# Ai Agent

> AI Agent - OpenAI Agents SDK/LangChain Agents/工具调用/记忆机制

- **Type:** Skill
- **Install:** `agentstack add skill-awesome-ai-dev-awesome-ai-dev-agent`
- **Verified:** Pending review
- **Seller:** [awesome-ai-dev](https://agentstack.voostack.com/s/awesome-ai-dev)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [awesome-ai-dev](https://github.com/awesome-ai-dev)
- **Source:** https://github.com/awesome-ai-dev/awesome-ai-dev/tree/main/.cursor/skills/ai/agent

## Install

```sh
agentstack add skill-awesome-ai-dev-awesome-ai-dev-agent
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# AI Agent 开发

## OpenAI Agents SDK

```typescript
import { Agent, tool } from '@openai/agents';

@tool
async function searchWeb(query: string) {
  // 搜索工具
  return `搜索结果: ${query}`;
}

@tool  
async function calculate(expr: string) {
  // 计算工具
  return eval(expr).toString();
}

const agent = Agent({
  name: 'assistant',
  instructions: '你是一个有帮助的助手',
  tools: [searchWeb, calculate]
});

const result = await agent.run('搜索今天的新闻，然后计算 2+2');
```

## LangChain Agents

```typescript
import { createOpenAIFunctionsAgent } from 'langchain/agents';
import { ChatOpenAI } from 'langchain/chat_models';
import { SerpAPI } from 'langchain/tools';
import { Calculator } from 'langchain/tools/calculator';

const tools = [new SerpAPI(), new Calculator()];

const agent = await createOpenAIFunctionsAgent({
  llm: new ChatOpenAI({ model: 'gpt-4o' }),
  tools
});

const result = await agent.invoke({
  input: '搜索 AI 新闻并计算 10+5'
});
```

## 工具定义

```typescript
// 自定义工具
import { tool } from 'langchain/core/tools';

const getWeather = tool(
  async ({ city }: { city: string }) => {
    // 调用天气 API
    return `城市 ${city} 天气晴朗，25度`;
  },
  {
    name: 'get_weather',
    description: '获取城市天气信息',
    schema: z.object({
      city: z.string().describe('城市名称')
    })
  }
);
```

## 记忆机制

```typescript
import { BufferMemory } from 'langchain/memory';

const memory = new BufferMemory({
  returnMessages: true,
  memoryKey: 'chat_history'
});

// 存储对话
await memory.saveContext(
  { input: '我叫张三' },
  { output: '你好张三，很高兴认识你' }
);

// 读取历史
const history = await memory.loadMemoryVariables({});
```

## Agent 模式

| 模式 | 说明 |
| --- | --- |
| ReAct | 推理 + 行动 |
| Plan-and-Execute | 计划后执行 |
| Tool Use | 工具调用 |
| Self-Reflection | 自我反思 |

## 最佳实践

1. 工具设计要清晰
2. 错误处理要完善
3. 避免无限循环
4. 合理使用记忆

## 参考

- `ai-tools/08-ai-platforms-api.md`

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [awesome-ai-dev](https://github.com/awesome-ai-dev)
- **Source:** [awesome-ai-dev/awesome-ai-dev](https://github.com/awesome-ai-dev/awesome-ai-dev)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** yes

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: flagged — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-awesome-ai-dev-awesome-ai-dev-agent
- Seller: https://agentstack.voostack.com/s/awesome-ai-dev
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.