of feature parity across SDKs:

Scroll sideways for more →

The official docs site also lists Kotlin, which runs on the JVM alongside the Java SDK.^[8] This multi-language strategy lets backend, mobile, and web teams build agents in the language they already use.

Two interoperability layers sit around ADK. The first is the Agent2Agent (A2A) protocol, an open standard Google announced on the same day as ADK, April 9, 2025, with more than 50 launch partners.^[2] A2A lets agents built by different vendors or in different frameworks discover one another and collaborate. It is built on familiar web standards (HTTP, Server-Sent Events, and JSON-RPC) and uses "Agent Cards," JSON capability descriptions that let one agent learn what another can do before delegating a task. Google frames A2A as complementary to MCP: MCP connects an agent to tools and data, while A2A connects agents to other agents. In June 2025 Google donated A2A to the Linux Foundation, which launched the Agent2Agent project on June 23, 2025 with founding members including Amazon Web Services, Cisco, Google, Microsoft, Salesforce, SAP, and ServiceNow; backing grew to more than 100 companies, and over 150 organizations by 2026.^[7][14] ADK gained native A2A support so that ADK agents can act as A2A clients and servers.

The second layer is deployment. Google's managed runtime, Vertex AI Agent Engine, runs ADK agents without the developer managing servers or containers, with built-in session management, tracing, and enterprise security.^[19] The ADK CLI deploys to it with a single adk deploy command, which packages the agent, wraps it in an AdkApp, and creates the deployment through the agent_engines.create() API.^[8] Agent Engine added support for ADK v1.0.0 and later in the google-cloud-aiplatform package version 1.95.0 and up. Agents can equally be containerized and run on Cloud Run, Google Kubernetes Engine, or any other infrastructure. Rounding out the ecosystem is Agent Garden, a curated collection of ready-to-use sample agents and tools accessible from the docs and the google/adk-samples repository, with one-click deployment of samples to Agent Engine via the Agent Starter Pack.^[6]

Adoption

ADK is woven through Google's own enterprise agent stack. Google has said publicly that ADK is the framework powering agents inside Agentspace (rebranded Gemini Enterprise) and the Google Customer Engagement Suite, so the kit's internal use is substantial.^[1] Google has cited early external users including Renault Group, the content platform Box, and the retail-pricing firm Revionics, and A2A launch and partner agents have come from companies such as Box, Workday, Salesforce, and ServiceNow.^[2] Independent developer coverage from outlets including InfoQ, InfoWorld, and DevOps.com tracked each language release through 2025 and 2026, and the Python repository's 20,000-plus GitHub stars indicate broad community uptake.^[9] Because much enterprise usage is private, precise deployment counts are not public, and figures here are limited to what Google and reporters have stated.

Relation to other agent frameworks

ADK entered a crowded field of agent frameworks that emerged in 2024 and 2025, and comparisons usually turn on orchestration style and ecosystem lock-in rather than raw capability:

Scroll sideways for more →

OpenAI released its Agents SDK in March 2025, about a month before ADK.^[17] Relative to LangGraph, which is favored for fine-grained control and observability, and CrewAI, which is praised for a gentle learning curve in prototyping, ADK's distinguishing pitch is tight integration with Google Cloud: easy access to Gemini, native enterprise connectors, built-in evaluation, and a one-command path to a managed runtime.^[17] Unlike OpenAI's SDK, ADK is not tied to one model provider; through the LiteLLM integration it can drive models from Anthropic, Meta, Mistral, and others. The frameworks are not strictly rivals at the protocol layer, since A2A and MCP are designed to let agents built in any of them interoperate.

Significance

ADK is the developer-facing centerpiece of Google's broader enterprise agentic AI strategy. Coupled with the A2A protocol for interoperability, Vertex AI Agent Engine for managed hosting, Agent Garden for samples, and Gemini Enterprise as the end-user surface, it gives Google a full-stack answer to competing agent platforms from OpenAI, Anthropic, and Microsoft. Two choices stand out. First, Google open-sourced both the kit (Apache 2.0) and the A2A protocol, then handed A2A to the Linux Foundation, a standards play intended to make cross-vendor agent collaboration vendor-neutral rather than proprietary. Second, by using the same framework internally that it ships to customers, Google positioned ADK as battle-tested production infrastructure rather than a demo toolkit. The rapid expansion from one language to four within roughly a year, and the move to a 2.0 generation with graph-based workflows, reflect how quickly the agent-framework category matured between 2025 and 2026, and how central these kits have become to enterprise adoption of generative AI.

References

1. "Agent Development Kit: Making it easy to build multi-agent applications." Google Developers Blog, April 9, 2025. https://developers.googleblog.com/en/agent-development-kit-easy-to-build-multi-agent-applications/ ↩
2. "Announcing the Agent2Agent Protocol (A2A)." Google Developers Blog, April 9, 2025. https://developers.googleblog.com/en/a2a-a-new-era-of-agent-interoperability/ ↩
3. "What's new with Agents: ADK, Agent Engine, and A2A Enhancements." Google Developers Blog, May 20, 2025. https://developers.googleblog.com/en/agents-adk-agent-engine-a2a-enhancements-google-io/ ↩
4. "Announcing ADK for Java 1.0.0: Building the Future of AI Agents in Java." Google Developers Blog, March 30, 2026. https://developers.googleblog.com/announcing-adk-for-java-100-building-the-future-of-ai-agents-in-java/ ↩
5. "Introducing Agent Development Kit for TypeScript." Google Developers Blog, April 21, 2026. https://developers.googleblog.com/introducing-agent-development-kit-for-typescript-build-ai-agents-with-the-power-of-a-code-first-approach/ ↩
6. "Agent Garden: Samples for learning, discovering and building." Google Developers Blog, 2025. https://developers.googleblog.com/agent-garden-samples-for-learning-discovering-and-building/ ↩
7. "Google Cloud donates A2A to Linux Foundation." Google Developers Blog, June 2025. https://developers.googleblog.com/en/google-cloud-donates-a2a-to-linux-foundation/ ↩
8. "Agent Development Kit (ADK)" (official documentation). adk.dev / google.github.io/adk-docs, accessed June 2026. https://adk.dev/ ↩
9. "google/adk-python" (repository and releases). GitHub, accessed June 2026. https://github.com/google/adk-python ↩
10. "google/adk-java." GitHub, accessed June 2026. https://github.com/google/adk-java
11. "google/adk-js." GitHub, accessed June 2026. https://github.com/google/adk-js
12. "Google Launches Agent Development Kit for Go." InfoQ, November 25, 2025. https://www.infoq.com/news/2025/11/go-agent-development-kit/ ↩
13. "Google ADK for Java 1.0 Introduces New App and Plugin Architecture." InfoQ, April 2026. https://www.infoq.com/news/2026/04/google-adk-1-0-new-architecture/
14. "Linux Foundation Launches the Agent2Agent Protocol Project." Linux Foundation, June 23, 2025. https://www.linuxfoundation.org/press/linux-foundation-launches-the-agent2agent-protocol-project-to-enable-secure-intelligent-communication-between-ai-agents ↩
15. Jack Wotherspoon. "What's New in Agent Development Kit (ADK) v1.0.0." Medium (Google Cloud Community), May 2025. https://medium.com/google-cloud/whats-new-in-agent-development-kit-adk-v1-0-0-fe8d79384bbd ↩
16. "Hands-on with the Google Agent Development Kit." InfoWorld, 2025. https://www.infoworld.com/article/4153857/hands-on-with-the-google-agent-development-kit.html
17. Victor Dibia. "AutoGen vs CrewAI vs LangGraph vs PydanticAI vs Google ADK vs OpenAI Agents." Newsletter, 2025. https://newsletter.victordibia.com/p/autogen-vs-crewai-vs-langgraph-vs ↩
18. "Google I/O '26 Fills Out Enterprise Agent Stack with Managed Agents, ADK 2.0." Virtualization Review, May 19, 2026. https://virtualizationreview.com/articles/2026/05/19/google-io-26-fills-out-enterprise-agent-stack-with-managed-agents-adk-2,-d-,0.aspx ↩
19. "Build and manage multi-system agents with Vertex AI." Google Cloud Blog, 2025. https://cloud.google.com/blog/products/ai-machine-learning/build-and-manage-multi-system-agents-with-vertex-ai ↩
20. "Agent Development Kit | Gemini Enterprise Agent Platform." Google Cloud Documentation, accessed June 2026. https://docs.cloud.google.com/gemini-enterprise-agent-platform/build/adk