@qloog: #每日推荐 Google ADK Go - 是 Google 推出的开源 Agent 开发框架 目标:用软件工程的原则来构建 AI Agent 核心设计理念: 1、Code-first:用 Go 代码定义 Agent 逻辑、工具和编排,而…
摘要
Google 发布了开源的 Agent 开发框架 ADK for Go,旨在通过软件工程原则构建 AI 代理,支持代码优先、模型无关和云原生部署。
查看缓存全文
缓存时间: 2026/05/09 14:08
#每日推荐 Google ADK Go - 是 Google 推出的开源 Agent 开发框架 目标:用软件工程的原则来构建 AI Agent 核心设计理念: 1、Code-first:用 Go 代码定义 Agent 逻辑、工具和编排,而不是写一堆 prompt 2、Model-agnostic:虽然对 Gemini 做了优化,但支持任何 LLM 3、Deployment-agnostic:不绑定 Google Cloud,可以部署到任何环境 4、Cloud-native:充分利用 Go 的并发和性能优势 5、内置 OpenTelemetry 可观测性组件 GitHub: https://github.com/google/adk-go 官方文档: https://adk.dev
google/adk-go
Source: https://github.com/google/adk-go
Agent Development Kit (ADK) for Go
An open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Important Links: Docs & Samples & Python ADK & Java ADK & ADK Web.
Agent Development Kit (ADK) is a flexible and modular framework that applies software development principles to AI agent creation. It is designed to simplify building, deploying, and orchestrating agent workflows, from simple tasks to complex systems. While optimized for Gemini, ADK is model-agnostic, deployment-agnostic, and compatible with other frameworks.
This Go version of ADK is ideal for developers building cloud-native agent applications, leveraging Go’s strengths in concurrency and performance.
✨ Key Features
- Idiomatic Go: Designed to feel natural and leverage the power of Go.
- Rich Tool Ecosystem: Utilize pre-built tools, custom functions, or integrate existing tools to give agents diverse capabilities.
- Code-First Development: Define agent logic, tools, and orchestration directly in Go for ultimate flexibility, testability, and versioning.
- Modular Multi-Agent Systems: Design scalable applications by composing multiple specialized agents.
- Deploy Anywhere: Easily containerize and deploy agents, with strong support for cloud-native environments like Google Cloud Run.
🚀 Installation
To add ADK Go to your project, run:
go get google.golang.org/adk
📄 License
This project is licensed under the Apache 2.0 License - see the LICENSE file for details.
The exception is internal/httprr - see its LICENSE file.
相似文章
@teach_fireworks: 主流 Agent 开发框架对比一图流! 这么多 Agent 开发框架该怎么选? 个人日常重度 coding / 研究开源项目:可以试 Pi Agent AI SaaS 或企业级 agent:OpenAI Agents SDK + Lang…
一篇推文对比了主流的AI Agent开发框架(如Pi Agent、OpenAI Agents SDK、LangGraph、LlamaIndex、Pydantic AI),并给出了不同场景下的选型建议。
@Xudong07452910: 开源框架推荐:《Agency Agents》—— 232 位专业 AI 智能体,按职能分工,覆盖 16 个业务部门 如果你用过 Claude Code 或 Codex,可能遇到过这个问题:AI 在代码任务上很能干,但让它做前端设计、写营销…
Agency Agents 是一个开源框架,提供232个专业AI智能体覆盖16个业务部门,每个智能体具有独特个性、沟通风格和交付标准,支持Claude Code、GitHub Copilot等多种开发工具,并有社区翻译版本。
@ba_niu80557: https://x.com/ba_niu80557/status/2062103965517721821
文章拆解了2026年Agent框架的六条设计路线(LangGraph、OpenAI Agents SDK、CrewAI、Dify、厂商原生SDK、Pi),并提供了基于状态管理、流程复杂度、人机交互、模型灵活性等维度的选型建议,适合需要在生产环境中选择Agent框架的团队参考。
@sitinme: Google 首席工程师写了 24 个 AI 编程 Skill,把整个开发生命周期都打包了! 上周拿 Claude Code 改一个老 API,需求是给两个接口加缓存。 我先丢了句"帮我加 Redis 缓存",它三分钟写完,看着挺漂亮。 …
Google 首席工程师 Addy Osmani 开源了 agent-skills,包含 24 个 AI 编程技能,将工程纪律打包给 AI agent 使用,以提升代码质量和开发效率。
@googledevs: Autonomous AI in action. Check out how the new Gemma 4 31B model operates as an ADK Agent, exploring, planning, and run…
Google DeepMind 发布 Gemma 4 系列开放权重模型,覆盖 2B 到 31B 四种规模,支持 128K–256K 上下文、推理与函数调用,采用 Apache 2.0 许可证,并配备 ADK 框架实现自主智能体能力。