返回排行榜

google/adk-python

Pythongoogle.github.io/adk-docs/

An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

agentagentsagents-sdkaiai-agentsmulti-agent-systemsmulti-agentsmulti-agents-collaborationaiagentframeworkgenaigenai-chatbotllms
Star 增长趋势
Star
20.8k
Forks
3.7k
周增长
Issues
375
15k20k
2025年4月2025年9月2026年2月2026年7月
制品库PyPIpip install adk-python
README

Agent Development Kit (ADK) 2.0

License PyPI version Python versions PyPI downloads Unit Tests Docs

An open-source, code-first Python framework for building, evaluating, and deploying sophisticated AI agents with flexibility and control.


⚠️ 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) and Workflow (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

🤝 Contributing

See CONTRIBUTING.md for details.

📄 License

This project is licensed under the Apache 2.0 License — see the LICENSE file for details.

相关仓库
Snailclimb/JavaGuide

Java 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

JavaScriptnpmApache License 2.0javainterview
javaguide.cn
157.2k46.2k
langgenius/dify

Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

TypeScriptnpmOtheraigpt
dify.ai
149.5k23.6k
TauricResearch/TradingAgents

TradingAgents: Multi-Agents LLM Financial Trading Framework

PythonPyPIApache License 2.0agentfinance
arxiv.org/pdf/2412.20138
93.8k18.1k
OpenHands/OpenHands

🙌 OpenHands: AI-Driven Development

PythonPyPIOtheragentartificial-intelligence
openhands.dev
81.4k10.4k
lobehub/lobehub

🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

TypeScriptnpmOtherchatgptopenai
lobehub.com
80.6k15.7k
bytedance/deer-flow

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

PythonPyPIMIT Licenseagentagentic
deerflow.tech
77.5k10.5k
dair-ai/Prompt-Engineering-Guide

🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

MDXMIT Licensedeep-learningprompt-engineering
promptingguide.ai
76.8k8.4k
hiyouga/LlamaFactory

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

PythonPyPIApache License 2.0fine-tuningllama
llamafactory.readthedocs.io
73.4k9k
shareAI-lab/learn-claude-code

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

PythonPyPIMIT Licenseagentclaude-code
learn.shareai.run
71.7k11.6k
FoundationAgents/MetaGPT

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

PythonPyPIMIT Licenseagentgpt
atoms.dev
69.4k8.9k
unslothai/unsloth

Unsloth is a local UI for training and running Gemma 4, Qwen3.6, DeepSeek, Kimi, GLM and other models.

PythonPyPIApache License 2.0fine-tuningllama
unsloth.ai/docs
68.6k6.2k
datawhalechina/hello-agents

📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

PythonPyPIOtheragenttutorial
hello-agents.datawhale.cc
67.5k8.4k