

Google Agent Development Kit (ADK)
Not yet source-checkedLink check failingGoogle's open-source framework for building, evaluating, and deploying production AI agents
Machine-drafted from the vendor's site · not yet source-checkedProfile updated Link checked How we rate
In short
Google Agent Development Kit (ADK) is an open-source framework for creating production-scale AI agents with built-in evaluation and deployment tools. It supports Python, Java, and Go, offering a structured alternative to LangGraph for teams using Google Cloud or multi-model setups.
Developers and platform teams building production multi-agent systems on Google Cloud who want an opinionated open-source framework with real deployment, evaluation, and observability tooling.
Solo hobbyists who just want a single prompt-loop chatbot, teams fully committed to a non-Google stack that already have LangGraph/CrewAI in production, or anyone who needs a no-code visual builder.
Google's Agent Development Kit (ADK) is an open-source framework for building, debugging, evaluating, and deploying AI agents at production scale. Originally released alongside the Gemini agent stack, it has grown into a multi-language toolkit — official SDKs cover Python, Java, and Go, with community/experimental support for TypeScript and Kotlin — that lets a developer describe an agent as code (tools, prompts, sub-agents, state) and then run it locally, in a hosted dev UI, on Cloud Run, on Kubernetes, or on Google's managed Agent Engine. The design point is production plumbing that hand-rolled LangChain-style scripts tend to skimp on: structured session/state management, a graph-based workflow model that mixes deterministic control flow with LLM reasoning, first-class multi-agent orchestration (sequential, parallel, hierarchical, loop patterns), streaming, tracing, evaluation harnesses, and safety/guardrail hooks. ADK is model-agnostic despite the Google branding — Gemini is the default via Vertex or the Gemini API, but LiteLLM adapters unlock Anthropic Claude, OpenAI, local Ollama models, and most other providers. Tools can be Python/Go/Java functions, MCP servers, OpenAPI specs, LangChain tools, or Google Cloud services (BigQuery, Vertex AI Search, Apigee). Typical workflows: a solo developer prototypes a single agent in `adk web`, iterates against the built-in evaluator with a golden-set of trajectories, then wraps that agent as a sub-agent inside a larger multi-agent system deployed to Agent Engine with tracing piped into Cloud Trace. It is a natural fit for teams already on Google Cloud who want an opinionated, batteries-included alternative to LangGraph, CrewAI, or writing bespoke orchestration on top of the raw Gemini SDK.
ADK is Google's most credible answer to LangGraph — and unlike a lot of Google developer launches it feels like it was built by people who actually deploy agents. If you're already on Vertex/Gemini, it is now the default choice; if you're not, the multi-language SDKs and clean MCP support still make it worth a serious look, provided you can stomach the API churn.
— The AI Tool Bible editorial team
Pros
- ✅ Genuinely open-source (Apache 2.0) with active Google engineering behind it, not a hosted-only product
- ✅ Multi-language: first-class Python, Java, and Go SDKs — rare among agent frameworks that are usually Python-only
- ✅ Built-in dev UI (`adk web`) with trace inspection, event stream, and session replay speeds up debugging enormously
- ✅ Model-agnostic via LiteLLM — Gemini is default but Claude, GPT, and local models plug in cleanly
- ✅ Rich multi-agent primitives out of the box: SequentialAgent, ParallelAgent, LoopAgent, and hierarchical sub-agents
- ✅ Tight Google Cloud integration for deployment (Cloud Run, GKE, Agent Engine) plus native BigQuery/Vertex Search tools
- ✅ Evaluation harness with trajectory-level scoring is included, not a separate paid add-on
- ✅ First-class MCP (Model Context Protocol) client and server support
Cons
- ⚠️ Documentation and examples lean heavily on Gemini + Google Cloud; non-Google paths work but feel like second-class citizens
- ⚠️ API surface is still evolving — breaking changes between minor versions have been common through 2025-2026
- ⚠️ Multi-agent orchestration primitives are powerful but the graph/callback model has a real learning curve compared to a plain prompt loop
- ⚠️ Agent Engine deployment is convenient but locks you into GCP billing and quotas
- ⚠️ TypeScript/Kotlin support lags the Python SDK in features and community examples
Facts
- API available
- Yes
- Open source
- Yes
- Model used
- Gemini (default) plus Claude, GPT-4/5, Llama, and other providers via LiteLLM
- Hacker News
- 213 stories · top 1,471 points · last Oct 21, 2026 · checked Nov 12, 2026
Where this tool sits
Use cases
Frequently asked
- Is Google ADK free to use?
- The framework itself is free and open-source under the Apache 2.0 license. Costs are incurred only from underlying model providers like Gemini API or Vertex AI, and any hosting infrastructure used.
- Which programming languages does ADK support?
- ADK provides official SDKs for Python, Java, and Go. It also includes community or experimental support for TypeScript and Kotlin, though these may lag behind the primary languages in features.
- Can I use models other than Gemini with ADK?
- Yes, ADK is model-agnostic. While Gemini is the default, LiteLLM adapters allow integration with Anthropic Claude, OpenAI models, local Ollama models, and other providers.
- What deployment options are available for ADK agents?
- Agents can run locally, in a hosted dev UI, or be deployed to Cloud Run, Kubernetes (GKE), or Google's managed Agent Engine. The framework includes tools for tracing and observability in these environments.
- Is ADK suitable for simple single-prompt chatbots?
- ADK is best for production multi-agent systems and complex workflows. It is not recommended for solo hobbyists who only need a simple single prompt-loop chatbot or those requiring a no-code visual builder.