adk-python
google/adk-python
An open-source, code-first Python framework for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Overview
Provides a toolkit to create complex AI agents with support for various execution flows and task delegation modes. Includes a new workflow runtime engine and detailed documentation links for guidance.
Categories
Tags
Similar tools
ECC
affaan-m/ECC
The agent harness performance optimization system
hermes-agent
NousResearch/hermes-agent
The self-improving AI agent built by Nous Research
AutoGPT
Significant-Gravitas/AutoGPT
AutoGPT: Build, Deploy, and Run AI Agents
ollama
ollama/ollama
Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
prompts.chat
f/prompts.chat
The world's largest open-source prompt library for AI
JavaGuide
Snailclimb/JavaGuide
Snailclimb/JavaGuide: 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Install
pip install adk-pythonREADME
Agent Development Kit (ADK) 2.0
An open-source, code-first Python framework for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Important Links: Docs, Samples & ADK Web.
⚠️ BREAKING CHANGES FROM 1.x
This release includes breaking changes to the agent API, event model, and session schema. Sessions generated by ADK 2.0 are readable by ADK 1.28+ (extra fields will be ignored), but are incompatible with older 1.x versions.
🔥 What's New in 2.0
-
Workflow Runtime: A graph-based execution engine for composing deterministic execution flows for agentic apps, with support for routing, fan-out/fan-in, loops, retry, state management, dynamic nodes, human-in-the-loop, and nested workflows.
-
Task API: Structured agent-to-agent delegation with multi-turn task mode, single-turn controlled output, mixed delegation patterns, human-in-the-loop, and task agents as workflow nodes.
🚀 Installation
pip install google-adk
Requirements: Python 3.10+.
To install optional integrations, you can use the following command:
pip install "google-adk[extensions]"
The release cadence is roughly bi-weekly.
Quick Start
Beginner Note: ADK applications are built using two main classes:
Agent(defines an AI's instructions, tools, and behavior) andWorkflow(orchestrates agents and tasks in a graph-based flow).
Agent
from google.adk import Agent
root_agent = Agent(
name="greeting_agent",
model="gemini-2.5-flash",
instruction="You are a helpful assistant. Greet the user warmly.",
)
Workflow
from google.adk import Agent, Workflow
generate_fruit_agent = Agent(
name="generate_fruit_agent",
instruction="Return the name of a random fruit. Return only the name.",
)
generate_benefit_agent = Agent(
name="generate_benefit_agent",
instruction="Tell me a health benefit about the specified fruit.",
)
root_agent = Workflow(
name="root_agent",
edges=[("START", generate_fruit_agent, generate_benefit_agent)],
)
Run Locally
# Interactive CLI
adk run path/to/my_agent
# Web UI (supports multi-agent directories or pointing directly to a single agent folder)
adk web path/to/agents_dir
📚 Documentation
- Getting Started: https://google.github.io/adk-docs/
- Samples: See
contributing/workflow_samples/andcontributing/task_samples/for workflow and task API examples.
🤝 Contributing
See CONTRIBUTING.md for details.
📄 License
This project is licensed under the Apache 2.0 License — see the LICENSE file for details.