diff --git a/packages/aiCore/AI_SDK_ARCHITECTURE.md b/packages/aiCore/AI_SDK_ARCHITECTURE.md
new file mode 100644
index 0000000000..e6316571d9
--- /dev/null
+++ b/packages/aiCore/AI_SDK_ARCHITECTURE.md
@@ -0,0 +1,688 @@
+# Cherry Studio AI Core 基于 Vercel AI SDK 的技术架构
+
+## 1. 架构设计理念
+
+### 1.1 设计目标
+- **统一接口**：使用 Vercel AI SDK 统一不同 AI Provider 的接口差异
+- **动态导入**：通过动态导入实现按需加载，减少打包体积
+- **最小包装**：直接使用 AI SDK 的类型和接口，避免重复定义
+- **中间件增强**：扩大中间件的介入范围，覆盖请求的全生命周期（规划中）
+- **类型安全**：利用 TypeScript 和 AI SDK 的类型系统确保类型安全
+- **轻量级**：专注核心功能，保持包的轻量和高效
+- **包级独立**：作为独立包管理，便于复用和维护
+
+### 1.2 核心优势
+- **标准化**：AI SDK 提供统一的模型接口，减少适配工作
+- **简化维护**：废弃复杂的 XxxApiClient，统一为工厂函数模式
+- **更好的开发体验**：完整的 TypeScript 支持和丰富的生态系统
+- **性能优化**：AI SDK 内置优化和最佳实践
+- **模块化设计**：独立包结构，支持跨项目复用
+- **可扩展中间件**：支持在请求全生命周期中插入自定义逻辑
+
+## 2. 整体架构图
+
+```mermaid
+graph TD
+    subgraph "Cherry Studio 主应用"
+        UI["用户界面"]
+        Components["React 组件"]
+    end
+
+    subgraph "packages/aiCore (AI Core 包)"
+        ApiClientFactory["ApiClientFactory (工厂类)"]
+        UniversalClient["UniversalAiSdkClient (统一客户端)"]
+        ProviderRegistry["Provider 注册表"]
+        MiddlewareChain["中间件链 (规划中)"]
+    end
+
+    subgraph "动态导入层"
+        DynamicImport["动态导入"]
+    end
+
+    subgraph "Vercel AI SDK"
+        AICore["ai (核心库)"]
+        OpenAI["@ai-sdk/openai"]
+        Anthropic["@ai-sdk/anthropic"]
+        Google["@ai-sdk/google"]
+        XAI["@ai-sdk/xai"]
+        Others["其他 19+ Providers"]
+    end
+
+    subgraph "中间件生态 (规划中)"
+        PreRequest["请求预处理"]
+        StreamTransform["流转换"]
+        PostProcess["后处理"]
+        ErrorHandle["错误处理"]
+        Logging["日志记录"]
+        Cache["缓存"]
+    end
+
+    UI --> ApiClientFactory
+    Components --> ApiClientFactory
+    ApiClientFactory --> UniversalClient
+    UniversalClient --> MiddlewareChain
+    MiddlewareChain --> ProviderRegistry
+    ProviderRegistry --> DynamicImport
+    DynamicImport --> OpenAI
+    DynamicImport --> Anthropic
+    DynamicImport --> Google
+    DynamicImport --> XAI
+    DynamicImport --> Others
+    
+    UniversalClient --> AICore
+    AICore --> streamText
+    AICore --> generateText
+    
+    MiddlewareChain --> PreRequest
+    MiddlewareChain --> StreamTransform
+    MiddlewareChain --> PostProcess
+    MiddlewareChain --> ErrorHandle
+    MiddlewareChain --> Logging
+    MiddlewareChain --> Cache
+```
+
+## 3. 包结构设计
+
+### 3.1 包级文件结构（当前简化版 + 规划）
+
+```
+packages/aiCore/
+├── src/
+│   ├── providers/
+│   │   ├── registry.ts              # Provider 注册表 ✅
+│   │   └── types.ts                 # 核心类型定义 ✅
+│   ├── clients/
+│   │   ├── UniversalAiSdkClient.ts  # 统一AI SDK客户端 ✅
+│   │   └── ApiClientFactory.ts     # 客户端工厂 ✅
+│   ├── middleware/                  # 中间件系统 (规划中)
+│   │   ├── lifecycle/               # 生命周期中间件
+│   │   │   ├── PreRequestMiddleware.ts
+│   │   │   ├── PostResponseMiddleware.ts
+│   │   │   ├── ErrorHandlingMiddleware.ts
+│   │   │   └── CacheMiddleware.ts
+│   │   ├── core/                    # 核心中间件
+│   │   │   ├── StreamProcessingMiddleware.ts
+│   │   │   ├── RequestValidationMiddleware.ts
+│   │   │   └── ResponseTransformMiddleware.ts
+│   │   ├── feat/                    # 特性中间件
+│   │   │   ├── ThinkingMiddleware.ts
+│   │   │   ├── ToolCallMiddleware.ts
+│   │   │   └── WebSearchMiddleware.ts
+│   │   ├── builder.ts               # 中间件构建器
+│   │   ├── composer.ts              # 中间件组合器
+│   │   ├── register.ts              # 中间件注册表
+│   │   └── types.ts                 # 中间件类型定义
+│   ├── services/                    # 高级服务 (规划中)
+│   │   ├── AiCoreService.ts         # 统一服务入口
+│   │   ├── CompletionsService.ts    # 文本生成服务
+│   │   ├── EmbeddingService.ts      # 嵌入服务
+│   │   └── ImageService.ts          # 图像生成服务
+│   └── index.ts                     # 包主入口文件 ✅
+├── package.json                     # 包配置文件 ✅
+├── tsconfig.json                    # TypeScript 配置 ✅
+├── README.md                        # 包说明文档 ✅
+└── AI_SDK_ARCHITECTURE.md           # 本文档 ✅
+```
+
+**图例：**
+- ✅ 已实现
+- 规划中：设计完成，待实现
+
+### 3.2 包配置 (package.json)
+
+```json
+{
+  "name": "@cherry-studio/ai-core",
+  "version": "1.0.0",
+  "description": "Cherry Studio AI Core - 基于 Vercel AI SDK 的统一 AI Provider 接口",
+  "main": "dist/index.js",
+  "types": "dist/index.d.ts",
+  "dependencies": {
+    "ai": "^4.3.16"
+  },
+  "peerDependenciesMeta": {
+    "@ai-sdk/openai": { "optional": true },
+    "@ai-sdk/anthropic": { "optional": true },
+    "@ai-sdk/google": { "optional": true },
+    "@ai-sdk/xai": { "optional": true }
+  },
+  "keywords": [
+    "ai", "sdk", "vercel-ai-sdk", "cherry-studio"
+  ]
+}
+```
+
+## 4. 核心组件详解
+
+### 4.1 Provider 注册表 (`providers/registry.ts`)
+
+统一管理所有 AI Provider 的注册和动态导入。
+
+**主要功能：**
+- 动态导入 AI SDK providers
+- 提供统一的 Provider 创建接口
+- 支持 19+ 官方 AI SDK providers
+- 类型安全的 Provider 配置
+
+**核心 API：**
+```typescript
+export interface ProviderConfig {
+  id: string
+  name: string
+  import: () => Promise<any>
+  creatorFunctionName: string
+}
+
+export class AiProviderRegistry {
+  getProvider(id: string): ProviderConfig | undefined
+  getAllProviders(): ProviderConfig[]
+  isSupported(id: string): boolean
+  registerProvider(config: ProviderConfig): void
+}
+```
+
+**支持的 Providers：**
+- OpenAI, Anthropic, Google, XAI
+- Azure OpenAI, Amazon Bedrock, Google Vertex
+- Groq, Together.ai, Fireworks, DeepSeek
+- Cerebras, DeepInfra, Replicate, Perplexity
+- Cohere, Fal AI, Vercel (19+ providers)
+
+### 4.2 统一AI SDK客户端 (`clients/UniversalAiSdkClient.ts`)
+
+将不同 AI providers 包装为统一接口。
+
+**主要功能：**
+- 异步初始化和动态加载
+- 统一的 stream() 和 generate() 方法
+- 直接使用 AI SDK 的 streamText() 和 generateText()
+- 配置验证和错误处理
+
+**核心 API：**
+```typescript
+export class UniversalAiSdkClient {
+  async initialize(): Promise<void>
+  isInitialized(): boolean
+  async stream(request: any): Promise<any>
+  async generate(request: any): Promise<any>
+  validateConfig(): boolean
+  getProviderInfo(): { id: string; name: string; isInitialized: boolean }
+}
+```
+
+### 4.3 客户端工厂 (`clients/ApiClientFactory.ts`)
+
+统一创建和管理 AI SDK 客户端。
+
+**主要功能：**
+- 统一的客户端创建接口
+- 智能缓存和复用机制
+- 批量创建和健康检查
+- 错误处理和重试
+
+**核心 API：**
+```typescript
+export class ApiClientFactory {
+  static async createAiSdkClient(providerId: string, options: any): Promise<UniversalAiSdkClient>
+  static getCachedClient(providerId: string, options: any): UniversalAiSdkClient | undefined
+  static clearCache(): void
+  static async healthCheck(): Promise<HealthCheckResult>
+  static getSupportedProviders(): ProviderInfo[]
+}
+```
+
+### 4.4 增强的中间件系统 (规划中)
+
+扩展中间件架构，支持请求全生命周期的介入。
+
+**生命周期阶段：**
+1. **Pre-Request**：请求预处理、参数验证、缓存检查
+2. **Request**：实际的 AI SDK 调用
+3. **Stream Processing**：流式响应处理、实时转换
+4. **Post-Response**：响应后处理、结果聚合
+5. **Error Handling**：错误处理、重试、降级
+
+**中间件分类：**
+
+**生命周期中间件：**
+- `PreRequestMiddleware`：请求前处理，参数验证、权限检查
+- `PostResponseMiddleware`：响应后处理，结果转换、统计记录
+- `ErrorHandlingMiddleware`：错误处理，重试机制、降级策略
+- `CacheMiddleware`：缓存中间件，请求缓存、结果缓存
+
+**核心中间件：**
+- `StreamProcessingMiddleware`：流式处理，chunk 转换、进度追踪
+- `RequestValidationMiddleware`：请求验证，schema 验证、安全检查
+- `ResponseTransformMiddleware`：响应转换，格式标准化、类型转换
+
+**特性中间件：**
+- `ThinkingMiddleware`：思考过程中间件，记录推理步骤
+- `ToolCallMiddleware`：工具调用中间件，函数调用处理
+- `WebSearchMiddleware`：网络搜索中间件，集成搜索功能
+
+**中间件 API 设计：**
+```typescript
+export interface Middleware {
+  name: string
+  priority: number
+  execute(context: MiddlewareContext, next: () => Promise<void>): Promise<void>
+}
+
+export interface MiddlewareContext {
+  request: AiCoreRequest
+  response?: AiCoreResponse
+  error?: Error
+  metadata: Record<string, any>
+  provider: string
+  model: string
+}
+
+export class MiddlewareChain {
+  use(middleware: Middleware): this
+  compose(): (context: MiddlewareContext) => Promise<void>
+  execute(context: MiddlewareContext): Promise<void>
+}
+```
+
+### 4.5 统一服务接口 (规划中)
+
+作为包的主要对外接口，提供高级 AI 功能。
+
+**服务方法：**
+- `completions()`: 文本生成
+- `streamCompletions()`: 流式文本生成
+- `generateObject()`: 结构化数据生成
+- `generateImage()`: 图像生成
+- `embed()`: 文本嵌入
+
+**API 设计：**
+```typescript
+export class AiCoreService {
+  constructor(middlewares?: Middleware[])
+  
+  async completions(request: CompletionRequest): Promise<CompletionResponse>
+  async streamCompletions(request: CompletionRequest): Promise<StreamCompletionResponse>
+  async generateObject<T>(request: ObjectGenerationRequest): Promise<T>
+  async generateImage(request: ImageGenerationRequest): Promise<ImageResponse>
+  async embed(request: EmbeddingRequest): Promise<EmbeddingResponse>
+  
+  use(middleware: Middleware): this
+  configure(config: AiCoreConfig): this
+}
+```
+
+## 5. 使用方式
+
+### 5.1 基础用法
+
+```typescript
+import { createAiSdkClient } from '@cherry-studio/ai-core'
+
+// 创建 OpenAI 客户端
+const client = await createAiSdkClient('openai', {
+  apiKey: 'your-api-key'
+})
+
+// 流式生成
+const result = await client.stream({
+  modelId: 'gpt-4',
+  messages: [{ role: 'user', content: 'Hello!' }]
+})
+
+// 非流式生成
+const response = await client.generate({
+  modelId: 'gpt-4',
+  messages: [{ role: 'user', content: 'Hello!' }]
+})
+```
+
+### 5.2 便捷函数
+
+```typescript
+import { createOpenAIClient, streamGeneration } from '@cherry-studio/ai-core'
+
+// 快速创建特定 provider 客户端
+const client = await createOpenAIClient({
+  apiKey: 'your-api-key'
+})
+
+// 便捷的一次性调用
+const result = await streamGeneration(
+  'anthropic',
+  'claude-3-sonnet',
+  [{ role: 'user', content: 'Hello!' }],
+  { apiKey: 'your-api-key' }
+)
+```
+
+### 5.3 多 Provider 支持
+
+```typescript
+import { createAiSdkClient, AiCore } from '@cherry-studio/ai-core'
+
+// 检查支持的 providers
+const providers = AiCore.getSupportedProviders()
+console.log(`支持 ${providers.length} 个 AI providers`)
+
+// 创建多个 provider 客户端
+const openai = await createAiSdkClient('openai', { apiKey: 'openai-key' })
+const anthropic = await createAiSdkClient('anthropic', { apiKey: 'anthropic-key' })
+const google = await createAiSdkClient('google', { apiKey: 'google-key' })
+const xai = await createAiSdkClient('xai', { apiKey: 'xai-key' })
+```
+
+### 5.4 在 Cherry Studio 中集成
+
+```typescript
+// 替换现有的 XxxApiClient
+// 之前：
+// const openaiClient = new OpenAIApiClient(config)
+// const anthropicClient = new AnthropicApiClient(config)
+
+// 现在：
+import { createAiSdkClient } from '@cherry-studio/ai-core'
+
+const createProviderClient = async (provider: CherryProvider) => {
+  return await createAiSdkClient(provider.id, {
+    apiKey: provider.apiKey,
+    baseURL: provider.baseURL
+  })
+}
+```
+
+### 5.5 中间件使用 (规划中)
+
+```typescript
+import { 
+  AiCoreService, 
+  ThinkingMiddleware, 
+  CacheMiddleware,
+  LoggingMiddleware 
+} from '@cherry-studio/ai-core'
+
+// 创建带中间件的服务
+const aiService = new AiCoreService()
+  .use(new CacheMiddleware({ ttl: 3600 }))
+  .use(new LoggingMiddleware({ level: 'info' }))
+  .use(new ThinkingMiddleware({ recordSteps: true }))
+
+// 使用增强的服务
+const result = await aiService.streamCompletions({
+  provider: 'openai',
+  model: 'gpt-4',
+  messages: [{ role: 'user', content: 'Explain quantum computing' }],
+  middleware: {
+    thinking: { enabled: true },
+    cache: { enabled: true, key: 'quantum-explanation' }
+  }
+})
+
+// 自定义中间件
+class CustomMiddleware implements Middleware {
+  name = 'custom'
+  priority = 100
+
+  async execute(context: MiddlewareContext, next: () => Promise<void>): Promise<void> {
+    console.log('Before request:', context.request)
+    
+    await next() // 执行下一个中间件或实际请求
+    
+    console.log('After response:', context.response)
+  }
+}
+
+aiService.use(new CustomMiddleware())
+```
+
+### 5.6 完整的工作流示例 (规划中)
+
+```typescript
+import { 
+  createAiSdkClient,
+  AiCoreService,
+  MiddlewareChain,
+  PreRequestMiddleware,
+  StreamProcessingMiddleware,
+  PostResponseMiddleware
+} from '@cherry-studio/ai-core'
+
+// 创建完整的工作流
+const createEnhancedAiService = async () => {
+  // 创建中间件链
+  const middlewareChain = new MiddlewareChain()
+    .use(new PreRequestMiddleware({
+      validateApiKey: true,
+      checkRateLimit: true
+    }))
+    .use(new StreamProcessingMiddleware({
+      enableProgressTracking: true,
+      chunkTransform: (chunk) => ({
+        ...chunk,
+        timestamp: Date.now()
+      })
+    }))
+    .use(new PostResponseMiddleware({
+      saveToHistory: true,
+      calculateMetrics: true
+    }))
+
+  // 创建服务实例
+  const service = new AiCoreService(middlewareChain.middlewares)
+
+  return service
+}
+
+// 使用增强服务
+const enhancedService = await createEnhancedAiService()
+
+const response = await enhancedService.completions({
+  provider: 'anthropic',
+  model: 'claude-3-sonnet',
+  messages: [
+    { role: 'user', content: 'Write a technical blog post about AI middleware' }
+  ],
+  options: {
+    temperature: 0.7,
+    maxTokens: 2000
+  },
+  middleware: {
+    // 中间件特定配置
+    thinking: { recordSteps: true },
+    cache: { enabled: true, ttl: 1800 },
+    logging: { level: 'debug' }
+  }
+})
+```
+
+## 6. 与现有架构的对比
+
+| 方面 | 现有架构 | 新架构 (AI Core 包) |
+|------|----------|-------------------|
+| **代码组织** | 集成在主应用中 | 独立包，模块化管理 |
+| **Provider 管理** | 各自独立的 XxxApiClient | 统一的 Provider 注册表 + 工厂 |
+| **接口标准化** | 手动适配各 Provider 差异 | AI SDK 统一接口 |
+| **类型安全** | 部分类型安全 | 完整的 TypeScript 支持 |
+| **维护成本** | 每个 Provider 需要单独维护 | 统一维护，新 Provider 快速接入 |
+| **包体积** | 所有 Provider 都打包 | 按需加载，动态导入 |
+| **复用性** | 仅限当前项目 | 可跨项目复用 |
+| **扩展性** | 添加新 Provider 复杂 | 只需在注册表中添加配置 |
+
+## 7. 简化设计原则
+
+### 7.1 最小包装原则
+- 直接使用 AI SDK 的类型，不重复定义
+- 避免过度抽象和复杂的中间层
+- 保持与 AI SDK 原生 API 的一致性
+
+### 7.2 动态导入优化
+```typescript
+// 按需加载，减少打包体积
+const module = await import('@ai-sdk/openai')
+const createOpenAI = module.createOpenAI
+```
+
+### 7.3 类型安全
+```typescript
+// 直接使用 AI SDK 类型
+import { streamText, generateText } from 'ai'
+
+// 避免重复定义，直接传递参数
+return streamText({ model, ...request })
+```
+
+### 7.4 配置简化
+```typescript
+// 简化的 Provider 配置
+interface ProviderConfig {
+  id: string                          // provider 标识
+  name: string                        // 显示名称  
+  import: () => Promise<any>          // 动态导入函数
+  creatorFunctionName: string         // 创建函数名
+}
+```
+
+## 8. 技术要点
+
+### 8.1 动态导入策略
+- **按需加载**：只加载用户实际使用的 providers
+- **缓存机制**：避免重复导入和初始化
+- **错误处理**：优雅处理导入失败的情况
+
+### 8.2 依赖管理策略
+- **核心依赖**：`ai` 库作为必需依赖
+- **可选依赖**：所有 `@ai-sdk/*` 包都是可选的
+- **版本兼容**：支持 AI SDK v3-v5 版本
+
+### 8.3 缓存策略
+- **客户端缓存**：基于 provider + options 的智能缓存
+- **配置哈希**：安全的 API key 哈希处理
+- **生命周期管理**：支持缓存清理和验证
+
+## 9. 迁移策略
+
+### 9.1 阶段一：包基础搭建 (Week 1) ✅ 已完成
+1. ✅ 创建简化的包结构
+2. ✅ 实现 Provider 注册表
+3. ✅ 创建统一客户端和工厂
+4. ✅ 配置构建和类型系统
+
+### 9.2 阶段二：核心功能完善 (Week 2) ✅ 已完成
+1. ✅ 支持 19+ 官方 AI SDK providers
+2. ✅ 实现缓存和错误处理
+3. ✅ 完善类型安全和 API 设计
+4. ✅ 添加便捷函数和工具
+
+### 9.3 阶段三：集成测试 (Week 3) 🔄 进行中
+1. 在 Cherry Studio 中集成测试
+2. 功能完整性验证
+3. 性能基准测试
+4. 兼容性问题修复
+
+### 9.4 阶段四：中间件系统实现 (Week 4-5) 📋 规划中
+1. **中间件核心架构**
+   - 实现 `MiddlewareChain` 和 `MiddlewareContext`
+   - 创建中间件接口和基础类型
+   - 建立中间件生命周期管理
+
+2. **生命周期中间件**
+   - `PreRequestMiddleware`：请求预处理
+   - `PostResponseMiddleware`：响应后处理
+   - `ErrorHandlingMiddleware`：错误处理
+   - `CacheMiddleware`：缓存机制
+
+3. **核心中间件**
+   - `StreamProcessingMiddleware`：流式处理
+   - `RequestValidationMiddleware`：请求验证
+   - `ResponseTransformMiddleware`：响应转换
+
+4. **集成到现有架构**
+   - 在 `UniversalAiSdkClient` 中集成中间件链
+   - 更新 `ApiClientFactory` 支持中间件配置
+   - 创建 `AiCoreService` 统一服务接口
+
+### 9.5 阶段五：特性中间件 (Week 6) 📋 规划中
+1. **Cherry Studio 特性中间件**
+   - `ThinkingMiddleware`：思考过程记录
+   - `ToolCallMiddleware`：工具调用处理
+   - `WebSearchMiddleware`：网络搜索集成
+
+2. **高级功能**
+   - 中间件组合器和构建器
+   - 动态中间件加载
+   - 中间件配置管理
+
+### 9.6 阶段六：文档和发布 (Week 7) 📋 规划中
+1. 完善使用文档和示例
+2. 中间件开发指南
+3. 准备发布到 npm
+4. 建立维护流程
+
+### 9.7 阶段七：生态系统扩展 (Week 8+) 🚀 未来规划
+1. 社区中间件插件系统
+2. 可视化中间件编排工具
+3. 性能监控和分析
+4. 高级缓存策略
+
+## 10. 预期收益
+
+### 10.1 开发效率提升
+- **90%** 减少新 Provider 接入时间（只需添加注册表配置）
+- **70%** 减少维护工作量
+- **95%** 提升开发体验（统一接口 + 类型安全）
+- **独立开发**：可以独立于主应用开发和测试
+
+### 10.2 代码质量改善
+- 完整的 TypeScript 类型安全
+- 统一的错误处理机制
+- 标准化的 AI SDK 接口
+- 更好的测试覆盖率
+
+### 10.3 架构优势
+- **轻量级**：最小化的包装层
+- **可复用**：其他项目可以直接使用
+- **可维护**：独立版本管理和发布
+- **可扩展**：新 provider 只需配置即可
+
+### 10.4 生态系统价值
+- 支持 AI SDK 的完整生态系统
+- 可以独立发布到 npm
+- 为开源社区贡献价值
+- 建立统一的 AI 基础设施
+
+## 11. 风险评估与应对
+
+### 11.1 技术风险
+- **AI SDK 版本兼容**：支持多版本兼容策略
+- **依赖管理**：合理使用 peerDependencies
+- **类型一致性**：直接使用 AI SDK 类型
+- **性能影响**：最小化包装层开销
+
+### 11.2 迁移风险
+- **功能对等性**：确保所有现有功能都能实现
+- **API 兼容性**：提供平滑的迁移路径
+- **集成复杂度**：保持简单的集成方式
+- **学习成本**：提供清晰的使用文档
+
+## 12. 总结
+
+简化的 AI Core 架构专注于核心价值：
+
+### 12.1 核心价值
+- **统一接口**：一套 API 支持 19+ AI providers
+- **按需加载**：只打包用户实际使用的 providers
+- **类型安全**：完整的 TypeScript 支持
+- **轻量高效**：最小化的包装层
+
+### 12.2 设计哲学
+- **直接使用 AI SDK**：避免重复造轮子
+- **最小包装**：只在必要时添加抽象层
+- **开发者友好**：简单易用的 API 设计
+- **生态兼容**：充分利用 AI SDK 生态系统
+
+### 12.3 成功关键
+1. **保持简单**：专注核心功能，避免过度设计
+2. **充分测试**：确保功能完整性和稳定性
+3. **渐进迁移**：平滑过渡，降低风险
+4. **文档完善**：支持快速上手和深度使用
+
+这个简化的架构为 Cherry Studio 提供了一个轻量、高效、可维护的 AI 基础设施，同时为社区贡献了一个高质量的开源包。 
\ No newline at end of file
diff --git a/packages/aiCore/README.md b/packages/aiCore/README.md
new file mode 100644
index 0000000000..99aa6ecc2a
--- /dev/null
+++ b/packages/aiCore/README.md
@@ -0,0 +1,114 @@
+# @cherry-studio/ai-core
+
+Cherry Studio AI Core 是一个基于 Vercel AI SDK 的统一 AI Provider 接口包。
+
+## 特性
+
+- 🚀 统一的 AI Provider 接口
+- 🔄 动态导入支持
+- 💾 智能缓存机制
+- 🛠️ TypeScript 支持
+- 📦 轻量级设计
+
+## 支持的 Providers
+
+基于 [AI SDK 官方支持的 providers](https://ai-sdk.dev/providers/ai-sdk-providers)：
+
+**核心 Providers:**
+- OpenAI
+- Anthropic
+- Google Generative AI
+- Google Vertex AI
+- Mistral AI
+- xAI (Grok)
+- Azure OpenAI
+- Amazon Bedrock
+
+**扩展 Providers:**
+- Cohere
+- Groq
+- Together.ai
+- Fireworks
+- DeepSeek
+- Cerebras
+- DeepInfra
+- Replicate
+- Perplexity
+- Fal AI
+- Vercel
+
+## 安装
+
+```bash
+npm install @cherry-studio/ai-core ai
+```
+
+还需要安装你要使用的 AI SDK provider:
+
+```bash
+npm install @ai-sdk/openai @ai-sdk/anthropic @ai-sdk/google
+```
+
+## 使用示例
+
+### 基础用法
+
+```typescript
+import { createAiSdkClient } from '@cherry-studio/ai-core'
+
+// 创建 OpenAI 客户端
+const client = await createAiSdkClient('openai', {
+  apiKey: 'your-api-key'
+})
+
+// 流式生成
+const result = await client.stream({
+  modelId: 'gpt-4',
+  messages: [
+    { role: 'user', content: 'Hello!' }
+  ]
+})
+
+// 非流式生成
+const response = await client.generate({
+  modelId: 'gpt-4',
+  messages: [
+    { role: 'user', content: 'Hello!' }
+  ]
+})
+```
+
+### 便捷函数
+
+```typescript
+import { createOpenAIClient, streamGeneration } from '@cherry-studio/ai-core'
+
+// 快速创建 OpenAI 客户端
+const client = await createOpenAIClient({
+  apiKey: 'your-api-key'
+})
+
+// 便捷流式生成
+const result = await streamGeneration(
+  'openai',
+  'gpt-4',
+  [{ role: 'user', content: 'Hello!' }],
+  { apiKey: 'your-api-key' }
+)
+```
+
+### 多 Provider 支持
+
+```typescript
+import { createAiSdkClient } from '@cherry-studio/ai-core'
+
+// 支持多种 AI providers
+const openaiClient = await createAiSdkClient('openai', { apiKey: 'openai-key' })
+const anthropicClient = await createAiSdkClient('anthropic', { apiKey: 'anthropic-key' })
+const googleClient = await createAiSdkClient('google', { apiKey: 'google-key' })
+const xaiClient = await createAiSdkClient('xai', { apiKey: 'xai-key' })
+```
+
+## License
+
+MIT 
\ No newline at end of file
diff --git a/packages/aiCore/package.json b/packages/aiCore/package.json
new file mode 100644
index 0000000000..4d9fd4d35f
--- /dev/null
+++ b/packages/aiCore/package.json
@@ -0,0 +1,117 @@
+{
+  "name": "@cherry-studio/ai-core",
+  "version": "1.0.0",
+  "description": "Cherry Studio AI Core - Unified AI Provider Interface Based on Vercel AI SDK",
+  "main": "dist/index.js",
+  "types": "dist/index.d.ts",
+  "scripts": {
+    "build": "tsc",
+    "dev": "tsc -w",
+    "clean": "rm -rf dist"
+  },
+  "keywords": [
+    "ai",
+    "sdk",
+    "openai",
+    "anthropic",
+    "google",
+    "cherry-studio",
+    "vercel-ai-sdk"
+  ],
+  "author": "Cherry Studio",
+  "license": "MIT",
+  "dependencies": {
+    "@ai-sdk/amazon-bedrock": "^2.2.10",
+    "@ai-sdk/anthropic": "^1.2.12",
+    "@ai-sdk/azure": "^1.3.23",
+    "@ai-sdk/cerebras": "^0.2.14",
+    "@ai-sdk/cohere": "^1.2.10",
+    "@ai-sdk/deepinfra": "^0.2.15",
+    "@ai-sdk/deepseek": "^0.2.14",
+    "@ai-sdk/fal": "^0.1.12",
+    "@ai-sdk/fireworks": "^0.2.14",
+    "@ai-sdk/google": "^1.2.19",
+    "@ai-sdk/google-vertex": "^2.2.24",
+    "@ai-sdk/groq": "^1.2.9",
+    "@ai-sdk/mistral": "^1.2.8",
+    "@ai-sdk/openai": "^1.3.22",
+    "@ai-sdk/perplexity": "^1.1.9",
+    "@ai-sdk/replicate": "^0.2.8",
+    "@ai-sdk/togetherai": "^0.2.14",
+    "@ai-sdk/vercel": "^0.0.1",
+    "@ai-sdk/xai": "^1.2.16",
+    "ai": "^4.3.16"
+  },
+  "peerDependenciesMeta": {
+    "@ai-sdk/amazon-bedrock": {
+      "optional": true
+    },
+    "@ai-sdk/anthropic": {
+      "optional": true
+    },
+    "@ai-sdk/azure": {
+      "optional": true
+    },
+    "@ai-sdk/cerebras": {
+      "optional": true
+    },
+    "@ai-sdk/cohere": {
+      "optional": true
+    },
+    "@ai-sdk/deepinfra": {
+      "optional": true
+    },
+    "@ai-sdk/deepseek": {
+      "optional": true
+    },
+    "@ai-sdk/fal": {
+      "optional": true
+    },
+    "@ai-sdk/fireworks": {
+      "optional": true
+    },
+    "@ai-sdk/google": {
+      "optional": true
+    },
+    "@ai-sdk/google-vertex": {
+      "optional": true
+    },
+    "@ai-sdk/groq": {
+      "optional": true
+    },
+    "@ai-sdk/mistral": {
+      "optional": true
+    },
+    "@ai-sdk/openai": {
+      "optional": true
+    },
+    "@ai-sdk/perplexity": {
+      "optional": true
+    },
+    "@ai-sdk/replicate": {
+      "optional": true
+    },
+    "@ai-sdk/together": {
+      "optional": true
+    },
+    "@ai-sdk/vercel": {
+      "optional": true
+    },
+    "@ai-sdk/xai": {
+      "optional": true
+    }
+  },
+  "devDependencies": {
+    "typescript": "^5.0.0"
+  },
+  "files": [
+    "dist"
+  ],
+  "exports": {
+    ".": {
+      "types": "./dist/index.d.ts",
+      "import": "./dist/index.js",
+      "require": "./dist/index.js"
+    }
+  }
+}
diff --git a/packages/aiCore/src/clients/ApiClientFactory.ts b/packages/aiCore/src/clients/ApiClientFactory.ts
new file mode 100644
index 0000000000..050c551dc9
--- /dev/null
+++ b/packages/aiCore/src/clients/ApiClientFactory.ts
@@ -0,0 +1,341 @@
+/**
+ * API Client Factory
+ * 整合现有实现的改进版API客户端工厂
+ */
+
+import { aiProviderRegistry } from '../providers/registry'
+import type { CacheStats as BaseCacheStats, ClientConfig as BaseClientConfig } from '../providers/types'
+import { UniversalAiSdkClient } from './UniversalAiSdkClient'
+
+// 客户端配置接口
+export interface ClientConfig extends BaseClientConfig {}
+
+// 缓存统计信息
+export interface CacheStats extends BaseCacheStats {}
+
+// 错误类型
+export class ClientFactoryError extends Error {
+  constructor(
+    message: string,
+    public providerId?: string,
+    public cause?: Error
+  ) {
+    super(message)
+    this.name = 'ClientFactoryError'
+  }
+}
+
+/**
+ * API Client Factory
+ * 统一管理和创建AI SDK客户端
+ */
+export class ApiClientFactory {
+  private static instance: ApiClientFactory
+  private static sdkClients = new Map<string, UniversalAiSdkClient>()
+  private static lastCleanup = new Date()
+
+  private constructor() {
+    // Private constructor for singleton pattern
+  }
+
+  public static getInstance(): ApiClientFactory {
+    if (!ApiClientFactory.instance) {
+      ApiClientFactory.instance = new ApiClientFactory()
+    }
+    return ApiClientFactory.instance
+  }
+
+  /**
+   * [NEW METHOD] Create a new universal client for ai-sdk providers.
+   * [新方法] 为 ai-sdk 提供商创建一个新的通用客户端。
+   */
+  static async createAiSdkClient(providerId: string, options: any = {}): Promise<UniversalAiSdkClient> {
+    try {
+      // 验证provider是否支持
+      if (!aiProviderRegistry.isSupported(providerId)) {
+        throw new ClientFactoryError(`Provider "${providerId}" is not supported`, providerId)
+      }
+
+      // 生成缓存键 - 对于有认证选项的providers，使用更精细的键
+      const cacheKey = this.generateCacheKey(providerId, options)
+
+      // 检查缓存
+      if (this.sdkClients.has(cacheKey)) {
+        const cachedClient = this.sdkClients.get(cacheKey)!
+        // 验证缓存的客户端是否仍然有效
+        if (cachedClient.isInitialized() && cachedClient.validateConfig()) {
+          return cachedClient
+        } else {
+          // 如果缓存的客户端无效，清理它
+          this.sdkClients.delete(cacheKey)
+          cachedClient.cleanup()
+        }
+      }
+
+      // 1. 创建一个新的通用客户端实例
+      const client = new UniversalAiSdkClient(providerId, options)
+
+      // 2. 初始化它（这将执行动态导入）
+      await client.initialize()
+
+      // 3. 验证配置
+      if (!client.validateConfig()) {
+        throw new ClientFactoryError(`Invalid configuration for provider "${providerId}"`, providerId)
+      }
+
+      // 4. 缓存并返回
+      this.sdkClients.set(cacheKey, client)
+      return client
+    } catch (error) {
+      if (error instanceof ClientFactoryError) {
+        throw error
+      }
+      throw new ClientFactoryError(
+        `Failed to create client for provider "${providerId}": ${error instanceof Error ? error.message : 'Unknown error'}`,
+        providerId,
+        error instanceof Error ? error : undefined
+      )
+    }
+  }
+
+  /**
+   * 获取缓存的客户端
+   */
+  static getCachedClient(providerId: string, options: any = {}): UniversalAiSdkClient | undefined {
+    const cacheKey = this.generateCacheKey(providerId, options)
+    return this.sdkClients.get(cacheKey)
+  }
+
+  /**
+   * 检查客户端是否存在于缓存中
+   */
+  static hasCachedClient(providerId: string, options: any = {}): boolean {
+    const cacheKey = this.generateCacheKey(providerId, options)
+    return this.sdkClients.has(cacheKey)
+  }
+
+  /**
+   * 生成缓存键
+   */
+  private static generateCacheKey(providerId: string, options: any): string {
+    // 创建一个包含关键配置的键，但不包含敏感信息的完整内容
+    const keyData = {
+      providerId,
+      apiKey: options.apiKey ? this.hashApiKey(options.apiKey) : undefined,
+      baseURL: options.baseURL,
+      organization: options.organization,
+      project: options.project,
+      // 添加其他相关但非敏感的配置
+      model: options.model,
+      region: options.region
+    }
+
+    // 移除undefined值
+    Object.keys(keyData).forEach((key) => {
+      if (keyData[key as keyof typeof keyData] === undefined) {
+        delete keyData[key as keyof typeof keyData]
+      }
+    })
+
+    return JSON.stringify(keyData)
+  }
+
+  /**
+   * 对API Key进行哈希处理（用于缓存键）
+   */
+  private static hashApiKey(apiKey: string): string {
+    // 简单的哈希方法，只取前8个字符和后4个字符
+    if (apiKey.length <= 12) {
+      return apiKey.slice(0, 4) + '...'
+    }
+    return apiKey.slice(0, 8) + '...' + apiKey.slice(-4)
+  }
+
+  /**
+   * 清理缓存
+   */
+  static clearCache(): void {
+    // 清理所有客户端
+    this.sdkClients.forEach((client) => {
+      try {
+        client.cleanup()
+      } catch (error) {
+        console.warn('Error cleaning up client:', error)
+      }
+    })
+
+    this.sdkClients.clear()
+    this.lastCleanup = new Date()
+  }
+
+  /**
+   * 清理特定provider的缓存
+   */
+  static clearProviderCache(providerId: string): void {
+    const keysToDelete: string[] = []
+
+    this.sdkClients.forEach((client, key) => {
+      if (key.includes(`"providerId":"${providerId}"`)) {
+        try {
+          client.cleanup()
+        } catch (error) {
+          console.warn(`Error cleaning up client for ${providerId}:`, error)
+        }
+        keysToDelete.push(key)
+      }
+    })
+
+    keysToDelete.forEach((key) => {
+      this.sdkClients.delete(key)
+    })
+  }
+
+  /**
+   * 获取缓存统计信息
+   */
+  static getCacheStats(): CacheStats {
+    return {
+      size: this.sdkClients.size,
+      keys: Array.from(this.sdkClients.keys()),
+      lastCleanup: this.lastCleanup
+    }
+  }
+
+  /**
+   * 预热指定的客户端
+   */
+  static async warmupClients(configs: ClientConfig[]): Promise<void> {
+    const warmupPromises = configs.map(async (config) => {
+      try {
+        const { providerId, ...options } = config
+        await this.createAiSdkClient(providerId, options)
+        console.log(`✅ Warmed up client for provider: ${providerId}`)
+      } catch (error) {
+        console.warn(`⚠️ Failed to warm up client for ${config.providerId}:`, error)
+      }
+    })
+
+    await Promise.allSettled(warmupPromises)
+  }
+
+  /**
+   * 获取所有支持的providers信息
+   */
+  static getSupportedProviders(): Array<{
+    id: string
+    name: string
+    hasCachedClient: boolean
+  }> {
+    const providers = aiProviderRegistry.getAllProviders()
+
+    return providers.map((provider) => ({
+      id: provider.id,
+      name: provider.name,
+      hasCachedClient: Array.from(this.sdkClients.keys()).some((key) => key.includes(`"providerId":"${provider.id}"`))
+    }))
+  }
+
+  /**
+   * 批量创建客户端
+   */
+  static async createMultipleClients(configs: ClientConfig[]): Promise<{
+    success: Array<{ providerId: string; client: UniversalAiSdkClient }>
+    errors: Array<{ providerId: string; error: Error }>
+  }> {
+    const success: Array<{ providerId: string; client: UniversalAiSdkClient }> = []
+    const errors: Array<{ providerId: string; error: Error }> = []
+
+    await Promise.allSettled(
+      configs.map(async (config) => {
+        try {
+          const { providerId, ...options } = config
+          const client = await this.createAiSdkClient(providerId, options)
+          success.push({ providerId, client })
+        } catch (error) {
+          errors.push({
+            providerId: config.providerId,
+            error: error instanceof Error ? error : new Error('Unknown error')
+          })
+        }
+      })
+    )
+
+    return { success, errors }
+  }
+
+  /**
+   * 健康检查 - 检查所有缓存客户端的状态
+   */
+  static async healthCheck(): Promise<{
+    healthy: number
+    unhealthy: number
+    total: number
+    details: Array<{
+      providerId: string
+      status: 'healthy' | 'unhealthy'
+      error?: string
+    }>
+  }> {
+    const details: Array<{
+      providerId: string
+      status: 'healthy' | 'unhealthy'
+      error?: string
+    }> = []
+
+    let healthy = 0
+    let unhealthy = 0
+
+    for (const [, client] of this.sdkClients) {
+      try {
+        const info = client.getProviderInfo()
+        if (client.isInitialized() && client.validateConfig()) {
+          healthy++
+          details.push({
+            providerId: info.id,
+            status: 'healthy'
+          })
+        } else {
+          unhealthy++
+          details.push({
+            providerId: info.id,
+            status: 'unhealthy',
+            error: 'Client not properly initialized or invalid config'
+          })
+        }
+      } catch (error) {
+        unhealthy++
+        details.push({
+          providerId: 'unknown',
+          status: 'unhealthy',
+          error: error instanceof Error ? error.message : 'Unknown error'
+        })
+      }
+    }
+
+    return {
+      healthy,
+      unhealthy,
+      total: this.sdkClients.size,
+      details
+    }
+  }
+}
+
+// 导出单例实例和便捷函数
+export const apiClientFactory = ApiClientFactory.getInstance()
+
+// 便捷函数
+export const createAiSdkClient = (providerId: string, options?: any) =>
+  ApiClientFactory.createAiSdkClient(providerId, options)
+
+export const getCachedClient = (providerId: string, options?: any) =>
+  ApiClientFactory.getCachedClient(providerId, options)
+
+export const clearCache = () => ApiClientFactory.clearCache()
+
+export const warmupClients = (configs: ClientConfig[]) => ApiClientFactory.warmupClients(configs)
+
+export const healthCheck = () => ApiClientFactory.healthCheck()
+
+// 默认导出
+export default ApiClientFactory
diff --git a/packages/aiCore/src/clients/UniversalAiSdkClient.ts b/packages/aiCore/src/clients/UniversalAiSdkClient.ts
new file mode 100644
index 0000000000..166b46f0a1
--- /dev/null
+++ b/packages/aiCore/src/clients/UniversalAiSdkClient.ts
@@ -0,0 +1,201 @@
+/**
+ * Universal AI SDK Client
+ * 基于现有实现的简化版统一AI SDK客户端
+ */
+
+import { generateText, streamText } from 'ai'
+
+import { aiProviderRegistry } from '../providers/registry'
+
+/**
+ * Universal AI SDK Client
+ * 统一的AI SDK客户端实现
+ */
+export class UniversalAiSdkClient {
+  private provider: any // The instantiated provider (e.g., from createOpenAI)
+  private initialized = false
+  private providerConfig: any
+
+  constructor(
+    private providerName: string,
+    private options: any // API keys, etc.
+  ) {}
+
+  /**
+   * 初始化客户端 - 异步步骤，因为涉及动态导入
+   */
+  async initialize(): Promise<void> {
+    if (this.initialized) return
+
+    // 获取Provider配置
+    this.providerConfig = aiProviderRegistry.getProvider(this.providerName)
+    if (!this.providerConfig) {
+      throw new Error(`Provider "${this.providerName}" is not registered.`)
+    }
+
+    try {
+      // 使用注册表的动态导入功能
+      const module = await this.providerConfig.import()
+
+      // 获取创建函数
+      const creatorFunction = module[this.providerConfig.creatorFunctionName]
+
+      if (typeof creatorFunction !== 'function') {
+        throw new Error(
+          `Creator function "${this.providerConfig.creatorFunctionName}" not found in the imported module for provider "${this.providerName}".`
+        )
+      }
+
+      // 创建provider实例
+      this.provider = creatorFunction(this.options)
+      this.initialized = true
+    } catch (error) {
+      if (error instanceof Error) {
+        throw new Error(`Failed to initialize provider "${this.providerName}": ${error.message}`)
+      }
+      throw new Error(`An unknown error occurred while initializing provider "${this.providerName}".`)
+    }
+  }
+
+  /**
+   * 检查是否已初始化
+   */
+  isInitialized(): boolean {
+    return this.initialized
+  }
+
+  /**
+   * 获取特定模型实例的辅助方法
+   */
+  private getModel(modelId: string): any {
+    if (!this.initialized) throw new Error('Client not initialized')
+
+    // 大多数providers都有直接调用模式：provider(modelId)
+    if (typeof this.provider === 'function') {
+      return this.provider(modelId)
+    }
+
+    throw new Error(`Unknown model access pattern for provider "${this.providerName}"`)
+  }
+
+  /**
+   * 实现流式逻辑，使用核心ai-sdk函数
+   */
+  async stream(request: any): Promise<any> {
+    if (!this.initialized) await this.initialize()
+
+    const model = this.getModel(request.modelId)
+
+    // 直接调用标准ai-sdk函数
+    return streamText({
+      model,
+      ...request
+    })
+  }
+
+  /**
+   * 实现非流式逻辑
+   */
+  async generate(request: any): Promise<any> {
+    if (!this.initialized) await this.initialize()
+
+    const model = this.getModel(request.modelId)
+
+    return generateText({
+      model,
+      ...request
+    })
+  }
+
+  /**
+   * 验证配置
+   */
+  validateConfig(): boolean {
+    try {
+      // 基础验证
+      if (!this.providerName) return false
+      if (!this.providerConfig) return false
+
+      // API Key验证（如果需要）
+      if (this.requiresApiKey() && !this.options?.apiKey) {
+        return false
+      }
+
+      return true
+    } catch {
+      return false
+    }
+  }
+
+  /**
+   * 检查Provider是否需要API Key
+   */
+  private requiresApiKey(): boolean {
+    // 大多数云服务Provider都需要API Key
+    const noApiKeyProviders = ['local', 'ollama'] // 本地运行的Provider
+    return !noApiKeyProviders.includes(this.providerName)
+  }
+
+  /**
+   * 获取Provider信息
+   */
+  getProviderInfo(): {
+    id: string
+    name: string
+    isInitialized: boolean
+  } {
+    return {
+      id: this.providerName,
+      name: this.providerConfig?.name || this.providerName,
+      isInitialized: this.initialized
+    }
+  }
+
+  /**
+   * 清理资源
+   */
+  cleanup(): void {
+    this.provider = null
+    this.initialized = false
+    this.providerConfig = null
+  }
+}
+
+// 工厂函数，方便创建客户端
+export async function createUniversalClient(providerName: string, options: any = {}): Promise<UniversalAiSdkClient> {
+  const client = new UniversalAiSdkClient(providerName, options)
+  await client.initialize()
+  return client
+}
+
+// 便捷的流式生成函数
+export async function streamGeneration(
+  providerName: string,
+  modelId: string,
+  messages: any[],
+  options: any = {}
+): Promise<any> {
+  const client = await createUniversalClient(providerName, options)
+
+  return client.stream({
+    modelId,
+    messages,
+    ...options
+  })
+}
+
+// 便捷的非流式生成函数
+export async function generateCompletion(
+  providerName: string,
+  modelId: string,
+  messages: any[],
+  options: any = {}
+): Promise<any> {
+  const client = await createUniversalClient(providerName, options)
+
+  return client.generate({
+    modelId,
+    messages,
+    ...options
+  })
+}
diff --git a/packages/aiCore/src/index.ts b/packages/aiCore/src/index.ts
new file mode 100644
index 0000000000..56c15811b9
--- /dev/null
+++ b/packages/aiCore/src/index.ts
@@ -0,0 +1,130 @@
+/**
+ * Cherry Studio AI Core Package
+ * 基于 Vercel AI SDK 的统一 AI Provider 接口
+ */
+
+// 核心导出
+export { ApiClientFactory, apiClientFactory } from './clients/ApiClientFactory'
+export { UniversalAiSdkClient } from './clients/UniversalAiSdkClient'
+export { aiProviderRegistry, PROVIDER_REGISTRY } from './providers/registry'
+
+// 类型导出
+export type { CacheStats, ClientConfig, ClientFactoryError } from './clients/ApiClientFactory'
+export type { ProviderConfig } from './providers/registry'
+export type { ProviderError } from './providers/types'
+
+// 便捷函数导出
+export { clearCache, createAiSdkClient, getCachedClient, healthCheck, warmupClients } from './clients/ApiClientFactory'
+export { createUniversalClient, generateCompletion, streamGeneration } from './clients/UniversalAiSdkClient'
+export { getAllProviders, getProvider, isProviderSupported, registerProvider } from './providers/registry'
+
+// 默认导出 - 主要的工厂类
+export { ApiClientFactory as default } from './clients/ApiClientFactory'
+
+// 导入内部使用的函数
+import { ApiClientFactory } from './clients/ApiClientFactory'
+import { clearCache, createAiSdkClient, healthCheck } from './clients/ApiClientFactory'
+import { aiProviderRegistry } from './providers/registry'
+import { getAllProviders, isProviderSupported } from './providers/registry'
+
+// 包信息
+export const AI_CORE_VERSION = '1.0.0'
+export const AI_CORE_NAME = '@cherry-studio/ai-core'
+
+// 包配置和实用工具
+export const AiCore = {
+  version: AI_CORE_VERSION,
+  name: AI_CORE_NAME,
+
+  // 快速创建客户端
+  async createClient(providerId: string, options: any = {}) {
+    return createAiSdkClient(providerId, options)
+  },
+
+  // 获取支持的providers
+  getSupportedProviders() {
+    return getAllProviders()
+  },
+
+  // 检查provider支持
+  isSupported(providerId: string) {
+    return isProviderSupported(providerId)
+  },
+
+  // 获取缓存统计
+  getCacheStats() {
+    return ApiClientFactory.getCacheStats()
+  },
+
+  // 健康检查
+  async healthCheck() {
+    return healthCheck()
+  },
+
+  // 清理所有资源
+  cleanup() {
+    clearCache()
+    aiProviderRegistry.cleanup()
+  }
+}
+
+// 便捷的预配置clients创建函数
+export const createOpenAIClient = async (options: { apiKey: string; baseURL?: string }) => {
+  return createAiSdkClient('openai', options)
+}
+
+export const createAnthropicClient = async (options: { apiKey: string; baseURL?: string }) => {
+  return createAiSdkClient('anthropic', options)
+}
+
+export const createGoogleClient = async (options: { apiKey: string; baseURL?: string }) => {
+  return createAiSdkClient('google', options)
+}
+
+export const createXAIClient = async (options: { apiKey: string; baseURL?: string }) => {
+  return createAiSdkClient('xai', options)
+}
+
+// 调试和开发工具
+export const DevTools = {
+  // 列出所有注册的providers
+  listProviders() {
+    return aiProviderRegistry.getAllProviders().map((p) => ({
+      id: p.id,
+      name: p.name
+    }))
+  },
+
+  // 测试provider连接
+  async testProvider(providerId: string, options: any) {
+    try {
+      const client = await createAiSdkClient(providerId, options)
+      const info = client.getProviderInfo()
+      return {
+        success: true,
+        providerId: info.id,
+        name: info.name,
+        isInitialized: info.isInitialized
+      }
+    } catch (error) {
+      return {
+        success: false,
+        providerId,
+        error: error instanceof Error ? error.message : 'Unknown error'
+      }
+    }
+  },
+
+  // 获取详细的缓存信息
+  getCacheDetails() {
+    const stats = ApiClientFactory.getCacheStats()
+    const providers = aiProviderRegistry.getAllProviders()
+
+    return {
+      cacheStats: stats,
+      supportedProviders: providers.length,
+      registeredProviders: aiProviderRegistry.getAllProviders().length,
+      activeClients: stats.size
+    }
+  }
+}
diff --git a/packages/aiCore/src/providers/registry.ts b/packages/aiCore/src/providers/registry.ts
new file mode 100644
index 0000000000..2f7a7d6412
--- /dev/null
+++ b/packages/aiCore/src/providers/registry.ts
@@ -0,0 +1,226 @@
+/**
+ * AI Provider 注册表
+ * 统一管理所有 AI SDK Providers 的动态导入和工厂函数
+ */
+
+// Provider 配置接口（简化版）
+export interface ProviderConfig {
+  id: string
+  name: string
+  // 动态导入函数
+  import: () => Promise<any>
+  // 创建函数名称
+  creatorFunctionName: string
+}
+
+/**
+ * AI SDK Provider 注册表
+ * 管理所有支持的 AI Providers 及其动态导入
+ */
+export class AiProviderRegistry {
+  private static instance: AiProviderRegistry
+  private registry = new Map<string, ProviderConfig>()
+
+  private constructor() {
+    this.initializeProviders()
+  }
+
+  public static getInstance(): AiProviderRegistry {
+    if (!AiProviderRegistry.instance) {
+      AiProviderRegistry.instance = new AiProviderRegistry()
+    }
+    return AiProviderRegistry.instance
+  }
+
+  /**
+   * 初始化所有支持的 Providers
+   * 基于 AI SDK 官方文档: https://ai-sdk.dev/providers/ai-sdk-providers
+   */
+  private initializeProviders(): void {
+    const providers: ProviderConfig[] = [
+      // 核心 AI SDK Providers
+      {
+        id: 'openai',
+        name: 'OpenAI',
+        import: () => import('@ai-sdk/openai'),
+        creatorFunctionName: 'createOpenAI'
+      },
+      {
+        id: 'anthropic',
+        name: 'Anthropic',
+        import: () => import('@ai-sdk/anthropic'),
+        creatorFunctionName: 'createAnthropic'
+      },
+      {
+        id: 'google',
+        name: 'Google Generative AI',
+        import: () => import('@ai-sdk/google'),
+        creatorFunctionName: 'createGoogleGenerativeAI'
+      },
+      {
+        id: 'google-vertex',
+        name: 'Google Vertex AI',
+        import: () => import('@ai-sdk/google-vertex'),
+        creatorFunctionName: 'createVertex'
+      },
+      {
+        id: 'mistral',
+        name: 'Mistral AI',
+        import: () => import('@ai-sdk/mistral'),
+        creatorFunctionName: 'createMistral'
+      },
+      {
+        id: 'xai',
+        name: 'xAI (Grok)',
+        import: () => import('@ai-sdk/xai'),
+        creatorFunctionName: 'createXai'
+      },
+      {
+        id: 'azure',
+        name: 'Azure OpenAI',
+        import: () => import('@ai-sdk/azure'),
+        creatorFunctionName: 'createAzure'
+      },
+      {
+        id: 'bedrock',
+        name: 'Amazon Bedrock',
+        import: () => import('@ai-sdk/amazon-bedrock'),
+        creatorFunctionName: 'createAmazonBedrock'
+      },
+      {
+        id: 'cohere',
+        name: 'Cohere',
+        import: () => import('@ai-sdk/cohere'),
+        creatorFunctionName: 'createCohere'
+      },
+      {
+        id: 'groq',
+        name: 'Groq',
+        import: () => import('@ai-sdk/groq'),
+        creatorFunctionName: 'createGroq'
+      },
+      {
+        id: 'together',
+        name: 'Together.ai',
+        import: () => import('@ai-sdk/togetherai'),
+        creatorFunctionName: 'createTogetherAI'
+      },
+      {
+        id: 'fireworks',
+        name: 'Fireworks',
+        import: () => import('@ai-sdk/fireworks'),
+        creatorFunctionName: 'createFireworks'
+      },
+      {
+        id: 'deepseek',
+        name: 'DeepSeek',
+        import: () => import('@ai-sdk/deepseek'),
+        creatorFunctionName: 'createDeepSeek'
+      },
+      {
+        id: 'cerebras',
+        name: 'Cerebras',
+        import: () => import('@ai-sdk/cerebras'),
+        creatorFunctionName: 'createCerebras'
+      },
+      {
+        id: 'deepinfra',
+        name: 'DeepInfra',
+        import: () => import('@ai-sdk/deepinfra'),
+        creatorFunctionName: 'createDeepInfra'
+      },
+      {
+        id: 'replicate',
+        name: 'Replicate',
+        import: () => import('@ai-sdk/replicate'),
+        creatorFunctionName: 'createReplicate'
+      },
+      {
+        id: 'perplexity',
+        name: 'Perplexity',
+        import: () => import('@ai-sdk/perplexity'),
+        creatorFunctionName: 'createPerplexity'
+      },
+      {
+        id: 'fal',
+        name: 'Fal AI',
+        import: () => import('@ai-sdk/fal'),
+        creatorFunctionName: 'createFal'
+      },
+      {
+        id: 'vercel',
+        name: 'Vercel',
+        import: () => import('@ai-sdk/vercel'),
+        creatorFunctionName: 'createVercel'
+      }
+    ]
+
+    // 初始化注册表
+    providers.forEach((config) => {
+      this.registry.set(config.id, config)
+    })
+  }
+
+  /**
+   * 获取所有已注册的 Providers
+   */
+  public getAllProviders(): ProviderConfig[] {
+    return Array.from(this.registry.values())
+  }
+
+  /**
+   * 根据 ID 获取 Provider 配置
+   */
+  public getProvider(id: string): ProviderConfig | undefined {
+    return this.registry.get(id)
+  }
+
+  /**
+   * 检查 Provider 是否支持（是否已注册）
+   */
+  public isSupported(id: string): boolean {
+    return this.registry.has(id)
+  }
+
+  /**
+   * 注册新的 Provider（用于扩展）
+   */
+  public registerProvider(config: ProviderConfig): void {
+    this.registry.set(config.id, config)
+  }
+
+  /**
+   * 清理资源
+   */
+  public cleanup(): void {
+    this.registry.clear()
+  }
+
+  /**
+   * 获取兼容现有实现的注册表格式
+   */
+  public getCompatibleRegistry(): Record<string, { import: () => Promise<any>; creatorFunctionName: string }> {
+    const compatibleRegistry: Record<string, { import: () => Promise<any>; creatorFunctionName: string }> = {}
+
+    this.getAllProviders().forEach((provider) => {
+      compatibleRegistry[provider.id] = {
+        import: provider.import,
+        creatorFunctionName: provider.creatorFunctionName
+      }
+    })
+
+    return compatibleRegistry
+  }
+}
+
+// 导出单例实例
+export const aiProviderRegistry = AiProviderRegistry.getInstance()
+
+// 便捷函数
+export const getProvider = (id: string) => aiProviderRegistry.getProvider(id)
+export const getAllProviders = () => aiProviderRegistry.getAllProviders()
+export const isProviderSupported = (id: string) => aiProviderRegistry.isSupported(id)
+export const registerProvider = (config: ProviderConfig) => aiProviderRegistry.registerProvider(config)
+
+// 兼容现有实现的导出
+export const PROVIDER_REGISTRY = aiProviderRegistry.getCompatibleRegistry()
diff --git a/packages/aiCore/src/providers/types.ts b/packages/aiCore/src/providers/types.ts
new file mode 100644
index 0000000000..8908a5967c
--- /dev/null
+++ b/packages/aiCore/src/providers/types.ts
@@ -0,0 +1,47 @@
+/**
+ * Provider 相关核心类型定义
+ * 只定义必要的接口，其他类型直接使用 AI SDK
+ */
+
+// Provider 配置接口（简化版）
+export interface ProviderConfig {
+  id: string
+  name: string
+  import: () => Promise<any>
+  creatorFunctionName: string
+}
+
+// API 客户端工厂接口
+export interface ApiClientFactory {
+  createAiSdkClient(providerId: string, options?: any): Promise<any>
+  getCachedClient(providerId: string, options?: any): any
+  clearCache(): void
+}
+
+// 客户端配置
+export interface ClientConfig {
+  providerId: string
+  apiKey?: string
+  baseURL?: string
+  [key: string]: any
+}
+
+// 错误类型
+export class ProviderError extends Error {
+  constructor(
+    message: string,
+    public providerId: string,
+    public code?: string,
+    public cause?: Error
+  ) {
+    super(message)
+    this.name = 'ProviderError'
+  }
+}
+
+// 缓存统计信息
+export interface CacheStats {
+  size: number
+  keys: string[]
+  lastCleanup?: Date
+}
diff --git a/packages/aiCore/tsconfig.json b/packages/aiCore/tsconfig.json
new file mode 100644
index 0000000000..b45b2bc8ca
--- /dev/null
+++ b/packages/aiCore/tsconfig.json
@@ -0,0 +1,26 @@
+{
+  "compilerOptions": {
+    "target": "ES2020",
+    "module": "ESNext",
+    "moduleResolution": "node",
+    "declaration": true,
+    "outDir": "./dist",
+    "rootDir": "./src",
+    "strict": true,
+    "esModuleInterop": true,
+    "skipLibCheck": true,
+    "forceConsistentCasingInFileNames": true,
+    "resolveJsonModule": true,
+    "allowSyntheticDefaultImports": true,
+    "noEmitOnError": false,
+    "experimentalDecorators": true,
+    "emitDecoratorMetadata": true
+  },
+  "include": [
+    "src/**/*"
+  ],
+  "exclude": [
+    "node_modules",
+    "dist"
+  ]
+} 
\ No newline at end of file
diff --git a/yarn.lock b/yarn.lock
index ad87138f87..67aea5b85e 100644
--- a/yarn.lock
+++ b/yarn.lock
@@ -74,6 +74,313 @@ __metadata:
   languageName: node
   linkType: hard
 
+"@ai-sdk/amazon-bedrock@npm:^2.2.10":
+  version: 2.2.10
+  resolution: "@ai-sdk/amazon-bedrock@npm:2.2.10"
+  dependencies:
+    "@ai-sdk/provider": "npm:1.1.3"
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+    "@smithy/eventstream-codec": "npm:^4.0.1"
+    "@smithy/util-utf8": "npm:^4.0.0"
+    aws4fetch: "npm:^1.0.20"
+  peerDependencies:
+    zod: ^3.0.0
+  checksum: 10c0/ca066cc4dd94146374492e18e313b7664b661562e7fa3c94ad55c731564744281d62662337718fe107c99d7d2ebf8fd655c8e2cb3dcbcd30b2e33cbc248c962e
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/anthropic@npm:1.2.12, @ai-sdk/anthropic@npm:^1.2.12":
+  version: 1.2.12
+  resolution: "@ai-sdk/anthropic@npm:1.2.12"
+  dependencies:
+    "@ai-sdk/provider": "npm:1.1.3"
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+  peerDependencies:
+    zod: ^3.0.0
+  checksum: 10c0/da13e1ed3c03efe207dbb0fd5fe9f399e4119e6687ec1096418a33a7eeea3c5f912a51c74b185bba3c203b15ee0c1b9cdf649711815ff8e769e31af266ac00fb
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/azure@npm:^1.3.23":
+  version: 1.3.23
+  resolution: "@ai-sdk/azure@npm:1.3.23"
+  dependencies:
+    "@ai-sdk/openai": "npm:1.3.22"
+    "@ai-sdk/provider": "npm:1.1.3"
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+  peerDependencies:
+    zod: ^3.0.0
+  checksum: 10c0/18fcd3271e316edffe1b289b1c148e3bf6e0e51e57440d6a5aa4d76b53831dd5219fffcedb92d7dddebac81add46151a00bf70bd9e14509421e3bb0e359fd6bf
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/cerebras@npm:^0.2.14":
+  version: 0.2.14
+  resolution: "@ai-sdk/cerebras@npm:0.2.14"
+  dependencies:
+    "@ai-sdk/openai-compatible": "npm:0.2.14"
+    "@ai-sdk/provider": "npm:1.1.3"
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+  peerDependencies:
+    zod: ^3.0.0
+  checksum: 10c0/a94f91daa618ce3f0499b77191f53c54a5a1f8bce6b4ad12acc976e4410f83271dfb1fb377bab9dee573f497d9a505160b757ac0120d8dc160c7081618f94b45
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/cohere@npm:^1.2.10":
+  version: 1.2.10
+  resolution: "@ai-sdk/cohere@npm:1.2.10"
+  dependencies:
+    "@ai-sdk/provider": "npm:1.1.3"
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+  peerDependencies:
+    zod: ^3.0.0
+  checksum: 10c0/7a7d026458322c9579d860244072525cbe939b86ad89f0cb29b0103fc8a1cb7e54b11bb5f13a4db6c18507a12a8a0b4035333c2e996d8ded4708b5ec355b78e7
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/deepinfra@npm:^0.2.15":
+  version: 0.2.15
+  resolution: "@ai-sdk/deepinfra@npm:0.2.15"
+  dependencies:
+    "@ai-sdk/openai-compatible": "npm:0.2.14"
+    "@ai-sdk/provider": "npm:1.1.3"
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+  peerDependencies:
+    zod: ^3.0.0
+  checksum: 10c0/569a7d9fdf2d4ab16e371243782ece401d2336ed152741789e91f2df24918e536b4e1e8ee9ae9436a1fe059e00c32a06c867f083c1d93443be2a564fd465459e
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/deepseek@npm:^0.2.14":
+  version: 0.2.14
+  resolution: "@ai-sdk/deepseek@npm:0.2.14"
+  dependencies:
+    "@ai-sdk/openai-compatible": "npm:0.2.14"
+    "@ai-sdk/provider": "npm:1.1.3"
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+  peerDependencies:
+    zod: ^3.0.0
+  checksum: 10c0/abf22e44336c2b9cf075da20d3e641bbe6584861820ebbcb37877ce4730503c561984b63040384aef53ae0b5835f6680f7c42477588ce5fdf6ad37df695e129e
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/fal@npm:^0.1.12":
+  version: 0.1.12
+  resolution: "@ai-sdk/fal@npm:0.1.12"
+  dependencies:
+    "@ai-sdk/provider": "npm:1.1.3"
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+  peerDependencies:
+    zod: ^3.0.0
+  checksum: 10c0/3e5f0a72cf479e017dbddafb5bcba64f51e3f7feba33045bb132a7ec3e0abe5b4b65740a0e4fc7631b7a0587f8beb8e52b94adee409e6c82db57ba5a87ab8006
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/fireworks@npm:^0.2.14":
+  version: 0.2.14
+  resolution: "@ai-sdk/fireworks@npm:0.2.14"
+  dependencies:
+    "@ai-sdk/openai-compatible": "npm:0.2.14"
+    "@ai-sdk/provider": "npm:1.1.3"
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+  peerDependencies:
+    zod: ^3.0.0
+  checksum: 10c0/c34dba26e0de8754017b4bc16c1b4a295863b4d18e33c5e1bf6e6057029c78cae397e610b34e1eae16af454653cbd97754b66a1f7eede9285df2e16f4637aec3
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/google-vertex@npm:^2.2.24":
+  version: 2.2.24
+  resolution: "@ai-sdk/google-vertex@npm:2.2.24"
+  dependencies:
+    "@ai-sdk/anthropic": "npm:1.2.12"
+    "@ai-sdk/google": "npm:1.2.19"
+    "@ai-sdk/provider": "npm:1.1.3"
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+    google-auth-library: "npm:^9.15.0"
+  peerDependencies:
+    zod: ^3.0.0
+  checksum: 10c0/720139b34e8b395d52517abdc81b54f8c6eac1334879f76c07515701bfc2c0dfec7aefb0aee3851e1ec9721462b02a3caffecc5803fd267604f5b1548b352ae3
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/google@npm:1.2.19, @ai-sdk/google@npm:^1.2.19":
+  version: 1.2.19
+  resolution: "@ai-sdk/google@npm:1.2.19"
+  dependencies:
+    "@ai-sdk/provider": "npm:1.1.3"
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+  peerDependencies:
+    zod: ^3.0.0
+  checksum: 10c0/b40d62ce822ce00850492e4a41c8b6b1ba2ddaaaa8f8d9b8381c198781adb23000fc4f434ef7edf5ba356a4455f8afbbdc5cbecbb0f66b7bcabbcd25758fc6b8
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/groq@npm:^1.2.9":
+  version: 1.2.9
+  resolution: "@ai-sdk/groq@npm:1.2.9"
+  dependencies:
+    "@ai-sdk/provider": "npm:1.1.3"
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+  peerDependencies:
+    zod: ^3.0.0
+  checksum: 10c0/b268c337fb656d6b36e2a0ee7737c073ad22521acf20b6861a51c269d4f49f59c269d6184ce21cbc61316987e46ed64696dffef57d6d60fb9c45f069d0f30297
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/mistral@npm:^1.2.8":
+  version: 1.2.8
+  resolution: "@ai-sdk/mistral@npm:1.2.8"
+  dependencies:
+    "@ai-sdk/provider": "npm:1.1.3"
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+  peerDependencies:
+    zod: ^3.0.0
+  checksum: 10c0/d798ce75685f86f8a77c38745c71328fd1bd6b361601d1cb613b94c3c709e890e15e369f8b7e7b009e28394ec42c500c775ec293d506de2be08b13730ea7a924
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/openai-compatible@npm:0.2.14":
+  version: 0.2.14
+  resolution: "@ai-sdk/openai-compatible@npm:0.2.14"
+  dependencies:
+    "@ai-sdk/provider": "npm:1.1.3"
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+  peerDependencies:
+    zod: ^3.0.0
+  checksum: 10c0/60980df8507c1e5d04ac51123bc15ea5cbf29eb88485f63da28d64ab5d9c3b335d2a2c9155a383605972ef5fa636929c8e2d360bf799153acf2b358e1af1fd47
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/openai@npm:1.3.22, @ai-sdk/openai@npm:^1.3.22":
+  version: 1.3.22
+  resolution: "@ai-sdk/openai@npm:1.3.22"
+  dependencies:
+    "@ai-sdk/provider": "npm:1.1.3"
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+  peerDependencies:
+    zod: ^3.0.0
+  checksum: 10c0/bcc73a84bebd15aa54568c3c77cedd5f999e282c5be180d5e28ebc789f8873dd0a74d87f1ec4a0f16e3e61b658c3b0734835daf176ed910966246db73c72b468
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/perplexity@npm:^1.1.9":
+  version: 1.1.9
+  resolution: "@ai-sdk/perplexity@npm:1.1.9"
+  dependencies:
+    "@ai-sdk/provider": "npm:1.1.3"
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+  peerDependencies:
+    zod: ^3.0.0
+  checksum: 10c0/02720dc2d65de771900a3b588b257ac9c3bdf8b3a9e255875b03e4ede9ef185a4c6d311782b5e8033306a6e7fde40fdec526345ba0843a84d45184a556e883ca
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/provider-utils@npm:2.2.8":
+  version: 2.2.8
+  resolution: "@ai-sdk/provider-utils@npm:2.2.8"
+  dependencies:
+    "@ai-sdk/provider": "npm:1.1.3"
+    nanoid: "npm:^3.3.8"
+    secure-json-parse: "npm:^2.7.0"
+  peerDependencies:
+    zod: ^3.23.8
+  checksum: 10c0/34c72bf5f23f2d3e7aef496da7099422ba3b3ff243c35511853e16c3f1528717500262eea32b19e3e09bc4452152a5f31e650512f53f08a5f5645d907bff429e
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/provider@npm:1.1.3":
+  version: 1.1.3
+  resolution: "@ai-sdk/provider@npm:1.1.3"
+  dependencies:
+    json-schema: "npm:^0.4.0"
+  checksum: 10c0/40e080e223328e7c89829865e9c48f4ce8442a6a59f7ed5dfbdb4f63e8d859a76641e2d31e91970dd389bddb910f32ec7c3dbb0ce583c119e5a1e614ea7b8bc4
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/react@npm:1.2.12":
+  version: 1.2.12
+  resolution: "@ai-sdk/react@npm:1.2.12"
+  dependencies:
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+    "@ai-sdk/ui-utils": "npm:1.2.11"
+    swr: "npm:^2.2.5"
+    throttleit: "npm:2.1.0"
+  peerDependencies:
+    react: ^18 || ^19 || ^19.0.0-rc
+    zod: ^3.23.8
+  peerDependenciesMeta:
+    zod:
+      optional: true
+  checksum: 10c0/5422feb4ffeebd3287441cf658733e9ad7f9081fc279e85f57700d7fe9f4ed8a0504789c1be695790df44b28730e525cf12acf0f52bfa5adecc561ffd00cb2a5
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/replicate@npm:^0.2.8":
+  version: 0.2.8
+  resolution: "@ai-sdk/replicate@npm:0.2.8"
+  dependencies:
+    "@ai-sdk/provider": "npm:1.1.3"
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+  peerDependencies:
+    zod: ^3.0.0
+  checksum: 10c0/96a90a815b60914126fce854dd32d5912cc4c09d418259af232214d083da8ea6857ad0c99b47758d59d2c4d845dcb33844bb97c6bd78238aee6a00c0069a5f94
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/togetherai@npm:^0.2.14":
+  version: 0.2.14
+  resolution: "@ai-sdk/togetherai@npm:0.2.14"
+  dependencies:
+    "@ai-sdk/openai-compatible": "npm:0.2.14"
+    "@ai-sdk/provider": "npm:1.1.3"
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+  peerDependencies:
+    zod: ^3.0.0
+  checksum: 10c0/ae8108fd81e583d7bde30cc391e048197b44dcb3881eecb69d65bc3ef8067a728e308b172587348278700e9b3235e3f6163bcdafb5bb2ec4cc87ff4f87a8e02b
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/ui-utils@npm:1.2.11":
+  version: 1.2.11
+  resolution: "@ai-sdk/ui-utils@npm:1.2.11"
+  dependencies:
+    "@ai-sdk/provider": "npm:1.1.3"
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+    zod-to-json-schema: "npm:^3.24.1"
+  peerDependencies:
+    zod: ^3.23.8
+  checksum: 10c0/de0a10f9e16010126a21a1690aaf56d545b9c0f8d8b2cc33ffd22c2bb2e914949acb9b3f86e0e39a0e4b0d4f24db12e2b094045e34b311de0c8f84bfab48cc92
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/vercel@npm:^0.0.1":
+  version: 0.0.1
+  resolution: "@ai-sdk/vercel@npm:0.0.1"
+  dependencies:
+    "@ai-sdk/openai-compatible": "npm:0.2.14"
+    "@ai-sdk/provider": "npm:1.1.3"
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+  peerDependencies:
+    zod: ^3.0.0
+  checksum: 10c0/608a747dc2abb2fc7789cad503769dab5cdedaf39f3494a70f7dbb42ea2dcccd91827b856508faac5305486981206397faa25edca3d593f42ab38869b220835c
+  languageName: node
+  linkType: hard
+
+"@ai-sdk/xai@npm:^1.2.16":
+  version: 1.2.16
+  resolution: "@ai-sdk/xai@npm:1.2.16"
+  dependencies:
+    "@ai-sdk/openai-compatible": "npm:0.2.14"
+    "@ai-sdk/provider": "npm:1.1.3"
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+  peerDependencies:
+    zod: ^3.0.0
+  checksum: 10c0/5418f42506679c49f8c6127b0cdf8185622ccb844d6cf928efe1f819b20cbb4eae631eb7dc534468c790fa7087438b4ebd3b4072c13fb28e0c947ebdd6628ec2
+  languageName: node
+  linkType: hard
+
 "@ampproject/remapping@npm:^2.2.0, @ampproject/remapping@npm:^2.3.0":
   version: 2.3.0
   resolution: "@ampproject/remapping@npm:2.3.0"
@@ -228,6 +535,38 @@ __metadata:
   languageName: node
   linkType: hard
 
+"@aws-crypto/crc32@npm:5.2.0":
+  version: 5.2.0
+  resolution: "@aws-crypto/crc32@npm:5.2.0"
+  dependencies:
+    "@aws-crypto/util": "npm:^5.2.0"
+    "@aws-sdk/types": "npm:^3.222.0"
+    tslib: "npm:^2.6.2"
+  checksum: 10c0/eab9581d3363af5ea498ae0e72de792f54d8890360e14a9d8261b7b5c55ebe080279fb2556e07994d785341cdaa99ab0b1ccf137832b53b5904cd6928f2b094b
+  languageName: node
+  linkType: hard
+
+"@aws-crypto/util@npm:^5.2.0":
+  version: 5.2.0
+  resolution: "@aws-crypto/util@npm:5.2.0"
+  dependencies:
+    "@aws-sdk/types": "npm:^3.222.0"
+    "@smithy/util-utf8": "npm:^2.0.0"
+    tslib: "npm:^2.6.2"
+  checksum: 10c0/0362d4c197b1fd64b423966945130207d1fe23e1bb2878a18e361f7743c8d339dad3f8729895a29aa34fff6a86c65f281cf5167c4bf253f21627ae80b6dd2951
+  languageName: node
+  linkType: hard
+
+"@aws-sdk/types@npm:^3.222.0":
+  version: 3.821.0
+  resolution: "@aws-sdk/types@npm:3.821.0"
+  dependencies:
+    "@smithy/types": "npm:^4.3.1"
+    tslib: "npm:^2.6.2"
+  checksum: 10c0/6202b2c0db1dd5ee78e6dc45c51f8b19deff0ee400dd5a7a15d089cc5493a2db6a6e0553ff32742e8bc810d428b36599534e14c1b466695550aef1b1d87f043d
+  languageName: node
+  linkType: hard
+
 "@babel/code-frame@npm:^7.10.4":
   version: 7.27.1
   resolution: "@babel/code-frame@npm:7.27.1"
@@ -509,6 +848,73 @@ __metadata:
   languageName: node
   linkType: hard
 
+"@cherry-studio/ai-core@workspace:packages/aiCore":
+  version: 0.0.0-use.local
+  resolution: "@cherry-studio/ai-core@workspace:packages/aiCore"
+  dependencies:
+    "@ai-sdk/amazon-bedrock": "npm:^2.2.10"
+    "@ai-sdk/anthropic": "npm:^1.2.12"
+    "@ai-sdk/azure": "npm:^1.3.23"
+    "@ai-sdk/cerebras": "npm:^0.2.14"
+    "@ai-sdk/cohere": "npm:^1.2.10"
+    "@ai-sdk/deepinfra": "npm:^0.2.15"
+    "@ai-sdk/deepseek": "npm:^0.2.14"
+    "@ai-sdk/fal": "npm:^0.1.12"
+    "@ai-sdk/fireworks": "npm:^0.2.14"
+    "@ai-sdk/google": "npm:^1.2.19"
+    "@ai-sdk/google-vertex": "npm:^2.2.24"
+    "@ai-sdk/groq": "npm:^1.2.9"
+    "@ai-sdk/mistral": "npm:^1.2.8"
+    "@ai-sdk/openai": "npm:^1.3.22"
+    "@ai-sdk/perplexity": "npm:^1.1.9"
+    "@ai-sdk/replicate": "npm:^0.2.8"
+    "@ai-sdk/togetherai": "npm:^0.2.14"
+    "@ai-sdk/vercel": "npm:^0.0.1"
+    "@ai-sdk/xai": "npm:^1.2.16"
+    ai: "npm:^4.3.16"
+    typescript: "npm:^5.0.0"
+  peerDependenciesMeta:
+    "@ai-sdk/amazon-bedrock":
+      optional: true
+    "@ai-sdk/anthropic":
+      optional: true
+    "@ai-sdk/azure":
+      optional: true
+    "@ai-sdk/cerebras":
+      optional: true
+    "@ai-sdk/cohere":
+      optional: true
+    "@ai-sdk/deepinfra":
+      optional: true
+    "@ai-sdk/deepseek":
+      optional: true
+    "@ai-sdk/fal":
+      optional: true
+    "@ai-sdk/fireworks":
+      optional: true
+    "@ai-sdk/google":
+      optional: true
+    "@ai-sdk/google-vertex":
+      optional: true
+    "@ai-sdk/groq":
+      optional: true
+    "@ai-sdk/mistral":
+      optional: true
+    "@ai-sdk/openai":
+      optional: true
+    "@ai-sdk/perplexity":
+      optional: true
+    "@ai-sdk/replicate":
+      optional: true
+    "@ai-sdk/together":
+      optional: true
+    "@ai-sdk/vercel":
+      optional: true
+    "@ai-sdk/xai":
+      optional: true
+  languageName: unknown
+  linkType: soft
+
 "@cherrystudio/embedjs-interfaces@npm:0.1.30":
   version: 0.1.30
   resolution: "@cherrystudio/embedjs-interfaces@npm:0.1.30"
@@ -3184,6 +3590,13 @@ __metadata:
   languageName: node
   linkType: hard
 
+"@opentelemetry/api@npm:1.9.0":
+  version: 1.9.0
+  resolution: "@opentelemetry/api@npm:1.9.0"
+  checksum: 10c0/9aae2fe6e8a3a3eeb6c1fdef78e1939cf05a0f37f8a4fae4d6bf2e09eb1e06f966ece85805626e01ba5fab48072b94f19b835449e58b6d26720ee19a58298add
+  languageName: node
+  linkType: hard
+
 "@parcel/watcher-android-arm64@npm:2.5.1":
   version: 2.5.1
   resolution: "@parcel/watcher-android-arm64@npm:2.5.1"
@@ -3815,6 +4228,94 @@ __metadata:
   languageName: node
   linkType: hard
 
+"@smithy/eventstream-codec@npm:^4.0.1":
+  version: 4.0.4
+  resolution: "@smithy/eventstream-codec@npm:4.0.4"
+  dependencies:
+    "@aws-crypto/crc32": "npm:5.2.0"
+    "@smithy/types": "npm:^4.3.1"
+    "@smithy/util-hex-encoding": "npm:^4.0.0"
+    tslib: "npm:^2.6.2"
+  checksum: 10c0/89b76826d4d3bf97317e3539ece105b9a03552144ad816a687b0b2cbca60e2b3513062c04b6cfacaffb270d616ffc8ac8bf549afc4aa676a6d7465df5a3215ba
+  languageName: node
+  linkType: hard
+
+"@smithy/is-array-buffer@npm:^2.2.0":
+  version: 2.2.0
+  resolution: "@smithy/is-array-buffer@npm:2.2.0"
+  dependencies:
+    tslib: "npm:^2.6.2"
+  checksum: 10c0/2f2523cd8cc4538131e408eb31664983fecb0c8724956788b015aaf3ab85a0c976b50f4f09b176f1ed7bbe79f3edf80743be7a80a11f22cd9ce1285d77161aaf
+  languageName: node
+  linkType: hard
+
+"@smithy/is-array-buffer@npm:^4.0.0":
+  version: 4.0.0
+  resolution: "@smithy/is-array-buffer@npm:4.0.0"
+  dependencies:
+    tslib: "npm:^2.6.2"
+  checksum: 10c0/ae393fbd5944d710443cd5dd225d1178ef7fb5d6259c14f3e1316ec75e401bda6cf86f7eb98bfd38e5ed76e664b810426a5756b916702cbd418f0933e15e7a3b
+  languageName: node
+  linkType: hard
+
+"@smithy/types@npm:^4.3.1":
+  version: 4.3.1
+  resolution: "@smithy/types@npm:4.3.1"
+  dependencies:
+    tslib: "npm:^2.6.2"
+  checksum: 10c0/8b350562b9ed4ff97465025b4ae77a34bb07b9d47fb6f9781755aac9401b0355a63c2fef307393e2dae3fa0277149dd7d83f5bc2a63d4ad3519ea32fd56b5cda
+  languageName: node
+  linkType: hard
+
+"@smithy/util-buffer-from@npm:^2.2.0":
+  version: 2.2.0
+  resolution: "@smithy/util-buffer-from@npm:2.2.0"
+  dependencies:
+    "@smithy/is-array-buffer": "npm:^2.2.0"
+    tslib: "npm:^2.6.2"
+  checksum: 10c0/223d6a508b52ff236eea01cddc062b7652d859dd01d457a4e50365af3de1e24a05f756e19433f6ccf1538544076b4215469e21a4ea83dc1d58d829725b0dbc5a
+  languageName: node
+  linkType: hard
+
+"@smithy/util-buffer-from@npm:^4.0.0":
+  version: 4.0.0
+  resolution: "@smithy/util-buffer-from@npm:4.0.0"
+  dependencies:
+    "@smithy/is-array-buffer": "npm:^4.0.0"
+    tslib: "npm:^2.6.2"
+  checksum: 10c0/be7cd33b6cb91503982b297716251e67cdca02819a15797632091cadab2dc0b4a147fff0709a0aa9bbc0b82a2644a7ed7c8afdd2194d5093cee2e9605b3a9f6f
+  languageName: node
+  linkType: hard
+
+"@smithy/util-hex-encoding@npm:^4.0.0":
+  version: 4.0.0
+  resolution: "@smithy/util-hex-encoding@npm:4.0.0"
+  dependencies:
+    tslib: "npm:^2.6.2"
+  checksum: 10c0/70dbb3aa1a79aff3329d07a66411ff26398df338bdd8a6d077b438231afe3dc86d9a7022204baddecd8bc633f059d5c841fa916d81dd7447ea79b64148f386d2
+  languageName: node
+  linkType: hard
+
+"@smithy/util-utf8@npm:^2.0.0":
+  version: 2.3.0
+  resolution: "@smithy/util-utf8@npm:2.3.0"
+  dependencies:
+    "@smithy/util-buffer-from": "npm:^2.2.0"
+    tslib: "npm:^2.6.2"
+  checksum: 10c0/e18840c58cc507ca57fdd624302aefd13337ee982754c9aa688463ffcae598c08461e8620e9852a424d662ffa948fc64919e852508028d09e89ced459bd506ab
+  languageName: node
+  linkType: hard
+
+"@smithy/util-utf8@npm:^4.0.0":
+  version: 4.0.0
+  resolution: "@smithy/util-utf8@npm:4.0.0"
+  dependencies:
+    "@smithy/util-buffer-from": "npm:^4.0.0"
+    tslib: "npm:^2.6.2"
+  checksum: 10c0/28a5a5372cbf0b3d2e32dd16f79b04c2aec6f704cf13789db922e9686fde38dde0171491cfa4c2c201595d54752a319faaeeed3c325329610887694431e28c98
+  languageName: node
+  linkType: hard
+
 "@strongtz/win32-arm64-msvc@npm:^0.4.7":
   version: 0.4.7
   resolution: "@strongtz/win32-arm64-msvc@npm:0.4.7"
@@ -4394,6 +4895,13 @@ __metadata:
   languageName: node
   linkType: hard
 
+"@types/diff-match-patch@npm:^1.0.36":
+  version: 1.0.36
+  resolution: "@types/diff-match-patch@npm:1.0.36"
+  checksum: 10c0/0bad011ab138baa8bde94e7815064bb881f010452463272644ddbbb0590659cb93f7aa2776ff442c6721d70f202839e1053f8aa62d801cc4166f7a3ea9130055
+  languageName: node
+  linkType: hard
+
 "@types/diff@npm:^7":
   version: 7.0.2
   resolution: "@types/diff@npm:7.0.2"
@@ -5824,6 +6332,26 @@ __metadata:
   languageName: node
   linkType: hard
 
+"ai@npm:^4.3.16":
+  version: 4.3.16
+  resolution: "ai@npm:4.3.16"
+  dependencies:
+    "@ai-sdk/provider": "npm:1.1.3"
+    "@ai-sdk/provider-utils": "npm:2.2.8"
+    "@ai-sdk/react": "npm:1.2.12"
+    "@ai-sdk/ui-utils": "npm:1.2.11"
+    "@opentelemetry/api": "npm:1.9.0"
+    jsondiffpatch: "npm:0.6.0"
+  peerDependencies:
+    react: ^18 || ^19 || ^19.0.0-rc
+    zod: ^3.23.8
+  peerDependenciesMeta:
+    react:
+      optional: true
+  checksum: 10c0/befe761c9386cda6de33370a2590900352b444d81959255c624e2bfd40765f126d29269f0ef3e00bde07daf237004aa0b66d0b253664aa478c148e923ce78c41
+  languageName: node
+  linkType: hard
+
 "ajv-formats@npm:^2.1.1":
   version: 2.1.1
   resolution: "ajv-formats@npm:2.1.1"
@@ -6232,6 +6760,13 @@ __metadata:
   languageName: node
   linkType: hard
 
+"aws4fetch@npm:^1.0.20":
+  version: 1.0.20
+  resolution: "aws4fetch@npm:1.0.20"
+  checksum: 10c0/a4eac7bd0d1c3e611c17ed1ef41ac0b48c0a8e74a985ad968c071e74d94586d3572edc943b43fa5ca756c686ea73baa2f48e264d657bb8c2e95c8e0037d48a87
+  languageName: node
+  linkType: hard
+
 "axios@npm:^1.7.3":
   version: 1.8.4
   resolution: "axios@npm:1.8.4"
@@ -6736,7 +7271,7 @@ __metadata:
   languageName: node
   linkType: hard
 
-"chalk@npm:^5.4.1":
+"chalk@npm:^5.3.0, chalk@npm:^5.4.1":
   version: 5.4.1
   resolution: "chalk@npm:5.4.1"
   checksum: 10c0/b23e88132c702f4855ca6d25cb5538b1114343e41472d5263ee8a37cccfccd9c4216d111e1097c6a27830407a1dc81fecdf2a56f2c63033d4dbbd88c10b0dcef
@@ -8169,6 +8704,13 @@ __metadata:
   languageName: node
   linkType: hard
 
+"diff-match-patch@npm:^1.0.5":
+  version: 1.0.5
+  resolution: "diff-match-patch@npm:1.0.5"
+  checksum: 10c0/142b6fad627b9ef309d11bd935e82b84c814165a02500f046e2773f4ea894d10ed3017ac20454900d79d4a0322079f5b713cf0986aaf15fce0ec4a2479980c86
+  languageName: node
+  linkType: hard
+
 "diff@npm:^7.0.0":
   version: 7.0.0
   resolution: "diff@npm:7.0.0"
@@ -10258,7 +10800,7 @@ __metadata:
   languageName: node
   linkType: hard
 
-"google-auth-library@npm:^9.14.2":
+"google-auth-library@npm:^9.14.2, google-auth-library@npm:^9.15.0":
   version: 9.15.1
   resolution: "google-auth-library@npm:9.15.1"
   dependencies:
@@ -11458,6 +12000,13 @@ __metadata:
   languageName: node
   linkType: hard
 
+"json-schema@npm:^0.4.0":
+  version: 0.4.0
+  resolution: "json-schema@npm:0.4.0"
+  checksum: 10c0/d4a637ec1d83544857c1c163232f3da46912e971d5bf054ba44fdb88f07d8d359a462b4aec46f2745efbc57053365608d88bc1d7b1729f7b4fc3369765639ed3
+  languageName: node
+  linkType: hard
+
 "json-stable-stringify-without-jsonify@npm:^1.0.1":
   version: 1.0.1
   resolution: "json-stable-stringify-without-jsonify@npm:1.0.1"
@@ -11490,6 +12039,19 @@ __metadata:
   languageName: node
   linkType: hard
 
+"jsondiffpatch@npm:0.6.0":
+  version: 0.6.0
+  resolution: "jsondiffpatch@npm:0.6.0"
+  dependencies:
+    "@types/diff-match-patch": "npm:^1.0.36"
+    chalk: "npm:^5.3.0"
+    diff-match-patch: "npm:^1.0.5"
+  bin:
+    jsondiffpatch: bin/jsondiffpatch.js
+  checksum: 10c0/f7822e48a8ef8b9f7c6024cc59b7d3707a9fe6d84fd776d169de5a1803ad551ffe7cfdc7587f3900f224bc70897355884ed43eb1c8ccd02e7f7b43a7ebcfed4f
+  languageName: node
+  linkType: hard
+
 "jsonfile@npm:^4.0.0":
   version: 4.0.0
   resolution: "jsonfile@npm:4.0.0"
@@ -16438,6 +17000,13 @@ __metadata:
   languageName: node
   linkType: hard
 
+"secure-json-parse@npm:^2.7.0":
+  version: 2.7.0
+  resolution: "secure-json-parse@npm:2.7.0"
+  checksum: 10c0/f57eb6a44a38a3eeaf3548228585d769d788f59007454214fab9ed7f01fbf2e0f1929111da6db28cf0bcc1a2e89db5219a59e83eeaec3a54e413a0197ce879e4
+  languageName: node
+  linkType: hard
+
 "seek-bzip@npm:^1.0.5":
   version: 1.0.6
   resolution: "seek-bzip@npm:1.0.6"
@@ -17214,6 +17783,18 @@ __metadata:
   languageName: node
   linkType: hard
 
+"swr@npm:^2.2.5":
+  version: 2.3.3
+  resolution: "swr@npm:2.3.3"
+  dependencies:
+    dequal: "npm:^2.0.3"
+    use-sync-external-store: "npm:^1.4.0"
+  peerDependencies:
+    react: ^16.11.0 || ^17.0.0 || ^18.0.0 || ^19.0.0
+  checksum: 10c0/882fc8291912860e0c50eae3470ebf0cd58b0144cb12adcc4b14c5cef913ea06479043830508d8b0b3d4061d99ad8dd52485c9c879fbd4e9b893484e6d8da9e3
+  languageName: node
+  linkType: hard
+
 "symbol-tree@npm:^3.2.4":
   version: 3.2.4
   resolution: "symbol-tree@npm:3.2.4"
@@ -17361,6 +17942,13 @@ __metadata:
   languageName: node
   linkType: hard
 
+"throttleit@npm:2.1.0":
+  version: 2.1.0
+  resolution: "throttleit@npm:2.1.0"
+  checksum: 10c0/1696ae849522cea6ba4f4f3beac1f6655d335e51b42d99215e196a718adced0069e48deaaf77f7e89f526ab31de5b5c91016027da182438e6f9280be2f3d5265
+  languageName: node
+  linkType: hard
+
 "through2@npm:4.0.2":
   version: 4.0.2
   resolution: "through2@npm:4.0.2"
@@ -17673,7 +18261,7 @@ __metadata:
   languageName: node
   linkType: hard
 
-"tslib@npm:^2.0.1, tslib@npm:^2.1.0, tslib@npm:^2.4.0, tslib@npm:^2.8.1":
+"tslib@npm:^2.0.1, tslib@npm:^2.1.0, tslib@npm:^2.4.0, tslib@npm:^2.6.2, tslib@npm:^2.8.1":
   version: 2.8.1
   resolution: "tslib@npm:2.8.1"
   checksum: 10c0/9c4759110a19c53f992d9aae23aac5ced636e99887b51b9e61def52611732872ff7668757d4e4c61f19691e36f4da981cd9485e869b4a7408d689f6bf1f14e62
@@ -17753,7 +18341,7 @@ __metadata:
   languageName: node
   linkType: hard
 
-"typescript@npm:^5.4.3, typescript@npm:^5.6.2":
+"typescript@npm:^5.0.0, typescript@npm:^5.4.3, typescript@npm:^5.6.2":
   version: 5.8.3
   resolution: "typescript@npm:5.8.3"
   bin:
@@ -17763,7 +18351,7 @@ __metadata:
   languageName: node
   linkType: hard
 
-"typescript@patch:typescript@npm%3A^5.4.3#optional!builtin<compat/typescript>, typescript@patch:typescript@npm%3A^5.6.2#optional!builtin<compat/typescript>":
+"typescript@patch:typescript@npm%3A^5.0.0#optional!builtin<compat/typescript>, typescript@patch:typescript@npm%3A^5.4.3#optional!builtin<compat/typescript>, typescript@patch:typescript@npm%3A^5.6.2#optional!builtin<compat/typescript>":
   version: 5.8.3
   resolution: "typescript@patch:typescript@npm%3A5.8.3#optional!builtin<compat/typescript>::version=5.8.3&hash=5786d5"
   bin: