agentkits - npm Package Compare versions

Comparing version 1.10.2 to 2.0.0

dist/cost/cost.test.js

@@ -42,2 +42,31 @@ import { describe, it, expect } from 'vitest';
 });
+describe('getPricing – new providers', () => {
+    it('returns grok pricing', () => {
+        const result = getPricing('grok');
+        expect(result.length).toBeGreaterThan(0);
+        expect(result[0].provider).toBe('grok');
+    });
+    it('returns cohere LLM and embedding pricing', () => {
+        const result = getPricing('cohere');
+        expect(result.length).toBeGreaterThanOrEqual(2);
+        const llm = result.find(p => p.model === 'command-r-plus');
+        const emb = result.find(p => p.model === 'embed-english-v3.0');
+        expect(llm).toBeDefined();
+        expect(emb).toBeDefined();
+        expect(emb.embeddingPer1M).toBe(0.10);
+    });
+    it.each(['grok', 'groq', 'perplexity'])('estimateCost works for %s', (provider) => {
+        const cost = estimateCost(provider, { promptTokens: 1000, completionTokens: 500 });
+        expect(cost.totalCost).toBeGreaterThan(0);
+    });
+    it.each(['yi', 'baichuan', 'siliconflow', 'stepfun', 'fireworks', 'together'])('estimateCost works for %s', (provider) => {
+        const cost = estimateCost(provider, { promptTokens: 1000, completionTokens: 500 });
+        expect(cost.totalCost).toBeGreaterThan(0);
+    });
+    it.each(['jina', 'voyage'])('getPricing returns embedding for %s', (provider) => {
+        const result = getPricing(provider);
+        expect(result.length).toBeGreaterThan(0);
+        expect(result[0].embeddingPer1M).toBeDefined();
+    });
+});
 describe('comparePricing', () => {
@@ -44,0 +73,0 @@ it('returns LLM pricing by default', () => {

dist/cost/index.js

@@ -27,2 +27,12 @@ /**
     { provider: 'minimax', model: 'MiniMax-Text-01', currency: 'CNY', inputPer1M: 1.00, outputPer1M: 8.00, updated: '2026-04' },
+    { provider: 'grok', model: 'grok-3', currency: 'USD', inputPer1M: 3.00, outputPer1M: 15.00, updated: '2026-04' },
+    { provider: 'cohere', model: 'command-r-plus', currency: 'USD', inputPer1M: 2.50, outputPer1M: 10.00, updated: '2026-04' },
+    { provider: 'yi', model: 'yi-large', currency: 'CNY', inputPer1M: 20.00, outputPer1M: 20.00, updated: '2026-04' },
+    { provider: 'baichuan', model: 'Baichuan4', currency: 'CNY', inputPer1M: 100.00, outputPer1M: 100.00, updated: '2026-04' },
+    { provider: 'siliconflow', model: 'deepseek-ai/DeepSeek-V3', currency: 'CNY', inputPer1M: 2.00, outputPer1M: 8.00, updated: '2026-04' },
+    { provider: 'stepfun', model: 'step-2-16k', currency: 'CNY', inputPer1M: 38.00, outputPer1M: 120.00, updated: '2026-04' },
+    { provider: 'fireworks', model: 'accounts/fireworks/models/llama-v3p1-70b-instruct', currency: 'USD', inputPer1M: 0.90, outputPer1M: 0.90, updated: '2026-04' },
+    { provider: 'together', model: 'meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo', currency: 'USD', inputPer1M: 0.88, outputPer1M: 0.88, updated: '2026-04' },
+    { provider: 'groq', model: 'llama-3.3-70b-versatile', currency: 'USD', inputPer1M: 0.59, outputPer1M: 0.79, updated: '2026-04' },
+    { provider: 'perplexity', model: 'sonar-pro', currency: 'USD', inputPer1M: 3.00, outputPer1M: 15.00, updated: '2026-04' },
     { provider: 'ollama', model: 'any', currency: 'USD', inputPer1M: 0, outputPer1M: 0, updated: '2026-04' },
@@ -36,2 +46,5 @@ // Embedding
     { provider: 'zhipu', model: 'embedding-3', currency: 'CNY', inputPer1M: 0.50, outputPer1M: 0, embeddingPer1M: 0.50, updated: '2026-04' },
+    { provider: 'cohere', model: 'embed-english-v3.0', currency: 'USD', inputPer1M: 0.10, outputPer1M: 0, embeddingPer1M: 0.10, updated: '2026-04' },
+    { provider: 'jina', model: 'jina-embeddings-v3', currency: 'USD', inputPer1M: 0.02, outputPer1M: 0, embeddingPer1M: 0.02, updated: '2026-04' },
+    { provider: 'voyage', model: 'voyage-3', currency: 'USD', inputPer1M: 0.06, outputPer1M: 0, embeddingPer1M: 0.06, updated: '2026-04' },
     { provider: 'ollama', model: 'nomic-embed-text', currency: 'USD', inputPer1M: 0, outputPer1M: 0, embeddingPer1M: 0, updated: '2026-04' },
@@ -38,0 +51,0 @@ ];

package.json

 {
   "name": "agentkits",
-  "version": "1.10.2",
+  "version": "2.0.0",
   "description": "Multi-provider AI toolkit for agents. One interface, any model.",
@@ -13,5 +13,4 @@ "type": "module",
     ".": {
-      "types": "./dist/index.d.ts",
       "import": "./dist/index.js",
-      "default": "./dist/index.js"
+      "types": "./dist/index.d.ts"
     },
@@ -18,0 +17,0 @@ "./errors": {

README.md

 <div align="center">
 
-# 📊 AgentKits
+# 🧰 AgentKits
 
-**带记忆的 OpenRouter：统一模型 API + 智能推荐 + 记忆增强**
+**多模型 AI 智能体工具库 · Multi-provider AI toolkit for agents**
 
-[![npm version](https://img.shields.io/badge/npm-v1.9.0-blue?style=flat-square)](https://www.npmjs.com/package/agentkits)
+[![npm version](https://img.shields.io/npm/v/agentkits.svg?style=flat-square)](https://www.npmjs.com/package/agentkits)
 [![License](https://img.shields.io/badge/license-Apache--2.0-blue.svg?style=flat-square)](LICENSE)
 [![TypeScript](https://img.shields.io/badge/TypeScript-5.7+-blue.svg?style=flat-square)](https://www.typescriptlang.org/)
+[![Tests](https://img.shields.io/badge/tests-571%20passing-brightgreen.svg?style=flat-square)](#)
+[![Node.js](https://img.shields.io/badge/node-%3E%3D18-green.svg?style=flat-square)](https://nodejs.org/)
 
-**一个 API 接入所有 LLM，自动推荐最优模型，每次调用自带记忆增强。**
+*19 个大模型 · 15 个向量化引擎 · 40 个功能模块 · 零锁定*
 
-[快速开始](#快速开始) · [功能亮点](#功能亮点) · [模型列表](#支持模型) · [API 参考](#api-参考) · [English](#english-version)
+[Quick Start](#快速开始-quick-start) · [Providers](#大模型供应商-llm-providers) · [Modules](#模块目录-module-catalog)
 
@@ -19,247 +21,260 @@ </div>
 
-## 快速开始
+## 为什么选择 AgentKits？
 
-```bash
-npm install agentkits
-```
+构建 AI 智能体不应被锁定在单一供应商。AgentKits 提供**统一接口**，覆盖 19 个大模型和 15 个向量化引擎。切换模型只需改一个配置，无需重写代码。
 
-```typescript
-import { recommendModel, createChat, withBrain } from 'agentkits';
+> **🇨🇳 深度支持中国大模型生态**：通义千问、智谱AI、月之暗面、零一万物、硅基流动、阶跃星辰、百川智能、DeepSeek深度求索、MiniMax — 一等公民，不是附加品。
 
-// 🎯 智能推荐：按任务 + 预算自动选最优模型
-const picks = recommendModel({ task: 'coding', budget: 'medium' });
-console.log(picks[0]);
-// { model: 'deepseek-coder-v2', provider: 'deepseek', reason: 'Best cost/perf for coding tasks', ... }
+```ts
+import { createChat, createEmbedding } from 'agentkits';
 
-// 🤖 统一调用：切换供应商只改一个词
-const chat = createChat({ provider: 'deepseek', model: 'deepseek-chat' });
-const reply = await chat.complete('用 TypeScript 写一个快排');
+// 切换供应商只需改一个词
+const chat = createChat({ provider: 'deepseek' });  // 深度求索
+const reply = await chat.complete('解释量子计算');
 
-// 🧠 记忆增强：自动从 DeepBrain 召回上下文
-const smartChat = withBrain(chat.complete.bind(chat), { brainUrl: 'http://localhost:3333' });
-const response = await smartChat({ messages: [{ role: 'user', content: '继续优化昨天的方案' }] });
+const emb = createEmbedding({ provider: 'dashscope' });  // 通义千问
+const vector = await emb.embed('你好世界');
 ```
 
----
+## 快速开始 Quick Start
 
-## 功能亮点
+```bash
+npm install agentkits
+```
 
-| | 功能 | 说明 |
-|---|---|---|
-| 🤖 | **统一模型 API** | OpenAI / Anthropic / Google / DeepSeek / 通义 / 智谱 / Moonshot / Ollama — 一个接口搞定 |
-| 🎯 | **智能推荐** | `recommendModel()` 按任务 + 预算 + 速度推荐最优模型 |
-| 💰 | **成本估算** | `estimateModelCost()` 20+ 模型精确定价，按 token 算钱 |
-| 🏥 | **健康检查** | `checkProvider()` 7 个 provider 实时可用性 + 延迟检测 |
-| 🧠 | **记忆增强** | `withBrain()` 每次调用自动串联 DeepBrain，recall → chat → learn |
-| 🎨 | **Web UI** | `KitsUI` 模型管理面板 + Playground，零配置启动 |
-| 📊 | **40 个模块** | RAG / Agent / 工作流 / MCP / A2A / 视觉 / TTS / STT / 护栏 |
+### 对话补全 Chat
 
----
+```ts
+import { createChat } from 'agentkits';
 
-## 支持模型
+// 使用任意供应商
+const chat = createChat({ provider: 'deepseek', model: 'deepseek-chat' });
+const reply = await chat.complete('你好！');
 
-### LLM 大模型 (19 providers)
+// 流式输出
+for await (const chunk of chat.stream('给我讲个故事')) {
+  process.stdout.write(chunk.content ?? '');
+}
+```
 
-| 模型 | 供应商 | 输入价格 ($/1M tokens) | 输出价格 ($/1M tokens) | 上下文窗口 | 最佳场景 |
-|------|--------|----------------------|----------------------|-----------|---------|
-| gpt-4o | OpenAI | $2.50 | $10.00 | 128K | 通用、视觉、编程 |
-| gpt-4o-mini | OpenAI | $0.15 | $0.60 | 128K | 简单任务、快速 |
-| claude-3.5-sonnet | Anthropic | $3.00 | $15.00 | 200K | 推理、编程 |
-| claude-3-haiku | Anthropic | $0.25 | $1.25 | 200K | 快速、低成本 |
-| gemini-1.5-pro | Google | $1.25 | $5.00 | 2M | 超长上下文分析 |
-| gemini-2.5-flash | Google | $0.15 | $0.60 | 1M | 快速、低成本 |
-| deepseek-chat | DeepSeek 深度求索 | $0.14 | $0.28 | 128K | GPT-4 级质量，极致性价比 |
-| deepseek-reasoner | DeepSeek 深度求索 | $0.55 | $2.19 | 128K | 深度推理 |
-| qwen-turbo | 通义千问 | $0.04 | $0.08 | 128K | 快速、超低成本 |
-| qwen-plus | 通义千问 | $0.11 | $0.28 | 128K | 中等质量 |
-| glm-4-flash | 智谱 AI | $0.01 | $0.01 | 128K | 近乎免费 |
-| glm-4-plus | 智谱 AI | $7.00 | $7.00 | 128K | 高质量中文 |
-| moonshot-v1-8k | 月之暗面 (Kimi) | $0.17 | $0.17 | 8K | 中文对话 |
-| grok-2 | xAI | — | — | 128K | 实时信息 |
-| 本地模型 | Ollama | 免费 | 免费 | 可变 | Llama3 / Qwen2.5 / 任意 |
+### 向量化 Embedding
 
-还支持：Yi (零一万物)、Baichuan (百川)、SiliconFlow (硅基流动)、StepFun (阶跃星辰)、MiniMax、Cohere、Fireworks、Together、Groq、Perplexity、Custom (任意 OpenAI 兼容)。
+```ts
+import { createEmbedding } from 'agentkits';
 
-### 向量化引擎 (15 providers)
+const emb = createEmbedding({ provider: 'dashscope' });  // 通义千问向量化
+const vector = await emb.embed('语义搜索');
+const batch = await emb.embedBatch(['文档1', '文档2', '文档3']);
+```
 
-| 模型 | 供应商 | 维度 | 价格 ($/1M tokens) |
-|------|--------|------|-------------------|
-| text-embedding-3-small | OpenAI | 1536 | $0.02 |
-| text-embedding-3-large | OpenAI | 3072 | $0.13 |
-| text-embedding-004 | Google | 768 | — |
-| text-embedding-v3 | 通义千问 | 1024 | — |
-| embedding-3 | 智谱 AI | 2048 | — |
-| jina-embeddings-v3 | Jina | 1024 | — |
-| nomic-embed-text | Ollama | 768 | 免费 |
+### 函数调用 Tool Calling
 
-还支持：DeepSeek、SiliconFlow、Cohere、Voyage、Mixedbread、Fireworks、Together、Custom。
+```ts
+import { createToolChat, defineTool } from 'agentkits';
 
----
+const weather = defineTool({
+  name: 'get_weather',
+  description: '获取城市天气',
+  parameters: { type: 'object', properties: { city: { type: 'string' } }, required: ['city'] },
+  handler: async ({ city }) => `${city}：晴，25°C`,
+});
 
-## API 参考
+const chat = createToolChat({ provider: 'zhipu', tools: [weather] });  // 智谱AI
+const result = await chat.run('北京今天天气怎么样？');
+```
 
-### 智能推荐
+### 工作流引擎 Workflow
 
-```typescript
-import { recommendModel, estimateModelCost } from 'agentkits';
+```ts
+import { createWorkflow } from 'agentkits';
 
-// 按任务 + 预算推荐
-const picks = recommendModel({
-  task: 'coding',           // 'chat' | 'coding' | 'analysis' | 'embedding' | 'vision'
-  budget: 'low',            // 'free' | 'low' | 'medium' | 'high'
-  speed: 'fast',            // 'fast' | 'medium' | 'slow'
-  local: false,             // true = 仅推荐 Ollama 本地模型
+const workflow = createWorkflow({
+  name: 'research-pipeline',
+  startStep: 'search',
+  steps: [
+    {
+      id: 'search', type: 'tool',
+      tool: { name: 'search', handler: async (input) => await searchWeb(input.query) },
+      input: (ctx) => ({ query: ctx.variables.topic }),
+      output: 'searchResults', next: 'summarize',
+    },
+    {
+      id: 'summarize', type: 'llm',
+      llm: { provider: 'deepseek', prompt: '总结以下内容：{{searchResults}}' },
+      output: 'summary',
+    },
+  ],
 });
-// → [{ model, provider, reason, estimatedCostPer1kTokens, speed, quality }]
-
-// 精确成本估算
-const cost = estimateModelCost('gpt-4o', 5000, 2000);
-// → { cost: 0.0325, currency: 'USD', breakdown: { input: 0.0125, output: 0.02 } }
 ```
 
-### 统一对话
+### MCP 客户端
 
-```typescript
-import { createChat } from 'agentkits';
+```ts
+import { createMCPClient } from 'agentkits';
 
-const chat = createChat({ provider: 'deepseek', model: 'deepseek-chat' });
-const reply = await chat.complete('你好');
-
-// 流式输出
-for await (const chunk of chat.stream('给我讲个故事')) {
-  process.stdout.write(chunk.content ?? '');
-}
+const mcp = await createMCPClient({ serverUrl: 'http://localhost:3001/sse' });
+const tools = await mcp.listTools();
+const result = await mcp.callTool('search', { query: 'hello' });
 ```
 
-### 记忆增强 (DeepBrain)
+### A2A 协议（Agent-to-Agent）
 
-```typescript
-import { withBrain, recall, learn } from 'agentkits';
+```ts
+import { createA2AClient, createA2AServer } from 'agentkits';
 
-// 中间件模式：自动 recall → chat → learn
-const smartChat = withBrain(originalChatFn, {
-  brainUrl: 'http://localhost:3333',
-  agentId: 'my-agent',
-  autoRecall: true,
-  autoLearn: true,
-  recallLimit: 5,
+const client = createA2AClient({ baseUrl: 'http://localhost:8080' });
+const card = await client.getAgentCard();
+const task = await client.sendTask({
+  id: 'task-1',
+  message: { role: 'user', parts: [{ type: 'text', text: '研究AI趋势' }] },
 });
-
-// 手动调用
-const memories = await recall('昨天的讨论', { brainUrl: 'http://localhost:3333' });
-await learn('新的知识点...', { brainUrl: 'http://localhost:3333' });
 ```
 
-### 健康检查
+### 可运行示例 Runnable Examples
 
-```typescript
-import { checkProvider } from 'agentkits';
+`examples/` 目录提供 6 个开箱即用的 `.mjs` 示例，`node` 直接运行：
 
-const status = await checkProvider('openai', { apiKey: 'sk-...' });
-// → { available: true, latencyMs: 234 }
+| 文件 | 说明 |
+|------|------|
+| [chat-basic.mjs](examples/chat-basic.mjs) | 最简对话（3 行代码）|
+| [chat-stream.mjs](examples/chat-stream.mjs) | 流式输出，逐字打印 |
+| [embedding-search.mjs](examples/embedding-search.mjs) | 文本向量化 + 余弦相似度搜索 |
+| [rag-pipeline.mjs](examples/rag-pipeline.mjs) | 完整 RAG 流程（分块 → 向量化 → 检索 → 生成）|
+| [multi-provider.mjs](examples/multi-provider.mjs) | 同一问题发给多个供应商，对比回答 |
+| [benchmark.mjs](examples/benchmark.mjs) | 响应速度、TTFT、Token 数基准测试 |
 
-// 支持的 provider: openai, anthropic, gemini, deepseek, moonshot, zhipu, ollama
+```bash
+# 设置环境变量
+export GEMINI_API_KEY=your-key
+
+# 运行任意示例
+node examples/chat-basic.mjs
+node examples/chat-stream.mjs
+node examples/embedding-search.mjs
+node examples/rag-pipeline.mjs
+node examples/multi-provider.mjs
+
+# 基准测试（支持 --providers 指定供应商）
+node examples/benchmark.mjs --providers gemini,deepseek,groq
 ```
 
-### Web UI
+---
 
-```typescript
-import { KitsUI } from 'agentkits';
+## 大模型供应商 LLM Providers (29)
 
-const ui = new KitsUI({ port: 4002 });
-await ui.start();
-// 打开 http://localhost:4002 → 模型管理面板 + Playground
-```
+| 供应商 Provider | 中文名 | 模型 Models | 流式 | 函数调用 | 视觉 |
+|---------|--------|------------|------|---------|------|
+| **OpenAI** | — | GPT-4o, GPT-4o-mini, o1, o3 | ✅ | ✅ | ✅ |
+| **Gemini** | — | Gemini 2.0/1.5 Pro/Flash | ✅ | ✅ | ✅ |
+| **DeepSeek** | 深度求索 | DeepSeek-V3, R1 | ✅ | ✅ | ❌ |
+| **DashScope** | 通义千问 | Qwen-Max/Plus/Turbo | ✅ | ✅ | ✅ |
+| **Zhipu** | 智谱AI | GLM-4, GLM-4V | ✅ | ✅ | ✅ |
+| **Moonshot** | 月之暗面 (Kimi) | moonshot-v1 | ✅ | ✅ | ❌ |
+| **Yi** | 零一万物 | Yi-Large | ✅ | ✅ | ❌ |
+| **Baichuan** | 百川智能 | Baichuan-4 | ✅ | ✅ | ❌ |
+| **SiliconFlow** | 硅基流动 | 多模型聚合 | ✅ | ✅ | ❌ |
+| **StepFun** | 阶跃星辰 | Step-2 | ✅ | ✅ | ❌ |
+| **MiniMax** | MiniMax | abab6.5s | ✅ | ✅ | ❌ |
+| **Grok** | — | grok-2 | ✅ | ✅ | ❌ |
+| **Cohere** | — | Command R+ | ✅ | ✅ | ❌ |
+| **Fireworks** | — | FireFunction, Mixtral | ✅ | ✅ | ❌ |
+| **Together** | — | Llama, Mixtral | ✅ | ✅ | ❌ |
+| **Groq** | — | Llama, Mixtral | ✅ | ✅ | ❌ |
+| **Perplexity** | — | Sonar | ✅ | ❌ | ❌ |
+| **Ollama** | 本地部署 | 任意本地模型 | ✅ | ✅ | ✅ |
+| **Custom** | 自定义 | 任意 OpenAI 兼容 | ✅ | ✅ | ✅ |
 
-### 更多能力
+### 向量化引擎 Embedding Providers (18)
 
-```typescript
-// 向量化
-import { createEmbedding } from 'agentkits';
-const emb = createEmbedding({ provider: 'openai' });
-const vector = await emb.embed('语义搜索');
+| 供应商 Provider | 中文名 | 模型 Models | 维度 |
+|---------|--------|------------|------|
+| **OpenAI** | — | text-embedding-3-small/large, ada-002 | 256–3072 |
+| **Gemini** | — | text-embedding-004 | 768 |
+| **DashScope** | 通义千问 | text-embedding-v3 | 1024 |
+| **DeepSeek** | 深度求索 | (兼容接口) | 可变 |
+| **Zhipu** | 智谱AI | embedding-3 | 2048 |
+| **SiliconFlow** | 硅基流动 | 多模型 | 可变 |
+| **Cohere** | — | embed-v3 | 1024 |
+| **Jina** | — | jina-embeddings-v3 | 1024 |
+| **Voyage** | — | voyage-3 | 1024 |
+| **Mixedbread** | — | mxbai-embed-large | 1024 |
+| **Nomic** | — | nomic-embed-text | 768 |
+| **Fireworks** | — | nomic, thenlper | 可变 |
+| **Together** | — | 多模型 | 可变 |
+| **Ollama** | 本地部署 | 任意本地模型 | 可变 |
+| **Custom** | 自定义 | 任意兼容接口 | 可变 |
 
-// 函数调用
-import { createToolChat, defineTool } from 'agentkits';
-const tool = defineTool({ name: 'search', description: '搜索', parameters: {...}, handler: async (p) => '...' });
-const chat = createToolChat({ provider: 'openai', tools: [tool] });
+---
 
-// RAG 管线
-import { createRAG } from 'agentkits';
-const rag = createRAG({ chatProvider: 'deepseek', embeddingProvider: 'openai' });
+## 模块目录 Module Catalog
 
-// Agent 循环
-import { createAgent } from 'agentkits';
-const agent = createAgent({ provider: 'openai', tools: [...] });
+### 核心 Core
 
-// 工作流引擎
-import { createWorkflow } from 'agentkits';
+| 模块 | 引入路径 | 说明 |
+|------|---------|------|
+| **大模型对话** | `agentkits/llm` | 统一对话补全接口，支持 19 个供应商 |
+| **向量化** | `agentkits/embedding` | 统一向量化接口，支持 15 个引擎 |
+| **流式输出** | `agentkits/streaming` | SSE 解析、流组合、中断控制 |
+| **结构化输出** | `agentkits/structured` | JSON Schema 校验的 LLM 输出 |
+| **函数调用** | `agentkits/function-calling` | 跨供应商的函数/工具调用格式转换 |
 
-// MCP 客户端
-import { createMCPClient } from 'agentkits';
+### 智能体构建 Agent Building
 
-// A2A 协议
-import { createA2AClient, createA2AServer } from 'agentkits';
+| 模块 | 引入路径 | 说明 |
+|------|---------|------|
+| **Agent 循环** | `agentkits/agent` | ReAct 风格智能体，支持工具调用循环 |
+| **工具调用** | `agentkits/tools` | 定义和执行工具，适配任意大模型 |
+| **多轮对话** | `agentkits/conversation` | 多轮对话管理，滑动窗口 |
+| **Agent 记忆** | `agentkits/agent-memory` | 短期/长期记忆，自动摘要 |
+| **提示词模板** | `agentkits/prompt-template` | Handlebars 风格模板引擎 |
+| **安全护栏** | `agentkits/guardrails` | 输入输出校验、内容过滤、PII 检测 |
 
-// 故障转移
-import { createChatWithFailover } from 'agentkits';
+### RAG 检索增强生成
 
-// 智能路由
-import { createRouter, createModelRouter } from 'agentkits';
+| 模块 | 引入路径 | 说明 |
+|------|---------|------|
+| **RAG 管线** | `agentkits/rag` | 完整的检索-增强-生成管线 |
+| **重排序** | `agentkits/rerank` | API 重排序（Cohere、Jina 等） |
+| **本地重排** | `agentkits/reranker` | Cross-encoder 本地重排序 |
+| **网页搜索** | `agentkits/web-search` | Brave、Tavily、Serper、SearXNG |
+| **PDF 解析** | `agentkits/pdf-parser` | PDF 文本提取与分块 |
+| **文本分块** | `agentkits/chunker` | 智能分块（固定、句子、递归、语义） |
 
-// 结构化输出、护栏、重排序、TTS、STT、图像生成...
-// 完整 40 个模块见下方模块目录
-```
+### 多模态 Multimodal
 
----
+| 模块 | 引入路径 | 说明 |
+|------|---------|------|
+| **视觉理解** | `agentkits/vision` | 跨供应商图像理解 |
+| **语音合成** | `agentkits/tts` | TTS（OpenAI、Azure、ElevenLabs） |
+| **语音识别** | `agentkits/stt` | STT 语音转文字 |
+| **图像生成** | `agentkits/image` | DALL-E、Stability 等 |
 
-## 模块目录 (40 modules)
+### 基础设施 Infrastructure
 
-<details>
-<summary>展开查看完整模块列表</summary>
+| 模块 | 引入路径 | 说明 |
+|------|---------|------|
+| **故障转移** | `agentkits/failover` | 自动供应商切换与健康检测 |
+| **智能路由** | `agentkits/router` | 按成本、速度、能力路由请求 |
+| **模型路由** | `agentkits/model-router` | 高级路由：模型画像与规则引擎 |
+| **限流器** | `agentkits/ratelimit` | Token bucket 限流 |
+| **供应商限流** | `agentkits/rate-limiter` | 按供应商限流（内置默认值） |
+| **响应缓存** | `agentkits/response-cache` | LRU + TTL 缓存 |
+| **重试** | `agentkits/retry` | 指数退避 + 抖动 |
+| **成本计算** | `agentkits/cost` | 跨供应商定价对比 |
+| **Token 计数** | `agentkits/token-counter` | 按模型精确计数 |
+| **代理服务器** | `agentkits/proxy` | OpenAI 兼容代理 |
+| **性能基准** | `agentkits/benchmark` | 供应商延迟与吞吐量基准测试 |
+| **供应商测试** | `agentkits/test` | 一键检测已配置供应商的连通性 |
+| **日志** | `agentkits/logger` | 结构化日志 |
+| **链路追踪** | `agentkits/tracing` | OpenTelemetry 兼容分布式追踪 |
+| **代码解释器** | `agentkits/code-interpreter` | 沙箱代码执行（JS、Python、Shell） |
+| **模型评估** | `agentkits/evaluation` | 多模型输出对比：延迟、成本、质量 |
 
-| 分类 | 模块 | 引入路径 | 说明 |
-|------|------|---------|------|
-| **核心** | 大模型对话 | `agentkits/llm` | 19 个供应商统一接口 |
-| | 向量化 | `agentkits/embedding` | 15 个引擎统一接口 |
-| | 流式输出 | `agentkits/streaming` | SSE 解析、流组合、中断控制 |
-| | 结构化输出 | `agentkits/structured` | JSON Schema 校验 |
-| | 函数调用 | `agentkits/function-calling` | 跨供应商工具调用格式转换 |
-| **智能体** | Agent 循环 | `agentkits/agent` | ReAct 风格智能体 |
-| | 工具调用 | `agentkits/tools` | 定义和执行工具 |
-| | 多轮对话 | `agentkits/conversation` | 滑动窗口管理 |
-| | 记忆 | `agentkits/agent-memory` | 短期/长期记忆、自动摘要 |
-| | 提示词模板 | `agentkits/prompt-template` | Handlebars 风格模板 |
-| | 安全护栏 | `agentkits/guardrails` | 输入输出校验、PII 检测 |
-| **RAG** | RAG 管线 | `agentkits/rag` | 检索-增强-生成 |
-| | 重排序 (API) | `agentkits/rerank` | Cohere / Jina 重排 |
-| | 重排序 (本地) | `agentkits/reranker` | Cross-encoder 本地重排 |
-| | 网页搜索 | `agentkits/web-search` | Brave / Tavily / Serper / SearXNG |
-| | PDF 解析 | `agentkits/pdf-parser` | 文本提取与分块 |
-| | 文本分块 | `agentkits/chunker` | 固定 / 句子 / 递归 / 语义 |
-| **多模态** | 视觉理解 | `agentkits/vision` | 跨供应商图像理解 |
-| | 语音合成 | `agentkits/tts` | OpenAI / Azure / ElevenLabs |
-| | 语音识别 | `agentkits/stt` | 语音转文字 |
-| | 图像生成 | `agentkits/image` | DALL-E / Stability |
-| **基础设施** | 故障转移 | `agentkits/failover` | 自动供应商切换 |
-| | 智能路由 | `agentkits/router` | 按成本/速度/能力路由 |
-| | 模型路由 | `agentkits/model-router` | 规则引擎 |
-| | 限流器 | `agentkits/ratelimit` | Token bucket |
-| | 供应商限流 | `agentkits/rate-limiter` | 按供应商限流 |
-| | 响应缓存 | `agentkits/response-cache` | LRU + TTL |
-| | 重试 | `agentkits/retry` | 指数退避 + 抖动 |
-| | 成本计算 | `agentkits/cost` | 跨供应商定价对比 |
-| | Token 计数 | `agentkits/token-counter` | 按模型精确计数 |
-| | 代理服务器 | `agentkits/proxy` | OpenAI 兼容代理 |
-| | 基准测试 | `agentkits/benchmark` | 延迟与吞吐量 |
-| | 供应商测试 | `agentkits/test` | 一键检测连通性 |
-| | 日志 | `agentkits/logger` | 结构化日志 |
-| | 链路追踪 | `agentkits/tracing` | OpenTelemetry 兼容 |
-| | 代码解释器 | `agentkits/code-interpreter` | 沙箱执行 JS/Python/Shell |
-| | 模型评估 | `agentkits/evaluation` | 多模型输出对比 |
-| **协议** | MCP 客户端 | `agentkits/mcp-client` | 连接 MCP 服务器 |
-| | 工作流引擎 | `agentkits/workflow` | 分支 / 并行 / 重试 |
-| | A2A 协议 | `agentkits/a2a` | Google Agent-to-Agent |
+### 协议与互操作 Protocol & Interop
 
-</details>
+| 模块 | 引入路径 | 说明 |
+|------|---------|------|
+| **MCP 客户端** | `agentkits/mcp-client` | 连接 MCP 服务器，自动转换工具定义 |
+| **工作流引擎** | `agentkits/workflow` | 多步骤工作流：分支、并行、重试 |
+| **A2A 协议** | `agentkits/a2a` | Google A2A 智能体间通信 |
 
@@ -271,10 +286,10 @@ ---
 ```bash
-npx agentkits chat       [--provider P] [--model M]      # 交互式对话
-npx agentkits embed      "文本" [--provider P]            # 生成向量
-npx agentkits benchmark  [--providers a,b,c] [--runs N]   # 供应商对比
-npx agentkits test                                        # 测试已配置供应商
-npx agentkits cost                                        # 定价对比
-npx agentkits serve      [--port N]                       # OpenAI 兼容代理
-npx agentkits list                                        # 列出所有供应商
-npx agentkits mcp connect <url>                           # 连接 MCP 服务器
+npx agentkits chat     [--provider P] [--model M]      # 交互式对话
+npx agentkits embed    "文本" [--provider P]            # 生成向量
+npx agentkits benchmark [--providers a,b,c] [--runs N]  # 供应商对比
+npx agentkits test                                      # 测试已配置供应商
+npx agentkits cost                                      # 定价对比
+npx agentkits serve    [--port N]                       # OpenAI 兼容代理
+npx agentkits list                                      # 列出所有供应商
+npx agentkits mcp connect <url>                         # 连接 MCP 服务器
 ```
@@ -284,42 +299,28 @@
 
-## 在 OPC Agent 中使用
+## 架构 Architecture
 
-[opc-agent](https://github.com/Deepleaper/opc-agent) 基于 AgentKits 构建，展示了完整的生产级用法：
-
-```typescript
-// opc-agent 内部使用 AgentKits 的模型推荐 + 统一调用
-import { recommendModel, createChat, withBrain, checkProvider } from 'agentkits';
-
-// 1. 推荐最适合当前任务的模型
-const picks = recommendModel({ task: 'coding', budget: 'low' });
-
-// 2. 创建带记忆的对话
-const chat = createChat({ provider: picks[0].provider, model: picks[0].model });
-const smartChat = withBrain(chat.complete.bind(chat), { brainUrl: process.env.BRAIN_URL });
-
-// 3. 健康检查确保可用
-const health = await checkProvider(picks[0].provider);
-if (!health.available) { /* fallback */ }
 ```
-
----
-
-## 四件套生态
-
-AgentKits 是跃盟科技 AI 四件套的核心层：
-
-| 层级 | 项目 | 定位 |
-|------|------|------|
-| 🧠 | [DeepBrain](https://github.com/Deepleaper/deepbrain) | 知识大脑 — 语义存储 + 自动关联 |
-| 📊 | **AgentKits** ← 你在这里 | 模型层 — 统一 API + 推荐 + 记忆增强 |
-| 🤖 | [OPC Agent](https://github.com/Deepleaper/opc-agent) | 智能体 — 基于 AgentKits 的生产级 Agent |
-| 🔌 | [OpenClaw](https://github.com/Deepleaper/openclaw) | 运行时 — Agent 编排 + 多端接入 |
-
+┌──────────────────────────────────────────────────────────┐
+│                     你的应用 Your App                     │
+├──────────────────────────────────────────────────────────┤
+│  Agent 循环 │ 工作流 │ RAG │ 工具 │ 多轮对话               │
+├──────────────────────────────────────────────────────────┤
+│  安全护栏 │ 记忆 │ 结构化输出 │ 提示词模板                 │
+├──────────────────────────────────────────────────────────┤
+│  路由 │ 故障转移 │ 缓存 │ 限流 │ 重试                     │
+├──────────────────────────────────────────────────────────┤
+│  MCP 客户端 │ A2A 协议 │ 链路追踪 │ 日志                   │
+├──────────────────────────────────────────────────────────┤
+│                   统一供应商接口                           │
+│  ┌─────┐ ┌──────┐ ┌──────┐ ┌─────┐ ┌─────┐            │
+│  │ LLM │ │ 向量 │ │ 视觉 │ │ TTS │ │ STT │  ...       │
+│  └──┬──┘ └──┬───┘ └──┬───┘ └──┬──┘ └──┬──┘            │
+├─────┼───────┼────────┼────────┼───────┼────────────────┤
+│  OpenAI · Gemini · DeepSeek · 通义 · 智谱 · Ollama +13  │
+└──────────────────────────────────────────────────────────┘
 ```
-DeepBrain (知识) → AgentKits (模型) → OPC Agent (智能体) → OpenClaw (运行时)
-```
 
 ---
 
-## 环境变量
+## 环境变量 Environment Variables
 
@@ -330,3 +331,2 @@ ```bash
 GEMINI_API_KEY=AI...
-ANTHROPIC_API_KEY=sk-ant-...
 
@@ -336,3 +336,3 @@ # 中国供应商
 DASHSCOPE_API_KEY=sk-...         # 通义千问
-ZHIPU_API_KEY=...                # 智谱 AI
+ZHIPU_API_KEY=...                # 智谱AI
 MOONSHOT_API_KEY=sk-...          # 月之暗面 (Kimi)
@@ -344,2 +344,7 @@ YI_API_KEY=...                   # 零一万物
 MINIMAX_API_KEY=...              # MiniMax
+
+# 更多
+GROQ_API_KEY=gsk_...
+COHERE_API_KEY=...
+JINA_API_KEY=jina_...
 ```
@@ -349,24 +354,19 @@
 
-## License
+## 开源协议 License
 
-Apache-2.0 · Made by [Deepleaper 跃盟科技](https://github.com/Deepleaper)
+Apache-2.0 · Made by [Deepleaper 跃盟科技](https://github.com/Magicray1217)
 
 ---
 
-<a name="english-version"></a>
+<details>
+<summary>English</summary>
 
-# English Version
+## Why AgentKits?
 
-<div align="center">
+AgentKits provides a **unified TypeScript interface** across 29 LLM providers and 18 embedding providers. Switching models requires changing one config value — no code rewrite needed.
 
-## 📊 AgentKits
+**First-class support for Chinese LLM ecosystem**: DashScope (Qwen), Zhipu AI (GLM), Moonshot (Kimi), Yi, Baichuan, SiliconFlow, StepFun, DeepSeek, MiniMax.
 
-**OpenRouter with Memory: Unified Model API + Smart Recommendation + Memory-Enhanced**
+## Install
 
-One API for all LLMs. Auto-recommend the best model. Every call enhanced with memory.
-
-</div>
-
-### Install
-
 ```bash
@@ -376,87 +376,42 @@ npm install agentkits
 
-### Quick Start
+## Quick Examples
 
-```typescript
-import { recommendModel, createChat, withBrain } from 'agentkits';
+```ts
+import { createChat, createEmbedding } from 'agentkits';
 
-// 🎯 Smart recommendation: pick the best model by task + budget
-const picks = recommendModel({ task: 'coding', budget: 'medium' });
-console.log(picks[0]);
-// { model: 'deepseek-coder-v2', provider: 'deepseek', reason: 'Best cost/perf for coding tasks', ... }
+const chat = createChat({ provider: 'deepseek' });
+const reply = await chat.complete('Explain quantum computing');
 
-// 🤖 Unified API: switch providers by changing one word
-const chat = createChat({ provider: 'deepseek', model: 'deepseek-chat' });
-const reply = await chat.complete('Write a quicksort in TypeScript');
-
-// 🧠 Memory-enhanced: auto-recall context from DeepBrain
-const smartChat = withBrain(chat.complete.bind(chat), { brainUrl: 'http://localhost:3333' });
+const emb = createEmbedding({ provider: 'openai' });
+const vector = await emb.embed('semantic search');
 ```
 
-### Features
+See the sections above for full code examples — all code blocks are bilingual.
 
-| | Feature | Description |
-|---|---|---|
-| 🤖 | **Unified Model API** | OpenAI / Anthropic / Google / DeepSeek / Qwen / Zhipu / Moonshot / Ollama — one interface |
-| 🎯 | **Smart Recommendation** | `recommendModel()` picks optimal model by task + budget + speed |
-| 💰 | **Cost Estimation** | `estimateModelCost()` precise pricing for 20+ models |
-| 🏥 | **Health Check** | `checkProvider()` real-time availability + latency for 7 providers |
-| 🧠 | **Memory-Enhanced** | `withBrain()` auto-chains DeepBrain: recall → chat → learn |
-| 🎨 | **Web UI** | Model management dashboard + Playground |
-| 📊 | **40 Modules** | RAG / Agent / Workflow / MCP / A2A / Vision / TTS / STT / Guardrails |
+## Providers
 
-### Supported Models
+- **LLM (19)**: OpenAI, Gemini, DeepSeek, DashScope, Zhipu, Moonshot, Yi, Baichuan, SiliconFlow, StepFun, MiniMax, Grok, Cohere, Fireworks, Together, Groq, Perplexity, Ollama, Custom
+- **Embedding (15)**: OpenAI, Gemini, DashScope, DeepSeek, Zhipu, SiliconFlow, Cohere, Jina, Voyage, Mixedbread, Nomic, Fireworks, Together, Ollama, Custom
 
-**LLM (19 providers):** OpenAI (GPT-4o), Anthropic (Claude 3.5), Google (Gemini 2.5), DeepSeek, DashScope (Qwen), Zhipu (GLM-4), Moonshot (Kimi), Yi, Baichuan, SiliconFlow, StepFun, MiniMax, Grok, Cohere, Fireworks, Together, Groq, Perplexity, Ollama, Custom.
+## Module Catalog (40 modules)
 
-**Embedding (15 providers):** OpenAI, Google, DashScope, DeepSeek, Zhipu, SiliconFlow, Cohere, Jina, Voyage, Mixedbread, Nomic, Fireworks, Together, Ollama, Custom.
+Refer to the [Module Catalog](#模块目录-module-catalog) table above — all import paths work as `import { ... } from 'agentkits/<module>'`.
 
-See the [Chinese section above](#支持模型) for the full pricing table.
+## CLI
 
-### API Reference
-
-```typescript
-// Recommend
-recommendModel({ task, budget, speed, local }) → ModelRecommendation[]
-estimateModelCost(model, inputTokens, outputTokens) → ModelCostEstimate
-
-// Chat
-createChat({ provider, model }) → ChatClient
-chat.complete(prompt) → string
-chat.stream(prompt) → AsyncIterable<StreamChunk>
-
-// Memory (DeepBrain)
-withBrain(chatFn, config) → wrappedChatFn  // middleware
-recall(query, config) → RecallResult[]
-learn(text, config) → void
-
-// Health
-checkProvider(provider, config?) → HealthCheckResult
-
-// Web UI
-new KitsUI({ port }).start()
-
-// And 40 more modules...
-```
-
-### CLI
-
 ```bash
-npx agentkits chat | embed | benchmark | test | cost | serve | list | mcp connect
+npx agentkits chat     [--provider P] [--model M]
+npx agentkits embed    "text" [--provider P]
+npx agentkits benchmark [--providers a,b,c] [--runs N]
+npx agentkits test
+npx agentkits cost
+npx agentkits serve    [--port N]
+npx agentkits list
+npx agentkits mcp connect <url>
 ```
 
-### Ecosystem
+## License
 
-```
-DeepBrain (knowledge) → AgentKits (models) → OPC Agent (agents) → OpenClaw (runtime)
-```
+Apache-2.0 · Made by [Deepleaper 跃盟科技](https://github.com/Magicray1217)
 
-| Layer | Project | Role |
-|-------|---------|------|
-| 🧠 | [DeepBrain](https://github.com/Deepleaper/deepbrain) | Knowledge brain — semantic store + auto-linking |
-| 📊 | **AgentKits** ← you are here | Model layer — unified API + recommendation + memory |
-| 🤖 | [OPC Agent](https://github.com/Deepleaper/opc-agent) | Agent — production-grade agent built on AgentKits |
-| 🔌 | [OpenClaw](https://github.com/Deepleaper/openclaw) | Runtime — agent orchestration + multi-platform |
-
-### License
-
-Apache-2.0 · Made by [Deepleaper 跃盟科技](https://github.com/Deepleaper)
+</details>

README.zh-CN.md

@@ -35,3 +35,3 @@ <div align="center">
 
-> 💡 **差异化优势**：市面上大多数 AI 框架只象征性支持 1-2 个中国模型。AgentKits 深度集成 **9 个中国大模型供应商**，覆盖对话、向量化、函数调用、流式输出全场景。
+> 💡 **中国模型支持**：AgentKits 深度集成 **9 个中国大模型供应商**，覆盖对话、向量化、函数调用、流式输出全场景。
 
@@ -38,0 +38,0 @@ ---

src/cost/index.ts

@@ -54,2 +54,12 @@ /**
   { provider: 'minimax',   model: 'MiniMax-Text-01',     currency: 'CNY', inputPer1M: 1.00,  outputPer1M: 8.00,  updated: '2026-04' },
+  { provider: 'grok',       model: 'grok-3',                                   currency: 'USD', inputPer1M: 3.00,  outputPer1M: 15.00, updated: '2026-04' },
+  { provider: 'cohere',     model: 'command-r-plus',                            currency: 'USD', inputPer1M: 2.50,  outputPer1M: 10.00, updated: '2026-04' },
+  { provider: 'yi',         model: 'yi-large',                                  currency: 'CNY', inputPer1M: 20.00, outputPer1M: 20.00, updated: '2026-04' },
+  { provider: 'baichuan',   model: 'Baichuan4',                                 currency: 'CNY', inputPer1M: 100.00,outputPer1M: 100.00,updated: '2026-04' },
+  { provider: 'siliconflow',model: 'deepseek-ai/DeepSeek-V3',                   currency: 'CNY', inputPer1M: 2.00,  outputPer1M: 8.00,  updated: '2026-04' },
+  { provider: 'stepfun',    model: 'step-2-16k',                                currency: 'CNY', inputPer1M: 38.00, outputPer1M: 120.00,updated: '2026-04' },
+  { provider: 'fireworks',  model: 'accounts/fireworks/models/llama-v3p1-70b-instruct', currency: 'USD', inputPer1M: 0.90, outputPer1M: 0.90, updated: '2026-04' },
+  { provider: 'together',   model: 'meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo', currency: 'USD', inputPer1M: 0.88, outputPer1M: 0.88, updated: '2026-04' },
+  { provider: 'groq',       model: 'llama-3.3-70b-versatile',                   currency: 'USD', inputPer1M: 0.59,  outputPer1M: 0.79,  updated: '2026-04' },
+  { provider: 'perplexity', model: 'sonar-pro',                                 currency: 'USD', inputPer1M: 3.00,  outputPer1M: 15.00, updated: '2026-04' },
   { provider: 'ollama',    model: 'any',                 currency: 'USD', inputPer1M: 0,     outputPer1M: 0,     updated: '2026-04' },
@@ -64,2 +74,5 @@
   { provider: 'zhipu',     model: 'embedding-3',            currency: 'CNY', inputPer1M: 0.50,  outputPer1M: 0, embeddingPer1M: 0.50, updated: '2026-04' },
+  { provider: 'cohere',     model: 'embed-english-v3.0',    currency: 'USD', inputPer1M: 0.10,  outputPer1M: 0, embeddingPer1M: 0.10, updated: '2026-04' },
+  { provider: 'jina',       model: 'jina-embeddings-v3',    currency: 'USD', inputPer1M: 0.02,  outputPer1M: 0, embeddingPer1M: 0.02, updated: '2026-04' },
+  { provider: 'voyage',     model: 'voyage-3',              currency: 'USD', inputPer1M: 0.06,  outputPer1M: 0, embeddingPer1M: 0.06, updated: '2026-04' },
   { provider: 'ollama',    model: 'nomic-embed-text',       currency: 'USD', inputPer1M: 0,     outputPer1M: 0, embeddingPer1M: 0,    updated: '2026-04' },
@@ -66,0 +79,0 @@ ];

New alerts

AI-detected potential code anomaly

Supply chain risk

AI has identified unusual behaviors that may pose a security risk.

Found 1 instance in 1 package

URL strings

Supply chain risk

Package contains fragments of external URLs or IP addresses, which the package may be accessing at runtime.

Found 1 instance in 1 package

Fixed alerts

AI-detected potential code anomaly

Supply chain risk

AI has identified unusual behaviors that may pose a security risk.

Found 1 instance in 1 package

URL strings

Supply chain risk

Package contains fragments of external URLs or IP addresses, which the package may be accessing at runtime.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

2450132

0.22%

Lines of code

19011

0.29%

Worsened metrics

Number of lines in readme file

410

-9.89%

No dependency changes