graph TD
    subgraph GCP ["Google Cloud Platform"]
        direction LR

        subgraph GlobalInfrastructure ["全球基础设施"]
            direction TB
            Region1["区域 1 (例如: us-central1)"]
            Region2["区域 N (例如: asia-northeast1)"]
            Zone1A["可用区 1-A"]
            Zone1B["可用区 1-B"]
            ZoneNA["可用区 N-A"]
            PoP["边缘节点 PoP"]

            Region1 --- Zone1A & Zone1B
            Region2 --- ZoneNA
            GlobalNetwork["全球高速网络"] --- Region1 & Region2 & PoP
        end

        subgraph CoreServices ["核心服务"]
            direction TB

            subgraph Compute ["计算服务"]
                GCE["Compute Engine (VMs)"]
                GKE["Kubernetes Engine (容器)"]
                AppEngine["App Engine (PaaS)"]
                CloudFunctions["Cloud Functions (FaaS)"]
            end

            subgraph Storage ["存储服务"]
                CloudStorage["Cloud Storage (对象)"]
                PersistentDisk["Persistent Disk (块)"]
                Filestore["Filestore (文件)"]
                CloudSQL["Cloud SQL (关系型DB)"]
                Spanner["Spanner (全球DB)"]
                Bigtable["Bigtable (NoSQL)"]
            end

            subgraph Networking ["网络服务"]
                VPC["VPC 网络"]
                LoadBalancing["Cloud Load Balancing"]
                CloudDNS["Cloud DNS"]
                CloudCDN["Cloud CDN"]
            end

            subgraph DataAnalytics ["数据与分析"]
                BigQuery["BigQuery (数据仓库)"]
                Dataflow["Dataflow (数据处理)"]
                PubSub["Pub/Sub (消息传递)"]
            end

            %% 连接关系 (高层次示意)
            Compute -- 使用 --> Storage
            Compute -- 连接 --> Networking
            Networking -- 连接 --> GlobalInfrastructure
            PoP -- 集成 --> CloudCDN
            DataAnalytics -- 处理 --> Storage
            DataAnalytics -- 交互 --> PubSub
            AppEngine & CloudFunctions -- 触发 --> PubSub
        end

        subgraph ManagementSecurity ["管理与安全 (贯穿各层)"]
            direction TB
            IAM["Identity & Access Management (IAM)"]
            SecurityCommand["Security Command Center"]
            CloudArmor["Cloud Armor"]
            Monitoring["Cloud Monitoring"]
            Logging["Cloud Logging"]
            Console["Cloud Console / CLI"]
        end

        %% 整体关系
        CoreServices -- 运行于 --> GlobalInfrastructure
        ManagementSecurity -- 管理与保护 --> CoreServices & GlobalInfrastructure

    end

    User["用户 / 应用"] --> LoadBalancing
    User --> CloudCDN
    User --> Console

    %% 样式 (可选)
    classDef default fill:#f9f,stroke:#333,stroke-width:2px;
    classDef infra fill:#e6f2ff,stroke:#36c,stroke-width:2px;
    classDef compute fill:#fff0e6,stroke:#f60,stroke-width:2px;
    classDef storage fill:#e6ffe6,stroke:#090,stroke-width:2px;
    classDef network fill:#ffe6e6,stroke:#c00,stroke-width:2px;
    classDef data fill:#ffffcc,stroke:#cc0,stroke-width:2px;
    classDef mgmt fill:#f0f0f0,stroke:#666,stroke-width:2px;

    class GlobalInfrastructure,Region1,Region2,Zone1A,Zone1B,ZoneNA,PoP,GlobalNetwork infra;
    class Compute,GCE,GKE,AppEngine,CloudFunctions compute;
    class Storage,CloudStorage,PersistentDisk,Filestore,CloudSQL,Spanner,Bigtable storage;
    class Networking,VPC,LoadBalancing,CloudDNS,CloudCDN network;
    class DataAnalytics,BigQuery,Dataflow,PubSub data;
    class ManagementSecurity,IAM,SecurityCommand,CloudArmor,Monitoring,Logging,Console mgmt;

Google Cloud Platform (GCP) 核心基础设施详解

全球基础设施与核心服务概览

[

ModelScope

base_url=‘https://api-inference.modelscope.cn/v1',

DeepSeek

模型主页： https://modelscope.cn/models/deepseek-ai/DeepSeek-V3.1 Model Name: deepseek-ai/DeepSeek-V3.1 Context: 128K SDK: 同时支持OpenAI API和Anthropic API

Moonshot

模型主页： https://platform.moonshot.cn/docs/api/ base_url = “https://api.moonshot.cn/v1", model = “kimi-k2-0711-preview”, “kimi-k2-turbo-preview”, 可以通过模型列表获取(GET https://api.moonshot.cn/v1/models) 上下文：128K key： https://platform.moonshot.cn/console/api-keys playground: https://platform.moonshot.cn/playground context: 128K

Agent Lightning

https://microsoft.github.io/agent-lightning/latest/

RAGEN

https://gemini.google.com/app/9ece70bdfdaea0dc

RAGEN 是一个利用强化学习训练 LLM 推理代理的系统，旨在解决多回合互动和随机环境中的挑战。该项目通过 StarPO 框架优化轨迹级别的推理和行动策略。RAGEN 的模块化设计包括环境状态管理器、上下文管理器和代理代理，支持多种环境和实验。项目强调了其在不同环境复杂性中的泛化能力，并提供了详细的设置和评估指南。

参考

-一份全面的AI Agent知识地图

https://zilliz.com/blog/top-10-ai-agents-to-watch-in-2025 12 Best AI Agents You Need to Try in 2025 https://medium.com/%40elisowski/a-list-of-ai-agents-set-to-dominate-in-2025-028f975c5b99 https://explodingtopics.com/blog/ai-agents

github copilot - creat-agent

/create-agent 是 VS Code 里 GitHub Copilot 的一个快捷命令，用来在 Agent mode 里生成可复用的自定义 agent，而不是直接执行一次性任务。 code.visualstudio 你只要描述想要的角色，例如“安全审查 agent”或“架构规划 agent”，Copilot 会继续追问细节，然后帮你产出一个 .agent.md 文件。 code.visualstudio

AI Skill Resource 为每个组织、每个岗位以及每位学习者找到合适的成长路径。立即在工作中开启人工智能带来的机遇，为未来热门岗位做好准备。

Artificial Intelligence for Beginners - A Curriculum 通过为期 12 周、包含 24 节课的课程，探索人工智能（AI）的世界！课程包含实践课、测验和实验。该课程适合初学者，涵盖 TensorFlow 和 PyTorch 等工具，以及人工智能伦理等内容。

做手办

绘制这张图中角色的1/7比例商业化手办，写实风格，真实环境。手巾摆放在电脑桌上，配有圆形透明亚克力底座，底座上无文字。电脑桌旁边放置一只印有原画风格插画的精美玩具包装盒。

数字人

transform the image to Ghibli/3D Carton/Chibi Style

This article details a project aiming to recreate the heroes of the Han Dynasty within 15 days, challenging the limits of Wan2.2. It involves various aspects of content creation, including music, scripting, image generation, video production, and the use of robust prompting techniques. Key points include:​ 1. Creation Motivation: Participate in the competition after the release of Wan2.2, be inspired by film analysis, and experiment with accumulated prompts.​ 2. Music Creation: Select Suno as the tool, input prompts, edit and remix unsatisfactory segments, and export multi - track music for later use in video editing.​ 3. Script and Storyboard: Only determine the general framework based on music and theme, and improve through continuous practice.​ 4. Image Generation: Choose image - to - video for better consistency. Use Midjourney for consistency, design character settings, and experiment with style prompts.​ 5. Video Production: Understand models from official documents, select videos based on performance and viewing experience, and use tools for high - definition enlargement and frame - filling.​ 6. Robust Prompting: Construct prompts using the RTF structure, ensure comprehensive and clear information, use positive expressions, and enhance model performance with few - shot examples.​ 7. Multiple Prompting Assistants: There are different prompting assistants for text - to - image, video generation, and seamless transition design between start and end frames, each with its own workflow and rules.

“AGI is not possible even in 10 years” 听起来像是单纯的情绪化表达，但是当前我们听完一圈真正科技大咖们的观点后，也许就能理解，这是基于当前Transformer架构的物理和数学局限性，提出的非常硬核的论证。