Agent Development Kit (ADK)
Agent Development Kit is a Python code library that helps developers build, test, and deploy AI agents.
What it is good for
- Building multi-step AI agents in Python code
- Testing and evaluating how an AI agent performs
- Deploying an AI agent to Google Cloud Run
- Connecting agents to tools through MCP servers
At a glance
- Who it is for
- Setup
- Requires programming
Level 5 of 5. You need to write code to use it.
- Cost
- Free and open source
- Type
- Framework or SDK
- Tasks
- Works with
- Gemini, Google Cloud Run, Vertex AI Agent Engine, Docker, MCP tools, OpenAPI
Momentum
- Rank this week
- Not ranked yet
- Best rank
- None yet
- GitHub stars
- 22,081
GitHub numbers as of Nov 2, 2026. Updated weekly.
Official links
Setup steps are on the official pages. We do not repeat them here, since they change.
Questions
- Is Agent Development Kit (ADK) free?
- Yes. It is free and open source (Apache-2.0 license).
- Do I need to know how to code to use Agent Development Kit (ADK)?
- Yes. You need to write code to use it.
- What does Agent Development Kit (ADK) work with?
- According to its own documentation, it works with Gemini, Google Cloud Run, Vertex AI Agent Engine, Docker, MCP tools, and OpenAPI.
- What is Agent Development Kit (ADK) good for?
- Building multi-step AI agents in Python code, testing and evaluating how an AI agent performs, deploying an AI agent to Google Cloud Run, and connecting agents to tools through MCP servers.
Similar agents
- LangChain
LangChain is a framework that helps developers build AI agents and LLM-powered applications that connect to models and data sources.
- crewAI
CrewAI is a Python framework that lets developers build teams of AI agents that split up and complete multi-step work.
- LangGraph
LangGraph is a framework that helps developers build long-running agents that keep their state and resume after failures.
- Agno
Agno is a framework and service platform that builds, runs, and improves AI agents for developers and teams who need them available as an API or MCP server.
- Conductor
Conductor is a workflow engine that runs multi-step jobs and AI agents reliably, so steps survive crashes and retries, for developers.
- Pydantic AI
Pydantic AI is a Python SDK that builds typed AI agents that return validated results for developers.