Repository files navigation

Agent Development Kit (ADK) is a flexible and modular framework that appliessoftware development principles to AI agent creation. It is designed tosimplify building, deploying, and orchestrating agent workflows, from simpletasks to complex systems. While optimized for Gemini, ADK is model-agnostic,deployment-agnostic, and compatible with other frameworks.

• Custom Service Registration: Add a service registry to provide a generic way to register custom service implementations to be used in FastAPI server. Seeshort instruction. (391628f)

• Rewind: Add the ability to rewind a session to before a previous invocation (9dce06f).

• New CodeExecutor: Introduces a new AgentEngineSandboxCodeExecutor class that supports executing agent-generated code using the Vertex AI Code Execution Sandbox API (ee39a89)

• Rich Tool Ecosystem: Utilize pre-built tools, custom functions,OpenAPI specs, MCP tools or integrate existing tools to give agents diversecapabilities, all for tight integration with the Google ecosystem.

• Code-First Development: Define agent logic, tools, and orchestrationdirectly in Python for ultimate flexibility, testability, and versioning.

• Agent Config: Build agents without code. Check out theAgent Config feature.

• Tool Confirmation: Atool confirmation flow(HITL) that can guard tool execution with explicit confirmation and custom input.

• Modular Multi-Agent Systems: Design scalable applications by composingmultiple specialized agents into flexible hierarchies.

• Deploy Anywhere: Easily containerize and deploy agents on Cloud Run orscale seamlessly with Vertex AI Agent Engine.

You can install the latest stable version of ADK usingpip:

pip install google-adk

The release cadence is roughly bi-weekly.

This version is recommended for most users as it represents the most recent official release.

Bug fixes and new features are merged into the main branch on GitHub first. If you need access to changes that haven't been included in an official PyPI release yet, you can install directly from the main branch:

pip install git+https://github.com/google/adk-python.git@main

Note: The development version is built directly from the latest code commits. While it includes the newest fixes and features, it may also contain experimental changes or bugs not present in the stable release. Use it primarily for testing upcoming changes or accessing critical fixes before they are officially released.

For remote agent-to-agent communication, ADK integrates with theA2A protocol.See thisexamplefor how they can work together.

Explore the full documentation for detailed guides on building, evaluating, anddeploying agents:

• Documentation

fromgoogle.adk.agentsimportAgentfromgoogle.adk.toolsimportgoogle_searchroot_agent=Agent(name="search_assistant",model="gemini-2.5-flash",# Or your preferred Gemini modelinstruction="You are a helpful assistant. Answer user questions using Google Search when needed.",description="An assistant that can search the web.",tools=[google_search])

Define a multi-agent system with coordinator agent, greeter agent, and task execution agent. Then ADK engine and the model will guide the agents to work together to accomplish the task.

fromgoogle.adk.agentsimportLlmAgent,BaseAgent# Define individual agentsgreeter=LlmAgent(name="greeter",model="gemini-2.5-flash", ...)task_executor=LlmAgent(name="task_executor",model="gemini-2.5-flash", ...)# Create parent agent and assign children via sub_agentscoordinator=LlmAgent(name="Coordinator",model="gemini-2.5-flash",description="I coordinate greetings and tasks.",sub_agents=[# Assign sub_agents heregreeter,task_executor    ])

A built-in development UI to help you test, evaluate, debug, and showcase your agent(s).

adkeval \    samples_for_testing/hello_world \    samples_for_testing/hello_world/hello_world_eval_set_001.evalset.json

We welcome contributions from the community! Whether it's bug reports, feature requests, documentation improvements, or code contributions, please see our

• General contribution guideline and flow.
• Then if you want to contribute code, please readCode Contributing Guidelines to get started.

We haveadk-python-community repo that is home to a growing ecosystem of community-contributed tools, third-partyservice integrations, and deployment scripts that extend the core capabilitiesof the ADK.

If you want to develop agent via vibe coding thellms.txt and thellms-full.txt can be used as context to LLM. While the former one is a summarized one and the later one has the full information in case your LLM has big enough context window.

• [Completed] ADK's 1st community meeting on Wednesday, October 15, 2025. Remember tojoin our group to get access to therecording, anddeck.

This project is licensed under the Apache 2.0 License - see theLICENSE file for details.

Happy Agent Building!