> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-docs-zh.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# 快速入门

> 本指南将引导您使用 Deep Agents SDK 创建您的第一个深度智能体。使用 SDK 以获得最大灵活性，您可以自行托管智能体或运行自定义 LangSmith 部署。若要在生产环境中运行智能体而无需管理基础设施，请参见 Managed Deep Agents 快速入门。

本指南将引导您使用 Deep Agents SDK 创建您的第一个深度智能体。使用 SDK 以获得最大灵活性，您可以自行托管智能体或运行自定义 [LangSmith 部署](https://docs.langchain.com/langsmith/deployment)。若要在生产环境中运行智能体而无需管理基础设施，请参见 [Managed Deep Agents 快速入门](https://docs.langchain.com/langsmith/managed-deep-agents-quickstart)。

您将构建一个研究智能体，该智能体可以进行研究并撰写报告。

构建 Deep Agents 研究快速入门

按照 Deep Agents 快速入门的说明，在本工作目录中构建 Deep Agents 研究智能体。

## 第 1 步：阅读指南

检测此项目使用的是 Python 还是 TypeScript/JavaScript。获取并遵循匹配的页面；将其视为包名称、模型字符串、搜索工具设置和代码的权威来源：

* Python: [https://docs.langchain.com/oss/python/deepagents/quickstart.md](https://docs.langchain.com/oss/python/deepagents/quickstart.md)
* TypeScript: [https://docs.langchain.com/oss/javascript/deepagents/quickstart.md](https://docs.langchain.com/oss/javascript/deepagents/quickstart.md)

## 第 2 步：安装依赖项

使用项目已使用的包管理器安装 `deepagents`（在 TypeScript 中还需安装 `langchain` / `@langchain/core`）。如果用户未使用 Google、OpenAI 或 Anthropic 内置提供程序搜索工具，则仅添加 Tavily。

## 第 3 步：配置模型凭证

检查是否设置了受支持的提供程序 API 密钥（例如 `GOOGLE_API_KEY`、`OPENAI_API_KEY` 或 `ANTHROPIC_API_KEY`）。如果没有设置，请询问用户要使用哪个提供程序，然后停止并等待他们创建密钥并在 shell 或 `.env` 文件中设置。不要凭空捏造、硬编码或提交 API 密钥。如果他们需要 Tavily，请以相同的方式询问他们设置 `TAVILY_API_KEY`。

## 第 4 步：实现研究智能体

按顺序遵循快速入门步骤：

1. 创建互联网搜索工具（当所选模型支持时，优先使用提供程序内置搜索工具；否则使用 Tavily）。
2. 使用搜索工具、指南中的一个 `provider:model` 字符串（或初始化的模型）以及页面中显示的研究系统提示词调用 `create_deep_agent`。
3. 对于可选的 LangSmith 追踪，请遵循 [https://docs.langchain.com/langsmith/create-an-agent](https://docs.langchain.com/langsmith/create-an-agent) 在基于智能体的工作区中注册智能体。询问用户自行设置 `LANGSMITH_AGENT_ID`、`LANGSMITH_AGENT_ENVIRONMENT`、`LANGSMITH_TRACING=true` 和 `LANGSMITH_API_KEY`。
4. 在指南中的样本研究查询上运行智能体并打印最终响应。

## 规则

* 仅限于本自托管 SDK 快速入门。不要添加 Managed Deep Agents 部署、评估或无关框架。如果用户希望使用管理路径，请将他们指向 Managed Deep Agents 快速入门。
* 当可用时，优先使用提供程序内置网络搜索；仅在需要时使用 Tavily。
* 当密钥、提供程序选择或项目约定不明确时，请询问而不是猜测。

> [!TIP]
>
> **使用 AI 编码助手？**
>
> * 安装 [LangChain 文档 MCP 服务器](https://langchain-docs-zh.mintlify.site/use-these-docs) 以使您的智能体能够访问最新的 LangChain 文档和示例。
>
>   连接LangChain文档MCP服务器
>
>   将LangChain文档MCP服务器与我的编程智能体连接，使其能够查询最新的LangChain、LangGraph和LangSmith文档及API参考。
>
>   需添加的服务器：
>
>   * `docs-langchain`: [https://docs.langchain.com/mcp](https://docs.langchain.com/mcp)
>   * `reference-langchain`: [https://reference.langchain.com/mcp](https://reference.langchain.com/mcp)
>
>   检测我正在使用的智能体或编辑器（Claude代码、Cursor、Codex CLI、Claude桌面、Deep Agents代码、VS Code、Antigravity或其他MCP兼容客户端），并从[https://docs.langchain.com/use-these-docs.md获取对应配置：](https://docs.langchain.com/use-these-docs.md获取对应配置：)
>
>   * Claude代码：使用`claude mcp add --transport http`为每个服务器（默认项目级访问；仅在要求全局访问时使用`--scope user`）
>   * Codex CLI：使用`codex mcp add`与每个服务器URL
>   * Cursor、Deep Agents代码、VS Code或Antigravity：将两个条目合并到MCP设置JSON中，使用页面中显示的对应客户端字段名称
>   * Claude桌面：在Settings > Connectors下添加两个URL
>
>   不要编造MCP URL。配置完成后确认两个服务器均被列出且可访问。
> * 安装 [LangChain 技能](https://github.com/langchain-ai/langchain-skills) 以提高您的智能体在 LangChain 生态系统任务上的性能。
>
>   安装 LangChain 技能
>
>   为我的编码智能体安装 LangChain 技能，以便它在 LangChain、LangGraph 和 Deep Agents 任务上表现更好。
>
>   使用 [https://github.com/langchain-ai/langchain-skills](https://github.com/langchain-ai/langchain-skills) 上的智能体技能安装程序：
>
>   ```bash theme={null}
>   npx skills add langchain-ai/langchain-skills --skill '*' --yes
>   ```
>
>   如果改为请求全局安装，请使用：
>
>   ```bash theme={null}
>   npx skills add langchain-ai/langchain-skills --skill '*' --yes --global
>   ```
>
>   检测您正在使用哪个智能体或编辑器。如果您使用 Claude Code 并偏好插件路径，请从该仓库的 README 文件中遵循市场安装方法（`/plugin marketplace add` 然后 `/plugin install`）。不要编造替代的技能包名称或安装 URL。安装完成后，确认这些技能对智能体可用。

## 前置条件

开始之前，请确保您有一个模型提供程序的 API 密钥（例如 Gemini、Anthropic、OpenAI）。

> [!NOTE]
>
> Deep Agents 需要一个支持 [工具调用](https://langchain-docs-zh.mintlify.site/langchain/oss/langchain/models.md#工具调用) 的模型。有关如何配置模型的详细信息，请参见 [自定义](https://langchain-docs-zh.mintlify.site/langchain/oss/deepagents/customization.md#模型)。

## 第 1 步：安装依赖项

:::python

```bash pip theme={null}
pip install deepagents
```

```bash uv theme={null}
uv init
uv add deepagents
uv sync
```

:::

:::js

```bash npm theme={null}
npm install deepagents langchain @langchain/core
```

```bash yarn theme={null}
yarn add deepagents langchain @langchain/core
```

```bash pnpm theme={null}
pnpm add deepagents langchain @langchain/core
```

:::

> [!NOTE]
>
> Google、OpenAI 和 Anthropic 都提供内置网络搜索工具：无需额外包或 API 密钥。如果您使用不同的提供程序或更喜欢 [Tavily](https://tavily.com/) 进行搜索，请安装 Tavily 包：
>
> :::python
>
> ```bash theme={null}
> pip install tavily-python
> ```
>
> :::
>
> :::js
>
> ```bash theme={null}
> npm install @langchain/tavily
> ```
>
> :::

## 第 2 步：设置您的 API 密钥

> [tab] Google
>
> ```bash theme={null}
> export GOOGLE_API_KEY="your-api-key"
> ```

> [tab] OpenAI
>
> ```bash theme={null}
> export OPENAI_API_KEY="your-api-key"
> ```

> [tab] Anthropic
>
> ```bash theme={null}
> export ANTHROPIC_API_KEY="your-api-key"
> ```

> [tab] OpenRouter
>
> ```bash theme={null}
> export OPENROUTER_API_KEY="your-api-key"
> export TAVILY_API_KEY="your-tavily-api-key"
> ```

> [tab] Fireworks
>
> ```bash theme={null}
> export FIREWORKS_API_KEY="your-api-key"
> export TAVILY_API_KEY="your-tavily-api-key"
> ```

> [tab] Baseten
>
> ```bash theme={null}
> export BASETEN_API_KEY="your-api-key"
> export TAVILY_API_KEY="your-tavily-api-key"
> ```

> [tab] Ollama
>
> ```bash theme={null}
> # Local: Ollama must be running on your machine
> # Cloud: Set your Ollama API key for hosted inference
> export OLLAMA_API_KEY="your-api-key"
> export TAVILY_API_KEY="your-tavily-api-key"
> ```

> [tab] Other
>
> ```bash theme={null}
> # Set the API key for your provider
> export <PROVIDER>_API_KEY="your-api-key"
> export TAVILY_API_KEY="your-tavily-api-key"
> ```
>
> Deep Agents 支持任何 [LangChain 对话模型](https://langchain-docs-zh.mintlify.site/langchain/oss/deepagents/models.md#支持的模型)。设置您的提供程序的 API 密钥。

> [!TIP]
>
> 如果您正在使用 LangSmith 的 [LLM 网关](https://docs.langchain.com/langsmith/llm-gateway)，则对提供程序的流量通过 LangSmith 进行路由。使用网关密钥作为 API 密钥。

## 第 3 步：创建一个搜索工具

Google、OpenAI 和 Anthropic 提供内置网络搜索工具，这些工具在服务器端运行：无需额外包或 API 密钥。将提供程序工具字典直接传递给 `create_deep_agent`。

> [tab] Provider search (recommended)
>
> :::python
>
> ```python Google theme={null}
> from deepagents import create_deep_agent
>
> # Google's built-in search — no extra install or API key needed
> internet_search = {"google_search": {}}
> ```
>
> ```python OpenAI theme={null}
> from deepagents import create_deep_agent
>
> # OpenAI's built-in web search — no extra install or API key needed
> internet_search = {"type": "web_search"}
> ```
>
> ```python Anthropic theme={null}
> from deepagents import create_deep_agent
>
> # Anthropic's built-in web search — no extra install or API key needed
> internet_search = {"type": "web_search_20260209", "name": "web_search"}
> ```
>
> :::
>
> :::js
>
> ```ts Google theme={null}
> import { createDeepAgent } from "deepagents";
>
> // Google's built-in search — no extra install or API key needed
> const internetSearch = { googleSearch: {} };
> ```
>
> ```ts OpenAI theme={null}
> import { createDeepAgent } from "deepagents";
>
> // OpenAI's built-in web search — no extra install or API key needed
> const internetSearch = { type: "web_search_preview" };
> ```
>
> ```ts Anthropic theme={null}
> import { createDeepAgent } from "deepagents";
>
> // Anthropic's built-in web search — no extra install or API key needed
> const internetSearch = { type: "web_search_20250305", name: "web_search" };
> ```
>
> :::

> [tab] Tavily (any provider)
>
> :::python
>
> ```python theme={null}
> import os
> from typing import Literal
>
> from tavily import TavilyClient
> from deepagents import create_deep_agent
>
> tavily_client = TavilyClient(api_key=os.environ["TAVILY_API_KEY"])
>
>
> def internet_search(
>     query: str,
>     max_results: int = 5,
>     topic: Literal["general", "news", "finance"] = "general",
>     include_raw_content: bool = False,
> ):
>     """Run a web search"""
>     return tavily_client.search(
>         query,
>         max_results=max_results,
>         include_raw_content=include_raw_content,
>         topic=topic,
>     )
> ```
>
> :::
>
> :::js
>
> ```ts theme={null}
> import { tool } from "langchain";
> import { TavilySearch } from "@langchain/tavily";
> import { z } from "zod";
>
> const internetSearch = tool(
>   async ({
>     query,
>     maxResults = 5,
>     topic = "general",
>     includeRawContent = false,
>   }: {
>     query: string;
>     maxResults?: number;
>     topic?: "general" | "news" | "finance";
>     includeRawContent?: boolean;
>   }) => {
>     const tavilySearch = new TavilySearch({
>       maxResults,
>       tavilyApiKey: process.env.TAVILY_API_KEY,
>       includeRawContent,
>       topic,
>     });
>     return await tavilySearch._call({ query });
>   },
>   {
>     name: "internet_search",
>     description: "Run a web search",
>     schema: z.object({
>       query: z.string().describe("The search query"),
>       maxResults: z
>         .number()
>         .optional()
>         .default(5)
>         .describe("Maximum number of results to return"),
>       topic: z
>         .enum(["general", "news", "finance"])
>         .optional()
>         .default("general")
>         .describe("Search topic category"),
>       includeRawContent: z
>         .boolean()
>         .optional()
>         .default(false)
>         .describe("Whether to include raw content"),
>     }),
>   },
> );
> ```
>
> :::

## 第 4 步：创建深度智能体

将您的搜索工具和模型传递给 `create_deep_agent`。在 `provider:model` 格式中传递一个 `model` 字符串，或传递一个 [初始化的模型实例](https://langchain-docs-zh.mintlify.site/langchain/oss/deepagents/models.md#配置模型参数)。有关所有提供程序的支持模型，请参见 [支持模型](https://langchain-docs-zh.mintlify.site/langchain/oss/deepagents/models.md#支持的模型)；有关经过测试的推荐模型，请参见 [建议模型](https://langchain-docs-zh.mintlify.site/langchain/oss/deepagents/models.md#推荐的模型)。

:::python

```python Google theme={null}
# System prompt to steer the agent to be an expert researcher
research_instructions = """You are an expert researcher. Your job is to conduct thorough research and then write a polished report.

You have access to an internet search tool as your primary means of gathering information.

## `internet_search`

Use this to run an internet search for a given query. You can specify the max number of results to return, the topic, and whether raw content should be included.
"""

agent = create_deep_agent(
    model="google_genai:gemini-3.6-flash",
    tools=[internet_search],
    system_prompt=research_instructions,
)
```

```python OpenAI theme={null}
# System prompt to steer the agent to be an expert researcher
research_instructions = """You are an expert researcher. Your job is to conduct thorough research and then write a polished report.

You have access to an internet search tool as your primary means of gathering information.

## `internet_search`

Use this to run an internet search for a given query. You can specify the max number of results to return, the topic, and whether raw content should be included.
"""

agent = create_deep_agent(
    model="openai:gpt-5.5",
    tools=[internet_search],
    system_prompt=research_instructions,
)
```

```python Anthropic theme={null}
# System prompt to steer the agent to be an expert researcher
research_instructions = """You are an expert researcher. Your job is to conduct thorough research and then write a polished report.

You have access to an internet search tool as your primary means of gathering information.

## `internet_search`

Use this to run an internet search for a given query. You can specify the max number of results to return, the topic, and whether raw content should be included.
"""

agent = create_deep_agent(
    model="anthropic:claude-sonnet-5",
    tools=[internet_search],
    system_prompt=research_instructions,
)
```

```python OpenRouter theme={null}
# System prompt to steer the agent to be an expert researcher
research_instructions = """You are an expert researcher. Your job is to conduct thorough research and then write a polished report.

You have access to an internet search tool as your primary means of gathering information.

## `internet_search`

Use this to run an internet search for a given query. You can specify the max number of results to return, the topic, and whether raw content should be included.
"""

agent = create_deep_agent(
    model="openrouter:z-ai/glm-5.2",
    tools=[internet_search],
    system_prompt=research_instructions,
)
```

```python Fireworks theme={null}
# System prompt to steer the agent to be an expert researcher
research_instructions = """You are an expert researcher. Your job is to conduct thorough research and then write a polished report.

You have access to an internet search tool as your primary means of gathering information.

## `internet_search`

Use this to run an internet search for a given query. You can specify the max number of results to return, the topic, and whether raw content should be included.
"""

agent = create_deep_agent(
    model="fireworks:accounts/fireworks/models/glm-5p2",
    tools=[internet_search],
    system_prompt=research_instructions,
)
```

```python Baseten theme={null}
# System prompt to steer the agent to be an expert researcher
research_instructions = """You are an expert researcher. Your job is to conduct thorough research and then write a polished report.

You have access to an internet search tool as your primary means of gathering information.

## `internet_search`

Use this to run an internet search for a given query. You can specify the max number of results to return, the topic, and whether raw content should be included.
"""

agent = create_deep_agent(
    model="baseten:zai-org/GLM-5.2",
    tools=[internet_search],
    system_prompt=research_instructions,
)
```

```python Ollama theme={null}
# System prompt to steer the agent to be an expert researcher
research_instructions = """You are an expert researcher. Your job is to conduct thorough research and then write a polished report.

You have access to an internet search tool as your primary means of gathering information.

## `internet_search`

Use this to run an internet search for a given query. You can specify the max number of results to return, the topic, and whether raw content should be included.
"""

agent = create_deep_agent(
    model="ollama:north-mini-code-1.0",
    tools=[internet_search],
    system_prompt=research_instructions,
)
```

:::

:::js

```ts Google theme={null}
import { createDeepAgent } from "deepagents";

// System prompt to steer the agent to be an expert researcher
const researchInstructions = `You are an expert researcher. Your job is to conduct thorough research and then write a polished report.

You have access to an internet search tool as your primary means of gathering information.

## \`internet_search\`

Use this to run an internet search for a given query. You can specify the max number of results to return, the topic, and whether raw content should be included.
`;

const agent = createDeepAgent({
  model: "google:gemini-3.6-flash",
  tools: [internetSearch],
  systemPrompt: researchInstructions,
});
```

```ts OpenAI theme={null}
import { createDeepAgent } from "deepagents";

// System prompt to steer the agent to be an expert researcher
const researchInstructions = `You are an expert researcher. Your job is to conduct thorough research and then write a polished report.

You have access to an internet search tool as your primary means of gathering information.

## \`internet_search\`

Use this to run an internet search for a given query. You can specify the max number of results to return, the topic, and whether raw content should be included.
`;

const agent = createDeepAgent({
  model: "openai:gpt-5.5",
  tools: [internetSearch],
  systemPrompt: researchInstructions,
});
```

```ts Anthropic theme={null}
import { createDeepAgent } from "deepagents";

// System prompt to steer the agent to be an expert researcher
const researchInstructions = `You are an expert researcher. Your job is to conduct thorough research and then write a polished report.

You have access to an internet search tool as your primary means of gathering information.

## \`internet_search\`

Use this to run an internet search for a given query. You can specify the max number of results to return, the topic, and whether raw content should be included.
`;

const agent = createDeepAgent({
  model: "anthropic:claude-sonnet-5",
  tools: [internetSearch],
  systemPrompt: researchInstructions,
});
```

```ts OpenRouter theme={null}
import { createDeepAgent } from "deepagents";

// System prompt to steer the agent to be an expert researcher
const researchInstructions = `You are an expert researcher. Your job is to conduct thorough research and then write a polished report.

You have access to an internet search tool as your primary means of gathering information.

## \`internet_search\`

Use this to run an internet search for a given query. You can specify the max number of results to return, the topic, and whether raw content should be included.
`;

const agent = createDeepAgent({
  model: "openrouter:z-ai/glm-5.2",
  tools: [internetSearch],
  systemPrompt: researchInstructions,
});
```

```ts Fireworks theme={null}
import { createDeepAgent } from "deepagents";

// System prompt to steer the agent to be an expert researcher
const researchInstructions = `You are an expert researcher. Your job is to conduct thorough research and then write a polished report.

You have access to an internet search tool as your primary means of gathering information.

## \`internet_search\`

Use this to run an internet search for a given query. You can specify the max number of results to return, the topic, and whether raw content should be included.
`;

const agent = createDeepAgent({
  model: "fireworks:accounts/fireworks/models/glm-5p2",
  tools: [internetSearch],
  systemPrompt: researchInstructions,
});
```

```ts Baseten theme={null}
import { createDeepAgent } from "deepagents";

// System prompt to steer the agent to be an expert researcher
const researchInstructions = `You are an expert researcher. Your job is to conduct thorough research and then write a polished report.

You have access to an internet search tool as your primary means of gathering information.

## \`internet_search\`

Use this to run an internet search for a given query. You can specify the max number of results to return, the topic, and whether raw content should be included.
`;

const agent = createDeepAgent({
  model: "baseten:zai-org/GLM-5.2",
  tools: [internetSearch],
  systemPrompt: researchInstructions,
});
```

```ts Ollama theme={null}
import { createDeepAgent } from "deepagents";

// System prompt to steer the agent to be an expert researcher
const researchInstructions = `You are an expert researcher. Your job is to conduct thorough research and then write a polished report.

You have access to an internet search tool as your primary means of gathering information.

## \`internet_search\`

Use this to run an internet search for a given query. You can specify the max number of results to return, the topic, and whether raw content should be included.
`;

const agent = createDeepAgent({
  model: "ollama:north-mini-code-1.0",
  tools: [internetSearch],
  systemPrompt: researchInstructions,
});
```

:::

## 第 5 步：设置 LangSmith 追踪

> [!NOTE]
>
> 在一个 [基于智能体的工作空间](https://docs.langchain.com/langsmith/agent-registry) 中，在发送跟踪信息之前，先 [创建一个智能体](https://docs.langchain.com/langsmith/create-an-agent)。使用 [智能体寻址](https://docs.langchain.com/langsmith/log-traces-to-agent) 来选择其标识符和环境。如果集成需要 `project_name`，请使用所选环境的 [`tracer_session_name`](https://docs.langchain.com/langsmith/create-an-agent#use-an-environment-project) 作为兼容性值。

[LangSmith](https://smith.langchain.com) 可以为您提供对智能体执行的可见性，允许您查看工具调用、子智能体委托和 LLM 响应。

在 [smith.langchain.com](https://smith.langchain.com) 注册，创建 API 密钥，并设置以下环境变量：

```bash theme={null}
export LANGSMITH_AGENT_ID="<your-agent-id>"
export LANGSMITH_AGENT_ENVIRONMENT="production"
export LANGSMITH_TRACING=true
export LANGSMITH_API_KEY="your-langsmith-api-key"
```

## 第 6 步：运行智能体

:::python

```python theme={null}
result = agent.invoke({"messages": [{"role": "user", "content": "What is langgraph?"}]})

# Print the agent's response
print(result["messages"][-1].content)
```

:::

:::js

```ts theme={null}
const result = await agent.invoke({
  messages: [{ role: "user", content: "What is langgraph?" }],
});

// Print the agent's response
console.log(result.messages[result.messages.length - 1].content);
```

:::

## 它是如何工作的？

您的深度智能体会自动：

1. **进行研究**，通过调用 `internet_search` 工具收集信息。
2. **管理上下文**，使用文件系统工具（[`write_file`](https://langchain-docs-zh.mintlify.site/langchain/oss/deepagents/overview#虚拟文件系统访问)、[`read_file`](https://langchain-docs-zh.mintlify.site/langchain/oss/deepagents/overview#虚拟文件系统访问)）将大型搜索结果卸载到外部。
3. **按需生成子智能体**，将复杂的子任务委托给专业的子智能体。
4. **综合报告**，将发现结果汇总为连贯的响应。

要添加结构化任务规划功能，请使用 `write_todos` 通过 @\[`TodoListMiddleware` 进行选择。有关详细信息，请参见 [任务规划](https://langchain-docs-zh.mintlify.site/langchain/oss/deepagents/overview.md#任务规划)。

## 示例

有关 Deep Agents 可构建的智能体和模式的示例，请参见 [示例](https://github.com/langchain-ai/deepagents/tree/main/examples)。

## 流式输出

Deep Agents 具有内置的 [流式输出](https://langchain-docs-zh.mintlify.site/langchain/oss/langchain/event-streaming.md)，可使用 LangGraph 实时更新智能体执行结果。
这允许您逐步观察输出，并审查和调试智能体和子智能体的工作，例如工具调用、工具结果和 LLM 响应。

## 下一步

现在你已经构建了你的第一个深度智能体：

* **自定义你的智能体**：了解 [自定义选项](https://langchain-docs-zh.mintlify.site/langchain/oss/deepagents/customization.md)，包括自定义系统提示词、工具和子智能体。
* **添加长期记忆**：启用 [持久记忆](https://langchain-docs-zh.mintlify.site/langchain/oss/deepagents/memory.md)跨对话。
* **部署到生产环境**：使用 [托管深度智能体](https://docs.langchain.com/langsmith/managed-deep-agents-overview)在 LangSmith 中创建、运行和操作深度智能体。
* **测试和评估**：使用 [LangSmith 评估](https://docs.langchain.com/langsmith/evaluation-quickstart)运行自动化测试，并衡量你的智能体相对于数据集的性能。

***

> 官方原文：[src/oss/deepagents/quickstart.mdx](https://github.com/langchain-ai/docs/blob/main/src/oss/deepagents/quickstart.mdx) · 非官方翻译，译文由 AI 生成，以英文原文为准。


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.