定制 Deep Agents - AI 开发中文文档

围绕你的目标构建框架。create_deep_agent为你提供生产就绪的基础：将其连接到你的数据，塑造其行为，并添加你的用例所需的功能。 :::python

from deepagents import create_deep_agent

agent = create_deep_agent(
    model="google_genai:gemini-3.6-flash",
    system_prompt="You are a helpful assistant.",
    tools=[search, fetch_url],
    memory=["./AGENTS.md"],
    skills=["./skills/"],
)

from deepagents import create_deep_agent

agent = create_deep_agent(
    model="openai:gpt-5.5",
    system_prompt="You are a helpful assistant.",
    tools=[search, fetch_url],
    memory=["./AGENTS.md"],
    skills=["./skills/"],
)

from deepagents import create_deep_agent

agent = create_deep_agent(
    model="anthropic:claude-sonnet-5",
    system_prompt="You are a helpful assistant.",
    tools=[search, fetch_url],
    memory=["./AGENTS.md"],
    skills=["./skills/"],
)

from deepagents import create_deep_agent

agent = create_deep_agent(
    model="openrouter:z-ai/glm-5.2",
    system_prompt="You are a helpful assistant.",
    tools=[search, fetch_url],
    memory=["./AGENTS.md"],
    skills=["./skills/"],
)

from deepagents import create_deep_agent

agent = create_deep_agent(
    model="fireworks:accounts/fireworks/models/glm-5p2",
    system_prompt="You are a helpful assistant.",
    tools=[search, fetch_url],
    memory=["./AGENTS.md"],
    skills=["./skills/"],
)

from deepagents import create_deep_agent

agent = create_deep_agent(
    model="baseten:zai-org/GLM-5.2",
    system_prompt="You are a helpful assistant.",
    tools=[search, fetch_url],
    memory=["./AGENTS.md"],
    skills=["./skills/"],
)

from deepagents import create_deep_agent

agent = create_deep_agent(
    model="ollama:north-mini-code-1.0",
    system_prompt="You are a helpful assistant.",
    tools=[search, fetch_url],
    memory=["./AGENTS.md"],
    skills=["./skills/"],
)

参数	功能
`model=`	使用哪个模型
`system_prompt=`	智能体的自定义指令
`tools=`	智能体可以调用的领域工具
`memory=`	启动时加载的 AGENTS.md 文件
`skills=`	按需知识技能目录
`backend=`	文件系统后端（默认为 StateBackend）
`permissions=`	文件系统路径级访问控制
`subagents=`	用于委托任务的定制子智能体
`middleware=`	额外中间件合并到 Deep Agents stack；一个 `.name` 匹配内置条目的实例会替换它，其他任何内容都会放在核心中间件条目之后、配置、提示词缓存和记忆之前
`interrupt_on=`	在工具调用前暂停以供人工批准
`response_format=`	结构化输出模式
`state_schema=`	定制图状态模式
`context_schema=`	每次运行时运行时上下文模式（用户 ID、API 密钥、功能标志）
profiles	每个模型的默认值作为一个可重用的包

Full function signature

create_deep_agent(
    model: str | BaseChatModel | None = None,
    tools: Sequence[BaseTool | Callable | dict[str, Any]] | None = None,
    *,
    system_prompt: str | SystemMessage | None = None,
    middleware: Sequence[AgentMiddleware[StateT_co, ContextT]] = (),
    subagents: Sequence[SubAgent | CompiledSubAgent | AsyncSubAgent] | None = None,
    skills: list[str] | None = None,
    memory: list[str] | None = None,
    permissions: list[FilesystemPermission] | None = None,
    backend: BackendProtocol | None = None,
    interrupt_on: dict[str, bool | InterruptOnConfig] | None = None,
    response_format: ResponseFormat[ResponseT] | type[ResponseT] | dict[str, Any] | None = None,
    state_schema: type[DeepAgentState] | None = None,
    context_schema: type[ContextT] | None = None,
    checkpointer: Checkpointer | None = None,
    store: BaseStore | None = None,
    debug: bool = False,
    name: str | None = None,
    cache: BaseCache | None = None
) -> CompiledStateGraph[AgentState[ResponseT], ContextT, InputAgentState, OutputAgentState[ResponseT]]

有关完整参数列表，请参阅 @[create_deep_agent API 参考。要从头开始构建完全定制的 harness，请参阅配置 harness 或遵循从头构建 deep agent 的分步指南。 ::: :::js createDeepAgent 附带了一个预组装的 harness：默认包含文件系统、摘要、子智能体和提示词缓存。以下参数允许您定义智能体的角色，将其连接到您的数据和工具，并通过额外的中间件扩展 Deep Agents stack。

import { createDeepAgent } from "deepagents";

const agent = await createDeepAgent({
  model: "google:gemini-3.6-flash",
  systemPrompt: "You are a helpful assistant.",
  tools: [search, fetchUrl],
  memory: ["./AGENTS.md"],
  skills: ["./skills/"],
});

import { createDeepAgent } from "deepagents";

const agent = await createDeepAgent({
  model: "openai:gpt-5.5",
  systemPrompt: "You are a helpful assistant.",
  tools: [search, fetchUrl],
  memory: ["./AGENTS.md"],
  skills: ["./skills/"],
});

import { createDeepAgent } from "deepagents";

const agent = await createDeepAgent({
  model: "anthropic:claude-sonnet-5",
  systemPrompt: "You are a helpful assistant.",
  tools: [search, fetchUrl],
  memory: ["./AGENTS.md"],
  skills: ["./skills/"],
});

import { createDeepAgent } from "deepagents";

const agent = await createDeepAgent({
  model: "openrouter:z-ai/glm-5.2",
  systemPrompt: "You are a helpful assistant.",
  tools: [search, fetchUrl],
  memory: ["./AGENTS.md"],
  skills: ["./skills/"],
});

import { createDeepAgent } from "deepagents";

const agent = await createDeepAgent({
  model: "fireworks:accounts/fireworks/models/glm-5p2",
  systemPrompt: "You are a helpful assistant.",
  tools: [search, fetchUrl],
  memory: ["./AGENTS.md"],
  skills: ["./skills/"],
});

import { createDeepAgent } from "deepagents";

const agent = await createDeepAgent({
  model: "baseten:zai-org/GLM-5.2",
  systemPrompt: "You are a helpful assistant.",
  tools: [search, fetchUrl],
  memory: ["./AGENTS.md"],
  skills: ["./skills/"],
});

import { createDeepAgent } from "deepagents";

const agent = await createDeepAgent({
  model: "ollama:north-mini-code-1.0",
  systemPrompt: "You are a helpful assistant.",
  tools: [search, fetchUrl],
  memory: ["./AGENTS.md"],
  skills: ["./skills/"],
});

参数	功能
`model`	使用哪个模型
`systemPrompt`	智能体的自定义指令
`tools`	智能体可以调用的领域工具
`memory`	启动时加载的 AGENTS.md 文件
`skills`	按需知识技能目录
`backend`	文件系统后端（默认为 StateBackend）
`permissions`	文件系统路径级访问控制
`subagents`	用于委托任务的定制子智能体
`middleware`	额外中间件追加到 Deep Agents stack
`interruptOn`	在工具调用前暂停以供人工批准
`responseFormat`	结构化输出模式
`contextSchema`	每次运行时运行时上下文模式（用户 ID、API 密钥、功能标志）

有关完整参数列表，请参阅 createDeepAgent API 参考。要从头开始构建完全定制的 harness，请参阅配置 harness，或遵循从头构建 deep agent 的分步指南。

当你添加工具、子智能体和后端时，使用 LangSmith 跟踪它们如何协同工作。按照可观测性快速入门设置即可。我们建议你同时设置 LangSmith 引擎，它监控你的跟踪记录、检测问题并建议解决方案。

模型

传递一个 model 字符串（provider:model 格式），或一个已初始化的模型实例。查看支持的所有模型，以及推荐测试模型获取经过测试的建议。

使用 provider:model 格式（例如 openai:gpt-5.5）快速切换模型。

:::python

👉 请阅读 OpenAI 对话模型集成文档

pip install -U "langchain[openai]"

uv add "langchain[openai]"

import os
from deepagents import create_deep_agent

os.environ["OPENAI_API_KEY"] = "sk-..."

agent = create_deep_agent(model="openai:gpt-5.5")
# this calls init_chat_model for the specified model with default parameters
# to use specific model parameters, use init_chat_model directly

import os
from langchain.chat_models import init_chat_model
from deepagents import create_deep_agent

os.environ["OPENAI_API_KEY"] = "sk-..."

model = init_chat_model(model="openai:gpt-5.5")
agent = create_deep_agent(model=model)

import os
from langchain_openai import ChatOpenAI
from deepagents import create_deep_agent

os.environ["OPENAI_API_KEY"] = "sk-..."

model = ChatOpenAI(model="gpt-5.5")
agent = create_deep_agent(model=model)

👉 请阅读 Anthropic 对话模型集成文档

pip install -U "langchain[anthropic]"

uv add "langchain[anthropic]"

import os
from deepagents import create_deep_agent

os.environ["ANTHROPIC_API_KEY"] = "sk-..."

agent = create_deep_agent(model="anthropic:claude-sonnet-4-6")
# this calls init_chat_model for the specified model with default parameters
# to use specific model parameters, use init_chat_model directly

import os
from langchain.chat_models import init_chat_model
from deepagents import create_deep_agent

os.environ["ANTHROPIC_API_KEY"] = "sk-..."

model = init_chat_model(model="claude-sonnet-4-6")
agent = create_deep_agent(model=model)

import os
from langchain_anthropic import ChatAnthropic
from deepagents import create_deep_agent

os.environ["ANTHROPIC_API_KEY"] = "sk-..."

model = ChatAnthropic(model="claude-sonnet-4-6")
agent = create_deep_agent(model=model)

👉 请阅读 Azure 对话模型集成文档

pip install -U "langchain[openai]"

uv add "langchain[openai]"

import os
from deepagents import create_deep_agent

os.environ["AZURE_OPENAI_API_KEY"] = "..."
os.environ["AZURE_OPENAI_ENDPOINT"] = "..."
os.environ["OPENAI_API_VERSION"] = "2025-03-01-preview"

agent = create_deep_agent(model="azure_openai:gpt-5.5")
# this calls init_chat_model for the specified model with default parameters
# to use specific model parameters, use init_chat_model directly

import os
from langchain.chat_models import init_chat_model
from deepagents import create_deep_agent

os.environ["AZURE_OPENAI_API_KEY"] = "..."
os.environ["AZURE_OPENAI_ENDPOINT"] = "..."
os.environ["OPENAI_API_VERSION"] = "2025-03-01-preview"

model = init_chat_model(
    model="azure_openai:gpt-5.5",
    azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
)
agent = create_deep_agent(model=model)

import os
from langchain_openai import AzureChatOpenAI
from deepagents import create_deep_agent

os.environ["AZURE_OPENAI_API_KEY"] = "..."
os.environ["AZURE_OPENAI_ENDPOINT"] = "..."
os.environ["OPENAI_API_VERSION"] = "2025-03-01-preview"

model = AzureChatOpenAI(
    model="gpt-5.5",
    azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
)
agent = create_deep_agent(model=model)

👉 请阅读 Google GenAI 对话模型集成文档

pip install -U "langchain[google-genai]"

uv add "langchain[google-genai]"

import os
from deepagents import create_deep_agent

os.environ["GOOGLE_API_KEY"] = "..."

agent = create_deep_agent(model="google_genai:gemini-3.6-flash")
# this calls init_chat_model for the specified model with default parameters
# to use specific model parameters, use init_chat_model directly

import os
from langchain.chat_models import init_chat_model
from deepagents import create_deep_agent

os.environ["GOOGLE_API_KEY"] = "..."

model = init_chat_model(model="google_genai:gemini-3.6-flash")
agent = create_deep_agent(model=model)

import os
from langchain_google_genai import ChatGoogleGenerativeAI
from deepagents import create_deep_agent

os.environ["GOOGLE_API_KEY"] = "..."

model = ChatGoogleGenerativeAI(model="gemini-3.6-flash")
agent = create_deep_agent(model=model)

👉 请阅读 AWS Bedrock 对话模型集成文档

pip install -U "langchain[aws]"

uv add "langchain[aws]"

from deepagents import create_deep_agent

# Follow the steps here to configure your credentials:
# https://docs.aws.amazon.com/bedrock/latest/userguide/getting-started.html

agent = create_deep_agent(
    model="anthropic.claude-sonnet-4-6",
    model_provider="bedrock_converse",
)
# this calls init_chat_model for the specified model with default parameters
# to use specific model parameters, use init_chat_model directly

from langchain.chat_models import init_chat_model
from deepagents import create_deep_agent

# Follow the steps here to configure your credentials:
# https://docs.aws.amazon.com/bedrock/latest/userguide/getting-started.html

model = init_chat_model(
    model="anthropic.claude-sonnet-4-6",
    model_provider="bedrock_converse",
)
agent = create_deep_agent(model=model)

from langchain_aws import ChatBedrock
from deepagents import create_deep_agent

# Follow the steps here to configure your credentials:
# https://docs.aws.amazon.com/bedrock/latest/userguide/getting-started.html

model = ChatBedrock(model="anthropic.claude-sonnet-4-6")
agent = create_deep_agent(model=model)

👉 请阅读 HuggingFace 对话模型集成文档

pip install -U "langchain[huggingface]"

uv add "langchain[huggingface]"

import os
from deepagents import create_deep_agent

os.environ["HUGGINGFACEHUB_API_TOKEN"] = "hf_..."

agent = create_deep_agent(
    model="microsoft/Phi-3-mini-4k-instruct",
    model_provider="huggingface",
    temperature=0.7,
    max_tokens=1024,
)
# this calls init_chat_model for the specified model with default parameters
# to use specific model parameters, use init_chat_model directly

import os
from langchain.chat_models import init_chat_model
from deepagents import create_deep_agent

os.environ["HUGGINGFACEHUB_API_TOKEN"] = "hf_..."

model = init_chat_model(
    model="microsoft/Phi-3-mini-4k-instruct",
    model_provider="huggingface",
    temperature=0.7,
    max_tokens=1024,
)
agent = create_deep_agent(model=model)

import os
from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint
from deepagents import create_deep_agent

os.environ["HUGGINGFACEHUB_API_TOKEN"] = "hf_..."

llm = HuggingFaceEndpoint(
    repo_id="microsoft/Phi-3-mini-4k-instruct",
    temperature=0.7,
    max_length=1024,
)
model = ChatHuggingFace(llm=llm)
agent = create_deep_agent(model=model)

传递任何支持的模型字符串，或已初始化的模型实例。例如：

pip install -U "langchain[deepseek]"

uv add "langchain[deepseek]"

from deepagents import create_deep_agent

agent = create_deep_agent(model="provider:model-name")

from deepagents import create_deep_agent
from langchain.chat_models import init_chat_model

model = init_chat_model("provider:model-name")
agent = create_deep_agent(model=model)

from langchain_<provider> import Chat<Provider>
# from langchain_deepseek import ChatDeepSeek

from deepagents import create_deep_agent

model = Chat<Provider>(model="model-name")
# model = ChatDeepSeek(model="deepseek-v4-pro")

agent = create_deep_agent(model=model)

::: :::js

👉 阅读 OpenAI 对话模型集成文档

npm install @langchain/openai deepagents

pnpm install @langchain/openai deepagents

yarn add @langchain/openai deepagents

bun add @langchain/openai deepagents

import { createDeepAgent } from "deepagents";

process.env.OPENAI_API_KEY = "your-api-key";

const agent = createDeepAgent({ model: "gpt-5.5" });
// this calls initChatModel for the specified model with default parameters
// to use specific model parameters, use initChatModel directly

import { initChatModel } from "langchain";
import { createDeepAgent } from "deepagents";

process.env.OPENAI_API_KEY = "your-api-key";

const model = await initChatModel("gpt-5.5");
const agent = createDeepAgent({
  model,
  temperature: 0,
});

import { ChatOpenAI } from "@langchain/openai";
import { createDeepAgent } from "deepagents";

const agent = createDeepAgent({
  model: new ChatOpenAI({
    model: "gpt-5.5",
    apiKey: "your-api-key",
    temperature: 0,
  }),
});

👉 阅读 Anthropic 对话模型集成文档

npm install @langchain/anthropic deepagents

pnpm install @langchain/anthropic deepagents

yarn add @langchain/anthropic deepagents

bun add @langchain/anthropic deepagents

import { createDeepAgent } from "deepagents";

process.env.ANTHROPIC_API_KEY = "your-api-key";

const agent = createDeepAgent({ model: "anthropic:claude-sonnet-4-6" });
// this calls initChatModel for the specified model with default parameters
// to use specific model parameters, use initChatModel directly

import { initChatModel } from "langchain";
import { createDeepAgent } from "deepagents";

process.env.ANTHROPIC_API_KEY = "your-api-key";

const model = await initChatModel("claude-sonnet-4-6");
const agent = createDeepAgent({
  model,
  temperature: 0,
});

import { ChatAnthropic } from "@langchain/anthropic";
import { createDeepAgent } from "deepagents";

const agent = createDeepAgent({
  model: new ChatAnthropic({
    model: "claude-sonnet-4-6",
    apiKey: "your-api-key",
    temperature: 0,
  }),
});

👉 阅读 Azure 对话模型集成文档

npm install @langchain/azure deepagents

pnpm install @langchain/azure deepagents

yarn add @langchain/azure deepagents

bun add @langchain/azure deepagents

import { createDeepAgent } from "deepagents";

process.env.AZURE_OPENAI_API_KEY = "your-api-key";
process.env.AZURE_OPENAI_ENDPOINT = "your-endpoint";
process.env.OPENAI_API_VERSION = "your-api-version";

const agent = createDeepAgent({ model: "azure_openai:gpt-5.5" });
// this calls initChatModel for the specified model with default parameters
// to use specific model parameters, use initChatModel directly

import { initChatModel } from "langchain";
import { createDeepAgent } from "deepagents";

process.env.AZURE_OPENAI_API_KEY = "your-api-key";
process.env.AZURE_OPENAI_ENDPOINT = "your-endpoint";
process.env.OPENAI_API_VERSION = "your-api-version";

const model = await initChatModel("azure_openai:gpt-5.5");
const agent = createDeepAgent({
  model,
  temperature: 0,
});

import { AzureChatOpenAI } from "@langchain/openai";
import { createDeepAgent } from "deepagents";

const agent = createDeepAgent({
  model: new AzureChatOpenAI({
    model: "gpt-5.5",
    azureOpenAIApiKey: "your-api-key",
    azureOpenAIApiEndpoint: "your-endpoint",
    azureOpenAIApiVersion: "your-api-version",
    temperature: 0,
  }),
});

👉 阅读 ChatGoogle 对话模型集成文档

npm install @langchain/google deepagents

pnpm install @langchain/google deepagents

yarn add @langchain/google deepagents

bun add @langchain/google deepagents

import { createDeepAgent } from "deepagents";

process.env.GOOGLE_API_KEY = "your-api-key";

const agent = createDeepAgent({ model: "google:gemini-3.1-pro-preview" });
// this calls initChatModel for the specified model with default parameters
// to use specific model parameters, use initChatModel directly

import { initChatModel } from "langchain";
import { createDeepAgent } from "deepagents";

process.env.GOOGLE_API_KEY = "your-api-key";

const model = await initChatModel("google:gemini-3.1-pro-preview");
const agent = createDeepAgent({
  model,
  temperature: 0,
});

import { ChatGoogle } from "@langchain/google/node";
import { createDeepAgent } from "deepagents";

const agent = createDeepAgent({
  model: new ChatGoogle({
    model: "gemini-3.1-pro-preview",
    apiKey: "your-api-key",
    temperature: 0,
  }),
});

👉 阅读 AWS Bedrock 对话模型集成文档

npm install @langchain/aws deepagents

pnpm install @langchain/aws deepagents

yarn add @langchain/aws deepagents

bun add @langchain/aws deepagents

import { createDeepAgent } from "deepagents";

// Follow the steps here to configure your credentials:
// https://docs.aws.amazon.com/bedrock/latest/userguide/getting-started.html

const agent = createDeepAgent({ model: "bedrock:anthropic.claude-sonnet-4-6" });
// this calls initChatModel for the specified model with default parameters
// to use specific model parameters, use initChatModel directly

import { initChatModel } from "langchain";
import { createDeepAgent } from "deepagents";

// Follow the steps here to configure your credentials:
// https://docs.aws.amazon.com/bedrock/latest/userguide/getting-started.html

const model = await initChatModel("bedrock:anthropic.claude-sonnet-4-6");
const agent = createDeepAgent({
  model,
  temperature: 0,
});

import { ChatBedrockConverse } from "@langchain/aws";
import { createDeepAgent } from "deepagents";

// Follow the steps here to configure your credentials:
// https://docs.aws.amazon.com/bedrock/latest/userguide/getting-started.html

const agent = createDeepAgent({
  model: new ChatBedrockConverse({
    model: "anthropic.claude-sonnet-4-6",
    region: "us-east-2",
    temperature: 0,
  }),
});

支持任何兼容的模型字符串，或已初始化的模型实例：

import { initChatModel } from "langchain";
import { createDeepAgent } from "deepagents";

const model = await initChatModel("provider:model-name");
const agent = createDeepAgent({ model });

:::

对话模型会自动重试瞬态 API 失败（使用指数退避）。关于默认值、限制和调整代码示例，请参考 LangChain 的模型页面 max_retries / timeout。

工具

除了用于文件管理和子智能体创建的内置工具，您还可以提供自定义工具： :::python

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,
    )


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

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,
    )


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

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,
    )


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

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,
    )


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

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,
    )


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

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,
    )


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

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,
    )


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

::: :::js

import { tool } from "langchain";
import { TavilySearch } from "@langchain/tavily";
import { createDeepAgent } from "deepagents";
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),
      topic: z
        .enum(["general", "news", "finance"])
        .optional()
        .default("general"),
      includeRawContent: z.boolean().optional().default(false),
    }),
  },
);

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

import { tool } from "langchain";
import { TavilySearch } from "@langchain/tavily";
import { createDeepAgent } from "deepagents";
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),
      topic: z
        .enum(["general", "news", "finance"])
        .optional()
        .default("general"),
      includeRawContent: z.boolean().optional().default(false),
    }),
  },
);

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

import { tool } from "langchain";
import { TavilySearch } from "@langchain/tavily";
import { createDeepAgent } from "deepagents";
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),
      topic: z
        .enum(["general", "news", "finance"])
        .optional()
        .default("general"),
      includeRawContent: z.boolean().optional().default(false),
    }),
  },
);

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

import { tool } from "langchain";
import { TavilySearch } from "@langchain/tavily";
import { createDeepAgent } from "deepagents";
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),
      topic: z
        .enum(["general", "news", "finance"])
        .optional()
        .default("general"),
      includeRawContent: z.boolean().optional().default(false),
    }),
  },
);

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

import { tool } from "langchain";
import { TavilySearch } from "@langchain/tavily";
import { createDeepAgent } from "deepagents";
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),
      topic: z
        .enum(["general", "news", "finance"])
        .optional()
        .default("general"),
      includeRawContent: z.boolean().optional().default(false),
    }),
  },
);

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

import { tool } from "langchain";
import { TavilySearch } from "@langchain/tavily";
import { createDeepAgent } from "deepagents";
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),
      topic: z
        .enum(["general", "news", "finance"])
        .optional()
        .default("general"),
      includeRawContent: z.boolean().optional().default(false),
    }),
  },
);

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

import { tool } from "langchain";
import { TavilySearch } from "@langchain/tavily";
import { createDeepAgent } from "deepagents";
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),
      topic: z
        .enum(["general", "news", "finance"])
        .optional()
        .default("general"),
      includeRawContent: z.boolean().optional().default(false),
    }),
  },
);

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

:::

MCP 工具

Deep Agents 完全支持模型上下文协议 (MCP) 工具。您可以从任何 MCP 服务器（数据库、API、文件系统等）加载工具，并直接将它们传递给 create_deep_agent。

:::python 使用 mcp 额外功能安装 LangChain 以连接到 MCP 服务器：

pip install "langchain[mcp]"

import asyncio

from deepagents import create_deep_agent
from langchain.mcp import MCPAdapter


async def main():
    config = {"mcpServers": {"my_server": {"url": "http://localhost:8000/mcp"}}}
    async with MCPAdapter(config) as adapter:
        tools = await adapter.list_tools()
        agent = create_deep_agent(
            model="google_genai:gemini-3.6-flash",
            tools=tools,
        )
        await agent.ainvoke(
            {
                "messages": [
                    {"role": "user", "content": "Use the MCP server to help me."}
                ]
            },
            config={"configurable": {"thread_id": "1"}},
        )

import asyncio

from deepagents import create_deep_agent
from langchain.mcp import MCPAdapter


async def main():
    config = {"mcpServers": {"my_server": {"url": "http://localhost:8000/mcp"}}}
    async with MCPAdapter(config) as adapter:
        tools = await adapter.list_tools()
        agent = create_deep_agent(
            model="openai:gpt-5.5",
            tools=tools,
        )
        await agent.ainvoke(
            {
                "messages": [
                    {"role": "user", "content": "Use the MCP server to help me."}
                ]
            },
            config={"configurable": {"thread_id": "1"}},
        )

import asyncio

from deepagents import create_deep_agent
from langchain.mcp import MCPAdapter


async def main():
    config = {"mcpServers": {"my_server": {"url": "http://localhost:8000/mcp"}}}
    async with MCPAdapter(config) as adapter:
        tools = await adapter.list_tools()
        agent = create_deep_agent(
            model="anthropic:claude-sonnet-5",
            tools=tools,
        )
        await agent.ainvoke(
            {
                "messages": [
                    {"role": "user", "content": "Use the MCP server to help me."}
                ]
            },
            config={"configurable": {"thread_id": "1"}},
        )

import asyncio

from deepagents import create_deep_agent
from langchain.mcp import MCPAdapter


async def main():
    config = {"mcpServers": {"my_server": {"url": "http://localhost:8000/mcp"}}}
    async with MCPAdapter(config) as adapter:
        tools = await adapter.list_tools()
        agent = create_deep_agent(
            model="openrouter:z-ai/glm-5.2",
            tools=tools,
        )
        await agent.ainvoke(
            {
                "messages": [
                    {"role": "user", "content": "Use the MCP server to help me."}
                ]
            },
            config={"configurable": {"thread_id": "1"}},
        )

import asyncio

from deepagents import create_deep_agent
from langchain.mcp import MCPAdapter


async def main():
    config = {"mcpServers": {"my_server": {"url": "http://localhost:8000/mcp"}}}
    async with MCPAdapter(config) as adapter:
        tools = await adapter.list_tools()
        agent = create_deep_agent(
            model="fireworks:accounts/fireworks/models/glm-5p2",
            tools=tools,
        )
        await agent.ainvoke(
            {
                "messages": [
                    {"role": "user", "content": "Use the MCP server to help me."}
                ]
            },
            config={"configurable": {"thread_id": "1"}},
        )

import asyncio

from deepagents import create_deep_agent
from langchain.mcp import MCPAdapter


async def main():
    config = {"mcpServers": {"my_server": {"url": "http://localhost:8000/mcp"}}}
    async with MCPAdapter(config) as adapter:
        tools = await adapter.list_tools()
        agent = create_deep_agent(
            model="baseten:zai-org/GLM-5.2",
            tools=tools,
        )
        await agent.ainvoke(
            {
                "messages": [
                    {"role": "user", "content": "Use the MCP server to help me."}
                ]
            },
            config={"configurable": {"thread_id": "1"}},
        )

import asyncio

from deepagents import create_deep_agent
from langchain.mcp import MCPAdapter


async def main():
    config = {"mcpServers": {"my_server": {"url": "http://localhost:8000/mcp"}}}
    async with MCPAdapter(config) as adapter:
        tools = await adapter.list_tools()
        agent = create_deep_agent(
            model="ollama:north-mini-code-1.0",
            tools=tools,
        )
        await agent.ainvoke(
            {
                "messages": [
                    {"role": "user", "content": "Use the MCP server to help me."}
                ]
            },
            config={"configurable": {"thread_id": "1"}},
        )

::: :::js 使用 @langchain/mcp-adapters 连接到 MCP 服务器：

npm install @langchain/mcp-adapters

import { createDeepAgent } from "deepagents";

const { MultiServerMCPClient } = await import("@langchain/mcp-adapters");

const client = new MultiServerMCPClient({
    my_server: {
        transport: "http",
        url: "http://localhost:8000/mcp",
    },
});

const tools = await client.getTools();

const agent = await createDeepAgent({
    model: "google:gemini-3.6-flash",
    tools,
});

const result = await agent.invoke({
    messages: [{ role: "user", content: "Use the MCP server to help me." }],
});

import { createDeepAgent } from "deepagents";

const { MultiServerMCPClient } = await import("@langchain/mcp-adapters");

const client = new MultiServerMCPClient({
    my_server: {
        transport: "http",
        url: "http://localhost:8000/mcp",
    },
});

const tools = await client.getTools();

const agent = await createDeepAgent({
    model: "openai:gpt-5.5",
    tools,
});

const result = await agent.invoke({
    messages: [{ role: "user", content: "Use the MCP server to help me." }],
});

import { createDeepAgent } from "deepagents";

const { MultiServerMCPClient } = await import("@langchain/mcp-adapters");

const client = new MultiServerMCPClient({
    my_server: {
        transport: "http",
        url: "http://localhost:8000/mcp",
    },
});

const tools = await client.getTools();

const agent = await createDeepAgent({
    model: "anthropic:claude-sonnet-5",
    tools,
});

const result = await agent.invoke({
    messages: [{ role: "user", content: "Use the MCP server to help me." }],
});

import { createDeepAgent } from "deepagents";

const { MultiServerMCPClient } = await import("@langchain/mcp-adapters");

const client = new MultiServerMCPClient({
    my_server: {
        transport: "http",
        url: "http://localhost:8000/mcp",
    },
});

const tools = await client.getTools();

const agent = await createDeepAgent({
    model: "openrouter:z-ai/glm-5.2",
    tools,
});

const result = await agent.invoke({
    messages: [{ role: "user", content: "Use the MCP server to help me." }],
});

import { createDeepAgent } from "deepagents";

const { MultiServerMCPClient } = await import("@langchain/mcp-adapters");

const client = new MultiServerMCPClient({
    my_server: {
        transport: "http",
        url: "http://localhost:8000/mcp",
    },
});

const tools = await client.getTools();

const agent = await createDeepAgent({
    model: "fireworks:accounts/fireworks/models/glm-5p2",
    tools,
});

const result = await agent.invoke({
    messages: [{ role: "user", content: "Use the MCP server to help me." }],
});

import { createDeepAgent } from "deepagents";

const { MultiServerMCPClient } = await import("@langchain/mcp-adapters");

const client = new MultiServerMCPClient({
    my_server: {
        transport: "http",
        url: "http://localhost:8000/mcp",
    },
});

const tools = await client.getTools();

const agent = await createDeepAgent({
    model: "baseten:zai-org/GLM-5.2",
    tools,
});

const result = await agent.invoke({
    messages: [{ role: "user", content: "Use the MCP server to help me." }],
});

import { createDeepAgent } from "deepagents";

const { MultiServerMCPClient } = await import("@langchain/mcp-adapters");

const client = new MultiServerMCPClient({
    my_server: {
        transport: "http",
        url: "http://localhost:8000/mcp",
    },
});

const tools = await client.getTools();

const agent = await createDeepAgent({
    model: "ollama:north-mini-code-1.0",
    tools,
});

const result = await agent.invoke({
    messages: [{ role: "user", content: "Use the MCP server to help me." }],
});

::: 有关详细配置选项，包括 stdio 服务器、OAuth 身份验证、工具过滤和有状态会话，请参阅完整的 MCP 指南。

系统提示词

将 system_prompt= 传递给智能体以提供您的自定义指令： :::python

from deepagents import create_deep_agent

research_instructions = """\
You are an expert researcher. Your job is to conduct \
thorough research, and then write a polished report. \
"""

agent = create_deep_agent(
    model="google_genai:gemini-3.6-flash",
    system_prompt=research_instructions,
)

from deepagents import create_deep_agent

research_instructions = """\
You are an expert researcher. Your job is to conduct \
thorough research, and then write a polished report. \
"""

agent = create_deep_agent(
    model="openai:gpt-5.5",
    system_prompt=research_instructions,
)

from deepagents import create_deep_agent

research_instructions = """\
You are an expert researcher. Your job is to conduct \
thorough research, and then write a polished report. \
"""

agent = create_deep_agent(
    model="anthropic:claude-sonnet-5",
    system_prompt=research_instructions,
)

from deepagents import create_deep_agent

research_instructions = """\
You are an expert researcher. Your job is to conduct \
thorough research, and then write a polished report. \
"""

agent = create_deep_agent(
    model="openrouter:z-ai/glm-5.2",
    system_prompt=research_instructions,
)

from deepagents import create_deep_agent

research_instructions = """\
You are an expert researcher. Your job is to conduct \
thorough research, and then write a polished report. \
"""

agent = create_deep_agent(
    model="fireworks:accounts/fireworks/models/glm-5p2",
    system_prompt=research_instructions,
)

from deepagents import create_deep_agent

research_instructions = """\
You are an expert researcher. Your job is to conduct \
thorough research, and then write a polished report. \
"""

agent = create_deep_agent(
    model="baseten:zai-org/GLM-5.2",
    system_prompt=research_instructions,
)

from deepagents import create_deep_agent

research_instructions = """\
You are an expert researcher. Your job is to conduct \
thorough research, and then write a polished report. \
"""

agent = create_deep_agent(
    model="ollama:north-mini-code-1.0",
    system_prompt=research_instructions,
)

::: :::js

import { createDeepAgent } from "deepagents";

const researchInstructions =
  `You are an expert researcher. ` +
  `Your job is to conduct thorough research, and then ` +
  `write a polished report.`;

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

import { createDeepAgent } from "deepagents";

const researchInstructions =
  `You are an expert researcher. ` +
  `Your job is to conduct thorough research, and then ` +
  `write a polished report.`;

const agent = createDeepAgent({
  model: "openai:gpt-5.5",
  systemPrompt: researchInstructions,
});

import { createDeepAgent } from "deepagents";

const researchInstructions =
  `You are an expert researcher. ` +
  `Your job is to conduct thorough research, and then ` +
  `write a polished report.`;

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

import { createDeepAgent } from "deepagents";

const researchInstructions =
  `You are an expert researcher. ` +
  `Your job is to conduct thorough research, and then ` +
  `write a polished report.`;

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

import { createDeepAgent } from "deepagents";

const researchInstructions =
  `You are an expert researcher. ` +
  `Your job is to conduct thorough research, and then ` +
  `write a polished report.`;

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

import { createDeepAgent } from "deepagents";

const researchInstructions =
  `You are an expert researcher. ` +
  `Your job is to conduct thorough research, and then ` +
  `write a polished report.`;

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

import { createDeepAgent } from "deepagents";

const researchInstructions =
  `You are an expert researcher. ` +
  `Your job is to conduct thorough research, and then ` +
  `write a polished report.`;

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

:::

除了字符串，主要智能体还接受一个 @[SystemMessage] 结构化内容块；Deep Agents 保留这些块（子智能体字典规范保持为字符串）。

Subagent prompts

声明式子智能体根据其自身模型解析配置覆盖，然后将解析后的配置的base_system_prompt/system_prompt_suffix应用于子智能体编写的system_prompt。仅包含system_prompt_suffix的配置（内置Anthropic/OpenAI配置的常见情况）将追加到编写的提示词中。设置base_system_prompt的配置将完全替换它。

General-purpose subagent prompt

自动添加的通用子智能体将其基础提示词解析为**general_purpose_subagent.system_prompt（如果设置）-> HarnessProfile.base_system_prompt（如果设置）-> SDK通用默认值**，并在顶部叠加配置后缀。当两个覆盖字段都设置时，通用特定字段优先，因此同时调整两个字段的调用者不会看到其通用覆盖被无声丢弃：

from deepagents import (
    GeneralPurposeSubagentProfile,
    HarnessProfile,
    register_harness_profile,
)

register_harness_profile(
    "anthropic",
    HarnessProfile(
        base_system_prompt="You are ACME's support orchestrator.",  # main agent
        general_purpose_subagent=GeneralPurposeSubagentProfile(
            system_prompt="You are a research subagent. Cite sources.",  # GP subagent
        ),
        system_prompt_suffix="Always think step by step.",
    ),
)

栈	最终系统提示词
主智能体	`"You are ACME's support orchestrator." + SUFFIX`
通用子智能体	`"You are a research subagent. Cite sources." + SUFFIX`

中间件

深度智能体支持任何中间件，包括以下内置中间件、LangChain预构建的中间件、特定提供者的中间件以及您自己编写的自定义中间件。 :::python 将中间件传递给create_deep_agent的middleware参数。每个实例通过将其.name与栈中已有的内置条目进行匹配，合并到深度智能体栈中：匹配则替换该实例，不匹配则插入@[PatchToolCallsMiddleware]之后。参见覆盖默认中间件实例。 ::: 将中间件传递给 middleware 的 createDeepAgent 参数。每个实例通过其 .name 被合并到 Deep Agents stack 中。名称与内置条目匹配的实例会替换该条目。其他内容则插入到 @[PatchToolCallsMiddleware] 之后。

Deep Agents 堆栈

:::python create_deep_agent 以固定顺序构建中间件。bare stack 是仅包含模型时得到的结果。full stack 是完整的组装顺序，包括仅在传递可选参数或解析的 harness profile 贡献时出现的槽位。 ::: :::js createDeepAgent 以固定顺序构建中间件。bare stack 是仅包含模型时得到的结果。full stack 是完整的组装顺序，包括仅在传递可选参数或解析的 harness profile 贡献时出现的槽位。 :::

裸栈模式

:::python 仅包含 model（无其他可选参数）时，主智能体通常包括：

@[FilesystemMiddleware]
@[SubAgentMiddleware]（因为通用子智能体会自动添加，除非 harness profile 禁用它）
@[SummarizationMiddleware]
@[PatchToolCallsMiddleware]
提示词缓存中间件（始终注册；对不支持的模型，每个条目不执行操作）
Harness profile 附加功能和排除工具过滤，如果解析的模型配置定义了它们 :::

:::js 仅有一个model（无其他可选参数），主智能体通常包括：

@[FilesystemMiddleware]
@[SubAgentMiddleware]（因为通用子智能体会自动添加，除非 harness profile 禁用它）
@[SummarizationMiddleware]
@[PatchToolCallsMiddleware]
提示词缓存中间件（为支持的提供者添加；其他地方不执行操作）
Harness profile 附加功能和排除工具过滤，如果解析的模型配置定义了它们
@[UnsupportedContentMiddleware] :::

全栈

从第一到最后一层： :::python

@[FilesystemMiddleware]: 处理文件系统操作，如读取、写入和导航目录。当你传递 permissions 时，这里包含文件系统权限强制执行，以便它可以评估智能体可能调用的每个工具。
@[SubAgentMiddleware]: 仅当至少有一个同步子智能体可用时。生成和协调子智能体以委托任务。包含在裸栈中，因为通用子智能体默认自动添加；通过禁用该子智能体并传递无同步 subagents 来省略它。参见无子智能体运行。
@[SummarizationMiddleware]: 当对话变长时（通过 @[create_summarization_middleware]），将消息历史压缩以保持在上下文限制内。
@[PatchToolCallsMiddleware]: 在消息历史中修复悬空工具调用，当运行在中断后恢复或接收格式错误的工具调用参数时。在Anthropic提示缓存和下方的尾栈之前运行。
@[AsyncSubAgentMiddleware]: 仅当你配置异步子智能体时。
你的中间件参数: 作为 middleware 参数传递的可选中间件在Patch之后但在堆栈其余部分之前合并。其 .name 与上面内置条目之一匹配的实例会替换该实例，而不是复制它；其他任何内容都会放在这里。参见覆盖默认中间件实例。
利用配置文件附加: 解析的模型配置文件提供的特定于提供者的中间件，如果有的话。
@[SkillsMiddleware]: 仅当你传递 skills 时。在您的中间件之后、提示缓存之前运行，因此它看到总结的对话和实际调用的模型。传递一个名为 SkillsMiddleware 的中间件会将其就地替换。
提示缓存 (@[AnthropicPromptCachingMiddleware] 和 @[BedrockPromptCachingMiddleware]): 两者始终注册并在Patch之后以及您的中间件之后运行，以便缓存的prefix与实际发送到模型的匹配。它们在它们不支持的模型上执行no-ops (unsupported_model_behavior="ignore")，因此Anthropic中间件适用于Anthropic模型，Bedrock中间件适用于具有缓存支持的AWS Bedrock模型。
@[MemoryMiddleware]: 仅当你传递 memory 时。
MemoryMiddleware 放在 profile extras 和提示缓存中间件之后，因此注入记忆的更新不太可能使缓存prefix失效。在 create_deep_agent 实现注释中也提到了相同的排序问题。
HumanInTheLoopMiddleware: 仅当通过 interrupt_on 时。在配置的工具调用处暂停，等待人工批准或输入。
排除工具过滤: 当 harness profile 列出排除的工具时，中间件会从智能体中移除这些工具。

::: :::js

@[FilesystemMiddleware]: 处理文件系统操作，如读取、写入和导航目录。当通过 permissions 时，文件系统权限强制执行包含在内，以便它可以评估智能体可能调用的每个工具。
@[SubAgentMiddleware]: 仅当至少有一个同步子智能体可用时。生成和协调子智能体以委托任务。包含在裸栈中，因为通用子智能体默认自动添加；通过禁用该子智能体并传递无同步 subagents 来省略它。参见无子智能体运行。
@[SummarizationMiddleware]: 当对话变长时，通过 @[createSummarizationMiddleware] 将消息历史压缩以保持在上下文限制内。
@[PatchToolCallsMiddleware]: 在运行中断后恢复或接收到格式错误的工具调用参数时，修复消息历史中的悬空工具调用。运行在 Anthropic 提示词缓存和下方的尾栈之前。
@[AsyncSubAgentMiddleware]: 仅当您配置异步子智能体时。
您的中间件参数: 作为 middleware 参数传递的可选中间件在 Patch 之后但在其余栈之前合并。其 .name 与内置条目匹配的实例会原位替换该条目，而不是重复它。其他内容会放在这里。
Harness profile 附加: 从解析的模型 profile 中提供的特定于提供者的中间件，如果有的话。
@[SkillsMiddleware]: 仅当通过 skills，或通过 createSkillsMiddleware 实例传递到 middleware。无论如何，它都在您的中间件之后、提示词缓存之前运行，因此可以看到总结的对话和实际调用的模型。
提示词缓存 (@[AnthropicPromptCachingMiddleware] 和 @[BedrockPromptCachingMiddleware]): 分别为 Anthropic 模型和 Amazon Bedrock Converse 模型自动添加。两者都在 Patch 之后和您的中间件之后运行，因此缓存的prefix与实际发送给模型的内容匹配。
@[MemoryMiddleware]: 仅当通过 memory。
MemoryMiddleware 放置在 profile 附加和提示词缓存中间件之后，因此注入的记忆更新不太可能使缓存前缀失效。在 createDeepAgent 实现评论中也提到了相同的排序问题。
HumanInTheLoopMiddleware: 仅当传递 interruptOn 时。在配置的工具调用处暂停，等待人工批准或输入。
排除工具过滤: 当 harness profile 列出排除的工具时，中间件会从智能体中移除这些工具。
@[UnsupportedContentMiddleware]: 使用文本占位符重写请求中的不支持的多元模态内容。

:::

同步子智能体栈

:::python 内置的通用子智能体和每个声明式的同步 SubAgent 图使用一个栈，create_deep_agent 在代码中构建。它在大致形状上与主智能体匹配（文件系统、摘要、Patch、配置文件额外信息、技能、Anthropic 和 Bedrock 缓存、可选权限），但子智能体图中没有 @[SubAgentMiddleware]（只有父智能体暴露 task 工具）。当声明式子智能体设置 interrupt_on 时，该值会被转发到 create_agent 以供子智能体使用，这会为配置的工具调用设置人工参与处理。 ::: :::js 内置的通用子智能体和每个声明式的同步 SubAgent 图使用一个栈，createDeepAgent 在代码中构建。它在大致形状上与主智能体匹配（文件系统、摘要、Patch、配置文件额外信息、技能、Anthropic 和 Bedrock 缓存、可选权限），但子智能体图中没有 @[SubAgentMiddleware]（只有父智能体暴露 task 工具）。当声明式子智能体设置 interruptOn 时，该值会被转发到 createAgent 以供子智能体使用，这会为配置的工具调用设置人工参与处理。 :::

预构建的中间件

LangChain 提供了额外的预构建中间件，允许你添加各种功能，如重试、回退或 PII 检测。更多详情请参见预构建的中间件。 :::python deepagents 库还暴露了 @[create_summarization_tool_middleware]，使智能体能够在适当时机触发摘要——例如在任务之间——而不是在固定的 Token 间隔。更多详情请参见摘要。 ::: :::js deepagents 包还为相同的工作流程暴露了 @[createSummarizationMiddleware]。更多详情请参见摘要。 :::

提供商特定的中间件

有关针对特定 LLM 提供商优化的提供商特定中间件，请参见中间件集成。

自定义中间件

你可以提供额外的中间件来扩展功能、添加工具或实现自定义钩子： :::python

from langchain.agents.middleware import wrap_tool_call
from langchain.tools import tool
from deepagents import create_deep_agent


@tool
def get_weather(city: str) -> str:
    """Get the weather in a city."""
    return f"The weather in {city} is sunny."


call_count = [0]  # Use list to allow modification in nested function


@wrap_tool_call
def log_tool_calls(request, handler):
    """Intercept and log every tool call - demonstrates cross-cutting concern."""
    call_count[0] += 1
    tool_name = request.name if hasattr(request, "name") else str(request)

    print(f"[Middleware] Tool call #{call_count[0]}: {tool_name}")
    print(f"[Middleware] Arguments: {request.args if hasattr(request, 'args') else 'N/A'}")

    # Execute the tool call
    result = handler(request)

    # Log the result
    print(f"[Middleware] Tool call #{call_count[0]} completed")

    return result


agent = create_deep_agent(
    model="google_genai:gemini-3.6-flash",
    tools=[get_weather],
    middleware=[log_tool_calls],
)

from langchain.agents.middleware import wrap_tool_call
from langchain.tools import tool
from deepagents import create_deep_agent


@tool
def get_weather(city: str) -> str:
    """Get the weather in a city."""
    return f"The weather in {city} is sunny."


call_count = [0]  # Use list to allow modification in nested function


@wrap_tool_call
def log_tool_calls(request, handler):
    """Intercept and log every tool call - demonstrates cross-cutting concern."""
    call_count[0] += 1
    tool_name = request.name if hasattr(request, "name") else str(request)

    print(f"[Middleware] Tool call #{call_count[0]}: {tool_name}")
    print(f"[Middleware] Arguments: {request.args if hasattr(request, 'args') else 'N/A'}")

    # Execute the tool call
    result = handler(request)

    # Log the result
    print(f"[Middleware] Tool call #{call_count[0]} completed")

    return result


agent = create_deep_agent(
    model="openai:gpt-5.5",
    tools=[get_weather],
    middleware=[log_tool_calls],
)

from langchain.agents.middleware import wrap_tool_call
from langchain.tools import tool
from deepagents import create_deep_agent


@tool
def get_weather(city: str) -> str:
    """Get the weather in a city."""
    return f"The weather in {city} is sunny."


call_count = [0]  # Use list to allow modification in nested function


@wrap_tool_call
def log_tool_calls(request, handler):
    """Intercept and log every tool call - demonstrates cross-cutting concern."""
    call_count[0] += 1
    tool_name = request.name if hasattr(request, "name") else str(request)

    print(f"[Middleware] Tool call #{call_count[0]}: {tool_name}")
    print(f"[Middleware] Arguments: {request.args if hasattr(request, 'args') else 'N/A'}")

    # Execute the tool call
    result = handler(request)

    # Log the result
    print(f"[Middleware] Tool call #{call_count[0]} completed")

    return result


agent = create_deep_agent(
    model="anthropic:claude-sonnet-5",
    tools=[get_weather],
    middleware=[log_tool_calls],
)

from langchain.agents.middleware import wrap_tool_call
from langchain.tools import tool
from deepagents import create_deep_agent


@tool
def get_weather(city: str) -> str:
    """Get the weather in a city."""
    return f"The weather in {city} is sunny."


call_count = [0]  # Use list to allow modification in nested function


@wrap_tool_call
def log_tool_calls(request, handler):
    """Intercept and log every tool call - demonstrates cross-cutting concern."""
    call_count[0] += 1
    tool_name = request.name if hasattr(request, "name") else str(request)

    print(f"[Middleware] Tool call #{call_count[0]}: {tool_name}")
    print(f"[Middleware] Arguments: {request.args if hasattr(request, 'args') else 'N/A'}")

    # Execute the tool call
    result = handler(request)

    # Log the result
    print(f"[Middleware] Tool call #{call_count[0]} completed")

    return result


agent = create_deep_agent(
    model="openrouter:z-ai/glm-5.2",
    tools=[get_weather],
    middleware=[log_tool_calls],
)

from langchain.agents.middleware import wrap_tool_call
from langchain.tools import tool
from deepagents import create_deep_agent


@tool
def get_weather(city: str) -> str:
    """Get the weather in a city."""
    return f"The weather in {city} is sunny."


call_count = [0]  # Use list to allow modification in nested function


@wrap_tool_call
def log_tool_calls(request, handler):
    """Intercept and log every tool call - demonstrates cross-cutting concern."""
    call_count[0] += 1
    tool_name = request.name if hasattr(request, "name") else str(request)

    print(f"[Middleware] Tool call #{call_count[0]}: {tool_name}")
    print(f"[Middleware] Arguments: {request.args if hasattr(request, 'args') else 'N/A'}")

    # Execute the tool call
    result = handler(request)

    # Log the result
    print(f"[Middleware] Tool call #{call_count[0]} completed")

    return result


agent = create_deep_agent(
    model="fireworks:accounts/fireworks/models/glm-5p2",
    tools=[get_weather],
    middleware=[log_tool_calls],
)

from langchain.agents.middleware import wrap_tool_call
from langchain.tools import tool
from deepagents import create_deep_agent


@tool
def get_weather(city: str) -> str:
    """Get the weather in a city."""
    return f"The weather in {city} is sunny."


call_count = [0]  # Use list to allow modification in nested function


@wrap_tool_call
def log_tool_calls(request, handler):
    """Intercept and log every tool call - demonstrates cross-cutting concern."""
    call_count[0] += 1
    tool_name = request.name if hasattr(request, "name") else str(request)

    print(f"[Middleware] Tool call #{call_count[0]}: {tool_name}")
    print(f"[Middleware] Arguments: {request.args if hasattr(request, 'args') else 'N/A'}")

    # Execute the tool call
    result = handler(request)

    # Log the result
    print(f"[Middleware] Tool call #{call_count[0]} completed")

    return result


agent = create_deep_agent(
    model="baseten:zai-org/GLM-5.2",
    tools=[get_weather],
    middleware=[log_tool_calls],
)

from langchain.agents.middleware import wrap_tool_call
from langchain.tools import tool
from deepagents import create_deep_agent


@tool
def get_weather(city: str) -> str:
    """Get the weather in a city."""
    return f"The weather in {city} is sunny."


call_count = [0]  # Use list to allow modification in nested function


@wrap_tool_call
def log_tool_calls(request, handler):
    """Intercept and log every tool call - demonstrates cross-cutting concern."""
    call_count[0] += 1
    tool_name = request.name if hasattr(request, "name") else str(request)

    print(f"[Middleware] Tool call #{call_count[0]}: {tool_name}")
    print(f"[Middleware] Arguments: {request.args if hasattr(request, 'args') else 'N/A'}")

    # Execute the tool call
    result = handler(request)

    # Log the result
    print(f"[Middleware] Tool call #{call_count[0]} completed")

    return result


agent = create_deep_agent(
    model="ollama:north-mini-code-1.0",
    tools=[get_weather],
    middleware=[log_tool_calls],
)

::: :::js

import { tool, createMiddleware } from "langchain";
import { createDeepAgent } from "deepagents";
import * as z from "zod";

const getWeather = tool(
  ({ city }: { city: string }) => {
    return `The weather in ${city} is sunny.`;
  },
  {
    name: "get_weather",
    description: "Get the weather in a city.",
    schema: z.object({
      city: z.string(),
    }),
  },
);

let callCount = 0;

const logToolCallsMiddleware = createMiddleware({
  name: "LogToolCallsMiddleware",
  wrapToolCall: async (request, handler) => {
    // Intercept and log every tool call - demonstrates cross-cutting concern
    callCount += 1;
    const toolName = request.toolCall.name;

    console.log(`[Middleware] Tool call #${callCount}: ${toolName}`);
    console.log(
      `[Middleware] Arguments: ${JSON.stringify(request.toolCall.args)}`,
    );

    // Execute the tool call
    const result = await handler(request);

    // Log the result
    console.log(`[Middleware] Tool call #${callCount} completed`);

    return result;
  },
});

const agent = await createDeepAgent({
  model: "google:gemini-3.6-flash",
  tools: [getWeather] as any,
  middleware: [logToolCallsMiddleware] as any,
});

import { tool, createMiddleware } from "langchain";
import { createDeepAgent } from "deepagents";
import * as z from "zod";

const getWeather = tool(
  ({ city }: { city: string }) => {
    return `The weather in ${city} is sunny.`;
  },
  {
    name: "get_weather",
    description: "Get the weather in a city.",
    schema: z.object({
      city: z.string(),
    }),
  },
);

let callCount = 0;

const logToolCallsMiddleware = createMiddleware({
  name: "LogToolCallsMiddleware",
  wrapToolCall: async (request, handler) => {
    // Intercept and log every tool call - demonstrates cross-cutting concern
    callCount += 1;
    const toolName = request.toolCall.name;

    console.log(`[Middleware] Tool call #${callCount}: ${toolName}`);
    console.log(
      `[Middleware] Arguments: ${JSON.stringify(request.toolCall.args)}`,
    );

    // Execute the tool call
    const result = await handler(request);

    // Log the result
    console.log(`[Middleware] Tool call #${callCount} completed`);

    return result;
  },
});

const agent = await createDeepAgent({
  model: "openai:gpt-5.5",
  tools: [getWeather] as any,
  middleware: [logToolCallsMiddleware] as any,
});

import { tool, createMiddleware } from "langchain";
import { createDeepAgent } from "deepagents";
import * as z from "zod";

const getWeather = tool(
  ({ city }: { city: string }) => {
    return `The weather in ${city} is sunny.`;
  },
  {
    name: "get_weather",
    description: "Get the weather in a city.",
    schema: z.object({
      city: z.string(),
    }),
  },
);

let callCount = 0;

const logToolCallsMiddleware = createMiddleware({
  name: "LogToolCallsMiddleware",
  wrapToolCall: async (request, handler) => {
    // Intercept and log every tool call - demonstrates cross-cutting concern
    callCount += 1;
    const toolName = request.toolCall.name;

    console.log(`[Middleware] Tool call #${callCount}: ${toolName}`);
    console.log(
      `[Middleware] Arguments: ${JSON.stringify(request.toolCall.args)}`,
    );

    // Execute the tool call
    const result = await handler(request);

    // Log the result
    console.log(`[Middleware] Tool call #${callCount} completed`);

    return result;
  },
});

const agent = await createDeepAgent({
  model: "anthropic:claude-sonnet-5",
  tools: [getWeather] as any,
  middleware: [logToolCallsMiddleware] as any,
});

import { tool, createMiddleware } from "langchain";
import { createDeepAgent } from "deepagents";
import * as z from "zod";

const getWeather = tool(
  ({ city }: { city: string }) => {
    return `The weather in ${city} is sunny.`;
  },
  {
    name: "get_weather",
    description: "Get the weather in a city.",
    schema: z.object({
      city: z.string(),
    }),
  },
);

let callCount = 0;

const logToolCallsMiddleware = createMiddleware({
  name: "LogToolCallsMiddleware",
  wrapToolCall: async (request, handler) => {
    // Intercept and log every tool call - demonstrates cross-cutting concern
    callCount += 1;
    const toolName = request.toolCall.name;

    console.log(`[Middleware] Tool call #${callCount}: ${toolName}`);
    console.log(
      `[Middleware] Arguments: ${JSON.stringify(request.toolCall.args)}`,
    );

    // Execute the tool call
    const result = await handler(request);

    // Log the result
    console.log(`[Middleware] Tool call #${callCount} completed`);

    return result;
  },
});

const agent = await createDeepAgent({
  model: "openrouter:z-ai/glm-5.2",
  tools: [getWeather] as any,
  middleware: [logToolCallsMiddleware] as any,
});

import { tool, createMiddleware } from "langchain";
import { createDeepAgent } from "deepagents";
import * as z from "zod";

const getWeather = tool(
  ({ city }: { city: string }) => {
    return `The weather in ${city} is sunny.`;
  },
  {
    name: "get_weather",
    description: "Get the weather in a city.",
    schema: z.object({
      city: z.string(),
    }),
  },
);

let callCount = 0;

const logToolCallsMiddleware = createMiddleware({
  name: "LogToolCallsMiddleware",
  wrapToolCall: async (request, handler) => {
    // Intercept and log every tool call - demonstrates cross-cutting concern
    callCount += 1;
    const toolName = request.toolCall.name;

    console.log(`[Middleware] Tool call #${callCount}: ${toolName}`);
    console.log(
      `[Middleware] Arguments: ${JSON.stringify(request.toolCall.args)}`,
    );

    // Execute the tool call
    const result = await handler(request);

    // Log the result
    console.log(`[Middleware] Tool call #${callCount} completed`);

    return result;
  },
});

const agent = await createDeepAgent({
  model: "fireworks:accounts/fireworks/models/glm-5p2",
  tools: [getWeather] as any,
  middleware: [logToolCallsMiddleware] as any,
});

import { tool, createMiddleware } from "langchain";
import { createDeepAgent } from "deepagents";
import * as z from "zod";

const getWeather = tool(
  ({ city }: { city: string }) => {
    return `The weather in ${city} is sunny.`;
  },
  {
    name: "get_weather",
    description: "Get the weather in a city.",
    schema: z.object({
      city: z.string(),
    }),
  },
);

let callCount = 0;

const logToolCallsMiddleware = createMiddleware({
  name: "LogToolCallsMiddleware",
  wrapToolCall: async (request, handler) => {
    // Intercept and log every tool call - demonstrates cross-cutting concern
    callCount += 1;
    const toolName = request.toolCall.name;

    console.log(`[Middleware] Tool call #${callCount}: ${toolName}`);
    console.log(
      `[Middleware] Arguments: ${JSON.stringify(request.toolCall.args)}`,
    );

    // Execute the tool call
    const result = await handler(request);

    // Log the result
    console.log(`[Middleware] Tool call #${callCount} completed`);

    return result;
  },
});

const agent = await createDeepAgent({
  model: "baseten:zai-org/GLM-5.2",
  tools: [getWeather] as any,
  middleware: [logToolCallsMiddleware] as any,
});

import { tool, createMiddleware } from "langchain";
import { createDeepAgent } from "deepagents";
import * as z from "zod";

const getWeather = tool(
  ({ city }: { city: string }) => {
    return `The weather in ${city} is sunny.`;
  },
  {
    name: "get_weather",
    description: "Get the weather in a city.",
    schema: z.object({
      city: z.string(),
    }),
  },
);

let callCount = 0;

const logToolCallsMiddleware = createMiddleware({
  name: "LogToolCallsMiddleware",
  wrapToolCall: async (request, handler) => {
    // Intercept and log every tool call - demonstrates cross-cutting concern
    callCount += 1;
    const toolName = request.toolCall.name;

    console.log(`[Middleware] Tool call #${callCount}: ${toolName}`);
    console.log(
      `[Middleware] Arguments: ${JSON.stringify(request.toolCall.args)}`,
    );

    // Execute the tool call
    const result = await handler(request);

    // Log the result
    console.log(`[Middleware] Tool call #${callCount} completed`);

    return result;
  },
});

const agent = await createDeepAgent({
  model: "ollama:north-mini-code-1.0",
  tools: [getWeather] as any,
  middleware: [logToolCallsMiddleware] as any,
});

:::

初始化后不要修改属性如果你需要在钩子调用之间跟踪值（例如计数器或累积数据），请使用图状态。图状态按设计是线程范围的，因此并发下的更新是安全的。请这样做：:::python

from langchain.agents.middleware import AgentMiddleware


class CustomMiddleware(AgentMiddleware):
    def __init__(self):
        pass

    def before_agent(self, state, runtime):
        return {"x": state.get("x", 0) + 1}  # Update graph state instead

::::::js

const customMiddleware = createMiddleware({
  name: "CustomMiddleware",
  beforeAgent: async (state) => {
    return { x: (state.x ?? 0) + 1 }; // Update graph state instead
  },
});

:::不要这样做：:::python

class CustomMiddlewareBad(AgentMiddleware):
    def __init__(self):
        self.x = 1

    def before_agent(self, state, runtime):
        self.x += 1  # Mutation causes race conditions

::::::js

let x = 1;

const customMiddlewareBad = createMiddleware({
  name: "CustomMiddleware",
  beforeAgent: async () => {
    x += 1; // Mutation causes race conditions
  },
});

::::::python 原地修改，例如在 before_agent 中修改 self.x 或在钩子中更改其他共享值，可能会导致细微的bug和竞态条件，因为许多操作并发运行（子智能体、并行工具和不同线程上的并行调用）。有关使用自定义属性扩展状态的详细信息，请参阅自定义中间件 - 自定义状态模式。 ::: :::js 原地修改，例如在 beforeAgent 中修改 state.x、在 beforeAgent 中变异共享变量，或在钩子中更改其他共享值，可能会导致细微的bug和竞态条件，因为许多操作并发运行（子智能体、并行工具和不同线程上的并行调用）。 :::如果你必须在自定义中间件中使用原地修改，请考虑当子智能体、并行工具或并发智能体调用同时运行时会发生什么。

覆盖默认中间件实例

:::python

通过匹配 .name 来覆盖默认中间件需要 deepagents>=0.7。

将一个中间件实例传递给 .name，使其匹配深度智能体堆栈中的条目，例如 @[SummarizationMiddleware]，以替换该内置实例，而不是追加一个副本。任何你传递的中间件实例，其 .name 不匹配内置条目，都不会被替换，它位于最后一个核心中间件条目之后，以及配置文件、提示词缓存和记忆之前。参见完整堆栈了解完整顺序。

from deepagents import create_deep_agent
from deepagents.backends import StateBackend
from deepagents.middleware import SummarizationMiddleware

backend = StateBackend()
model = "openai:gpt-5.5"

custom_summarization = SummarizationMiddleware(
    model=model,
    backend=backend,
    summary_prompt="Your custom summary prompt here.",
)

agent = create_deep_agent(
    model=model,
    middleware=[custom_summarization],  # replaces the default SummarizationMiddleware
)

覆盖替换默认中间件实例，而不是与其合并。这意味着你的替换必须配置所有它需要的设置。这对于 FilesystemMiddleware 特别重要：如果你覆盖它，你必须将 backend（如果适用，则为 permissions）直接传递给你的自定义实例，因为它不会继承传递给 create_deep_agent() 的 backend= 和 permissions=。要限制可用的文件系统工具，请将 tools 允许列表传递给你的自定义 @[FilesystemMiddleware] 实例；参见虚拟文件系统访问的“限制文件系统工具”示例。

通用子智能体（深度智能体会自动添加），会从主智能体继承默认中间件的覆盖，而不会传递主智能体特有的中间件。通过 subagents= 定义的声明式子智能体不会继承主智能体的中间件定制。将覆盖直接传递到该子智能体自己的 middleware 字段中以应用；该字段与 middleware= 相同的方式匹配于同步子智能体栈。

示例

Adjust when summarization triggers

使用自定义 trigger 和 keep 阈值覆盖 @[SummarizationMiddleware]，以便比默认值更早或更晚地压缩对话历史，并控制每次压缩后有多少条最近消息得以保留。

from deepagents import create_deep_agent
from deepagents.backends import StateBackend
from deepagents.middleware import SummarizationMiddleware

backend = StateBackend()
model = "anthropic:claude-sonnet-4-6"

agent = create_deep_agent(
    model=model,
    middleware=[
        SummarizationMiddleware(
            model=model,
            backend=backend,
            trigger=("tokens", 100000),  # summarize once the conversation exceeds 100k tokens
            keep=("messages", 20),  # keep the most recent 20 messages verbatim
        ),
    ],
)

trigger 也接受 ("fraction", ...) 作为模型上下文窗口的百分比，并且阈值列表使用 OR 语义将它们组合在一起。参见 @[SummarizationMiddleware] 参考文档以获取完整选项集。

使用更便宜的模型生成摘要

summarizer 参数需要 deepagents>=0.7.26。

使用 summarizer= 覆盖 @[SummarizationMiddleware]，以便用不同的模型或自定义可调用对象生成摘要。主 model 仍然提供配置文件和 Token 计数。传入模型名称字符串或 BaseChatModel 实例，即可使用该模型和 summary_prompt 生成摘要。传入 Runnable 或可调用对象直接生成摘要文本；此时不使用 summary_prompt。

from deepagents import create_deep_agent
from deepagents.backends import StateBackend
from deepagents.middleware import SummarizationMiddleware

backend = StateBackend()
model = "anthropic:claude-sonnet-4-6"

agent = create_deep_agent(
    model=model,
    middleware=[
        SummarizationMiddleware(
            model=model,  # profile and token counting
            backend=backend,
            summarizer="anthropic:claude-haiku-5-5",  # cheaper model writes the summary
        ),
    ],
)

Update the prompt cache TTL

覆盖 @[AnthropicPromptCachingMiddleware] 以延长缓存寿命，超过默认的 5m TTL，适用于在回合之间有较长间隔的智能体。参见提示词缓存了解默认情况下缓存的用法。

from deepagents import create_deep_agent
from langchain_anthropic.middleware import AnthropicPromptCachingMiddleware

agent = create_deep_agent(
    model="anthropic:claude-sonnet-4-6",
    middleware=[
        AnthropicPromptCachingMiddleware(ttl="1h"),  # replaces the default 5m TTL
    ],
)

Restrict the enabled filesystem tools

FilesystemMiddleware 上的 tools 允许列表需要 deepagents>=0.7。

使用 tools 允许列表覆盖 @[FilesystemMiddleware]，仅向模型暴露文件系统工具的子集，而不是完整的默认集。

from deepagents import create_deep_agent
from deepagents.backends import StateBackend
from deepagents.middleware import FilesystemMiddleware

backend = StateBackend()

# Read-only agent: write_file, edit_file, delete, and execute are never shown
agent = create_deep_agent(
    model="anthropic:claude-sonnet-4-6",
    backend=backend,
    middleware=[
        FilesystemMiddleware(backend=backend, tools=["read_file", "ls", "glob", "grep"]),
    ],
)

更多详情请参见限制文件系统工具。

Customize how the skill catalog appears in the system prompt

使用自定义 system_prompt= 模板覆盖 @[SkillsMiddleware]，以控制自动生成的技能目录的呈现方式——例如，添加周边上下文、重新排序部分，或将路由提示（优先级、类别偏差）放置在与目录相同的块中。模板必须包含 {skills_locations}、{skills_list} 和 {skills_load_warnings} 插槽，中间件在每次回合时都会替换这些插槽——因此，随着技能的添加、重命名或删除，目录会自动保持同步。以下示例将路由提示与目录并置：

from deepagents import create_deep_agent
from deepagents.backends.filesystem import FilesystemBackend
from deepagents.middleware.skills import SkillsMiddleware

backend = FilesystemBackend(root_dir="/path/to/skills")

custom_skills_prompt = """## Skills

Routing hints:
- For research topics → prefer arxiv-search first
- For general questions → use web-research
- For LangGraph documentation → langgraph-docs

{skills_locations}

{skills_list}

{skills_load_warnings}
"""

agent = create_deep_agent(
    model="anthropic:claude-sonnet-4-6",
    middleware=[
        SkillsMiddleware(
            backend=backend,
            sources=["/path/to/skills"],
            system_prompt=custom_skills_prompt,
        ),
    ],
)

不要在此情况下将 skills= 传递给 create_deep_agent：覆盖实例已经拥有 backend 和 sources。任何缺失的槽位（{skills_locations}， {skills_list}，{skills_load_warnings}）在构建时引发 ValueError。

Suppress the auto-generated skill catalog

使用 system_prompt=None 覆盖 @[SkillsMiddleware] 来加载技能，而完全不在系统提示词中追加技能部分。技能保留在 state["skills_metadata"] 中，技能文件可以通过文件系统工具保持可访问性，因此，如果调用者更喜欢在 create_deep_agent(system_prompt=...) 中编写自己的描述块（例如，一个紧凑的手写路由摘要），他们可以添加他们需要的精确指导，而无需内置的指导。

from deepagents import create_deep_agent
from deepagents.backends.filesystem import FilesystemBackend
from deepagents.middleware.skills import SkillsMiddleware

backend = FilesystemBackend(root_dir="/path/to/skills")

agent = create_deep_agent(
    model="anthropic:claude-sonnet-4-6",
    system_prompt="""You are a research assistant.

Skills (read the SKILL.md file when relevant):
- /path/to/skills/arxiv-search/SKILL.md — papers
- /path/to/skills/web-research/SKILL.md — general web lookups
- /path/to/skills/langgraph-docs/SKILL.md — LangGraph documentation
""",
    middleware=[
        SkillsMiddleware(
            backend=backend,
            sources=["/path/to/skills"],
            system_prompt=None,
        ),
    ],
)

技能名称、路径以及在 create_deep_agent 的 system_prompt 中任何手写的提示都是调用者负责在技能变化时保持同步。

::: :::js 传递一个中间件实例，其 .name 与 Deep Agents 堆栈中的条目匹配，例如 @[SummarizationMiddleware]，以替换该内置实例，而不是追加重复项。任何你传递的中间件，其 .name 不与内置条目匹配，都不会被替换，它位于最后一个核心中间件条目之后，以及配置文件、提示词缓存和记忆之前。参见完整堆栈了解完整顺序。

import {
  createDeepAgent,
  createSummarizationMiddleware,
  StateBackend,
} from "deepagents";

const backend = new StateBackend();
const model = "openai:gpt-5.5";

const customSummarization = createSummarizationMiddleware({
  model,
  backend,
  summaryPrompt: "Your custom summary prompt here.",
});

const agent = createDeepAgent({
  model,
  middleware: [customSummarization], // replaces the default SummarizationMiddleware
});

覆盖替换默认中间件实例，它不会与该实例合并。这意味着你的替换必须完全配置它需要的任何设置。这对于 FilesystemMiddleware 特别重要：如果你覆盖它，你必须将 backend（如果适用，则包括 permissions）直接传递给 createFilesystemMiddleware，因为它不会继承传递给 createDeepAgent 的 backend 和 permissions。要限制可用的文件系统工具，将一个 tools 允许列表传递给你的自定义 @[FilesystemMiddleware] 实例；参见虚拟文件系统访问。

通用子智能体，Deep Agents 自动添加的，会从主智能体继承默认中间件的覆盖，而不会传递主智能体特有的中间件。通过 subagents 定义的声明式子智能体不会继承主智能体的中间件定制。将覆盖直接传递到该子智能体自己的 middleware 字段中以应用它；该字段与同步子智能体堆栈匹配，方式与 middleware 与主智能体匹配相同。

示例

Keep binary file content out of checkpointed history

使用 offloadBinaryContent: true 覆盖 @[FilesystemMiddleware] 以在 /blobs 后端存储二进制 read_file 负载和内联 HumanMessage 媒体，而不是在检查点消息历史中存储。状态保持一个小型引用；模型请求从每个运行的缓存或后端重新水化。这使代理在多个回合中读取许多二进制文件时保持检查点大小较小。

二进制内容卸载需要 deepagents>=1.14.2。使用一个后端，该后端将对象存储在图状态之外，例如沙盒或 FilesystemBackend。当 /blobs 路由到 StateBackend 时，卸载没有效果。将您传递给 createFilesystemMiddleware 的相同 backend 传递给 createDeepAgent。

import {
  createDeepAgent,
  createFilesystemMiddleware,
  FilesystemBackend,
} from "deepagents";

const backend = new FilesystemBackend({
  rootDir: "/path/to/project",
  virtualMode: true,
});

const agent = createDeepAgent({
  model: "anthropic:claude-sonnet-4-6",
  backend,
  middleware: [
    createFilesystemMiddleware({ backend, offloadBinaryContent: true }),
  ],
});

更多信息，请参阅 Offload binary content。

:::

解释器

使用 interpreters 添加一个 eval 工具，该工具在作用域 QuickJS 运行时中运行 JavaScript。当代理需要以编程方式组合工具、批量处理工作、在代码中处理错误或在不完整 shell 环境中转换结构化数据时，解释器很有用。 :::python

from deepagents import create_deep_agent
from langchain_quickjs import CodeInterpreterMiddleware

agent = create_deep_agent(
    model="google_genai:gemini-3.6-flash",
    middleware=[CodeInterpreterMiddleware()],
)

from deepagents import create_deep_agent
from langchain_quickjs import CodeInterpreterMiddleware

agent = create_deep_agent(
    model="openai:gpt-5.5",
    middleware=[CodeInterpreterMiddleware()],
)

from deepagents import create_deep_agent
from langchain_quickjs import CodeInterpreterMiddleware

agent = create_deep_agent(
    model="anthropic:claude-sonnet-5",
    middleware=[CodeInterpreterMiddleware()],
)

from deepagents import create_deep_agent
from langchain_quickjs import CodeInterpreterMiddleware

agent = create_deep_agent(
    model="openrouter:z-ai/glm-5.2",
    middleware=[CodeInterpreterMiddleware()],
)

from deepagents import create_deep_agent
from langchain_quickjs import CodeInterpreterMiddleware

agent = create_deep_agent(
    model="fireworks:accounts/fireworks/models/glm-5p2",
    middleware=[CodeInterpreterMiddleware()],
)

from deepagents import create_deep_agent
from langchain_quickjs import CodeInterpreterMiddleware

agent = create_deep_agent(
    model="baseten:zai-org/GLM-5.2",
    middleware=[CodeInterpreterMiddleware()],
)

from deepagents import create_deep_agent
from langchain_quickjs import CodeInterpreterMiddleware

agent = create_deep_agent(
    model="ollama:north-mini-code-1.0",
    middleware=[CodeInterpreterMiddleware()],
)

::: :::js

import { createDeepAgent } from "deepagents";
import { createCodeInterpreterMiddleware } from "@langchain/quickjs";

const agent = createDeepAgent({
  model: "google:gemini-3.6-flash",
  middleware: [createCodeInterpreterMiddleware()],
});

import { createDeepAgent } from "deepagents";
import { createCodeInterpreterMiddleware } from "@langchain/quickjs";

const agent = createDeepAgent({
  model: "openai:gpt-5.5",
  middleware: [createCodeInterpreterMiddleware()],
});

import { createDeepAgent } from "deepagents";
import { createCodeInterpreterMiddleware } from "@langchain/quickjs";

const agent = createDeepAgent({
  model: "anthropic:claude-sonnet-5",
  middleware: [createCodeInterpreterMiddleware()],
});

import { createDeepAgent } from "deepagents";
import { createCodeInterpreterMiddleware } from "@langchain/quickjs";

const agent = createDeepAgent({
  model: "openrouter:z-ai/glm-5.2",
  middleware: [createCodeInterpreterMiddleware()],
});

import { createDeepAgent } from "deepagents";
import { createCodeInterpreterMiddleware } from "@langchain/quickjs";

const agent = createDeepAgent({
  model: "fireworks:accounts/fireworks/models/glm-5p2",
  middleware: [createCodeInterpreterMiddleware()],
});

import { createDeepAgent } from "deepagents";
import { createCodeInterpreterMiddleware } from "@langchain/quickjs";

const agent = createDeepAgent({
  model: "baseten:zai-org/GLM-5.2",
  middleware: [createCodeInterpreterMiddleware()],
});

import { createDeepAgent } from "deepagents";
import { createCodeInterpreterMiddleware } from "@langchain/quickjs";

const agent = createDeepAgent({
  model: "ollama:north-mini-code-1.0",
  middleware: [createCodeInterpreterMiddleware()],
});

::: 有关设置、程序化工具调用、子代理编排和限制的信息，请参阅 Interpreters。

子代理

为了隔离详细工作并避免上下文膨胀，请使用子代理： :::python

import os
from typing import Literal

from deepagents import create_deep_agent
from tavily import TavilyClient

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,
    )


research_subagent = {
    "name": "research-agent",
    "description": "Used to research more in depth questions",
    "system_prompt": "You are a great researcher",
    "tools": [internet_search],
    "model": "openai:gpt-5.5",  # Optional override, defaults to main agent model
}
subagents = [research_subagent]

agent = create_deep_agent(
    model="google_genai:gemini-3.6-flash",
    subagents=subagents,
)

::: :::js

import { tool } from "langchain";
import { TavilySearch } from "@langchain/tavily";
import { createDeepAgent, type SubAgent } from "deepagents";
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),
      topic: z
        .enum(["general", "news", "finance"])
        .optional()
        .default("general"),
      includeRawContent: z.boolean().optional().default(false),
    }),
  },
);

const researchSubagent: SubAgent = {
  name: "research-agent",
  description: "Used to research more in depth questions",
  systemPrompt: "You are a great researcher",
  tools: [internetSearch],
  model: "google:gemini-3.6-flash", // Optional override, defaults to main agent model
};
const subagents = [researchSubagent];

const agent = createDeepAgent({
  model: "google:gemini-3.6-flash",
  subagents,
});

import { tool } from "langchain";
import { TavilySearch } from "@langchain/tavily";
import { createDeepAgent, type SubAgent } from "deepagents";
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),
      topic: z
        .enum(["general", "news", "finance"])
        .optional()
        .default("general"),
      includeRawContent: z.boolean().optional().default(false),
    }),
  },
);

const researchSubagent: SubAgent = {
  name: "research-agent",
  description: "Used to research more in depth questions",
  systemPrompt: "You are a great researcher",
  tools: [internetSearch],
  model: "openai:gpt-5.5", // Optional override, defaults to main agent model
};
const subagents = [researchSubagent];

const agent = createDeepAgent({
  model: "google:gemini-3.6-flash",
  subagents,
});

import { tool } from "langchain";
import { TavilySearch } from "@langchain/tavily";
import { createDeepAgent, type SubAgent } from "deepagents";
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),
      topic: z
        .enum(["general", "news", "finance"])
        .optional()
        .default("general"),
      includeRawContent: z.boolean().optional().default(false),
    }),
  },
);

const researchSubagent: SubAgent = {
  name: "research-agent",
  description: "Used to research more in depth questions",
  systemPrompt: "You are a great researcher",
  tools: [internetSearch],
  model: "anthropic:claude-sonnet-5", // Optional override, defaults to main agent model
};
const subagents = [researchSubagent];

const agent = createDeepAgent({
  model: "google:gemini-3.6-flash",
  subagents,
});

import { tool } from "langchain";
import { TavilySearch } from "@langchain/tavily";
import { createDeepAgent, type SubAgent } from "deepagents";
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),
      topic: z
        .enum(["general", "news", "finance"])
        .optional()
        .default("general"),
      includeRawContent: z.boolean().optional().default(false),
    }),
  },
);

const researchSubagent: SubAgent = {
  name: "research-agent",
  description: "Used to research more in depth questions",
  systemPrompt: "You are a great researcher",
  tools: [internetSearch],
  model: "openrouter:z-ai/glm-5.2", // Optional override, defaults to main agent model
};
const subagents = [researchSubagent];

const agent = createDeepAgent({
  model: "google:gemini-3.6-flash",
  subagents,
});

import { tool } from "langchain";
import { TavilySearch } from "@langchain/tavily";
import { createDeepAgent, type SubAgent } from "deepagents";
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),
      topic: z
        .enum(["general", "news", "finance"])
        .optional()
        .default("general"),
      includeRawContent: z.boolean().optional().default(false),
    }),
  },
);

const researchSubagent: SubAgent = {
  name: "research-agent",
  description: "Used to research more in depth questions",
  systemPrompt: "You are a great researcher",
  tools: [internetSearch],
  model: "fireworks:accounts/fireworks/models/glm-5p2", // Optional override, defaults to main agent model
};
const subagents = [researchSubagent];

const agent = createDeepAgent({
  model: "google:gemini-3.6-flash",
  subagents,
});

import { tool } from "langchain";
import { TavilySearch } from "@langchain/tavily";
import { createDeepAgent, type SubAgent } from "deepagents";
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),
      topic: z
        .enum(["general", "news", "finance"])
        .optional()
        .default("general"),
      includeRawContent: z.boolean().optional().default(false),
    }),
  },
);

const researchSubagent: SubAgent = {
  name: "research-agent",
  description: "Used to research more in depth questions",
  systemPrompt: "You are a great researcher",
  tools: [internetSearch],
  model: "baseten:zai-org/GLM-5.2", // Optional override, defaults to main agent model
};
const subagents = [researchSubagent];

const agent = createDeepAgent({
  model: "google:gemini-3.6-flash",
  subagents,
});

import { tool } from "langchain";
import { TavilySearch } from "@langchain/tavily";
import { createDeepAgent, type SubAgent } from "deepagents";
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),
      topic: z
        .enum(["general", "news", "finance"])
        .optional()
        .default("general"),
      includeRawContent: z.boolean().optional().default(false),
    }),
  },
);

const researchSubagent: SubAgent = {
  name: "research-agent",
  description: "Used to research more in depth questions",
  systemPrompt: "You are a great researcher",
  tools: [internetSearch],
  model: "ollama:north-mini-code-1.0", // Optional override, defaults to main agent model
};
const subagents = [researchSubagent];

const agent = createDeepAgent({
  model: "google:gemini-3.6-flash",
  subagents,
});

::: 更多信息，请参阅 Subagents。

后端

深度代理的工具可以使用虚拟文件系统来存储、访问和编辑文件。默认情况下，深度代理使用一个 @[StateBackend]。如果您正在使用 skills 或 memory，您必须在创建代理之前将预期的技能或内存文件添加到后端。

一个线程作用域文件系统后端存储在 langgraph 状态中。文件在线程内（通过您的检查点器）跨回合持久化，并且不会跨线程共享。:::python

from deepagents import create_deep_agent
from deepagents.backends import StateBackend

# By default we provide a StateBackend
agent = create_deep_agent(model="google_genai:gemini-3.6-flash")

# Under the hood, it looks like
agent2 = create_deep_agent(
    model="google_genai:gemini-3.6-flash",
    backend=StateBackend(),
)

from deepagents import create_deep_agent
from deepagents.backends import StateBackend

# By default we provide a StateBackend
agent = create_deep_agent(model="openai:gpt-5.5")

# Under the hood, it looks like
agent2 = create_deep_agent(
    model="openai:gpt-5.5",
    backend=StateBackend(),
)

from deepagents import create_deep_agent
from deepagents.backends import StateBackend

# By default we provide a StateBackend
agent = create_deep_agent(model="anthropic:claude-sonnet-5")

# Under the hood, it looks like
agent2 = create_deep_agent(
    model="anthropic:claude-sonnet-5",
    backend=StateBackend(),
)

from deepagents import create_deep_agent
from deepagents.backends import StateBackend

# By default we provide a StateBackend
agent = create_deep_agent(model="openrouter:z-ai/glm-5.2")

# Under the hood, it looks like
agent2 = create_deep_agent(
    model="openrouter:z-ai/glm-5.2",
    backend=StateBackend(),
)

from deepagents import create_deep_agent
from deepagents.backends import StateBackend

# By default we provide a StateBackend
agent = create_deep_agent(model="fireworks:accounts/fireworks/models/glm-5p2")

# Under the hood, it looks like
agent2 = create_deep_agent(
    model="fireworks:accounts/fireworks/models/glm-5p2",
    backend=StateBackend(),
)

from deepagents import create_deep_agent
from deepagents.backends import StateBackend

# By default we provide a StateBackend
agent = create_deep_agent(model="baseten:zai-org/GLM-5.2")

# Under the hood, it looks like
agent2 = create_deep_agent(
    model="baseten:zai-org/GLM-5.2",
    backend=StateBackend(),
)

from deepagents import create_deep_agent
from deepagents.backends import StateBackend

# By default we provide a StateBackend
agent = create_deep_agent(model="ollama:north-mini-code-1.0")

# Under the hood, it looks like
agent2 = create_deep_agent(
    model="ollama:north-mini-code-1.0",
    backend=StateBackend(),
)

::::::js

import { createDeepAgent, StateBackend } from "deepagents";

// By default we provide a StateBackend
const agent = createDeepAgent();

// Under the hood, it looks like
const agent2 = createDeepAgent({
  backend: new StateBackend(),
});

:::

本地计算机的文件系统。

此后端授予代理直接文件系统读写访问权限。小心使用，仅在适当的环境中使用。更多信息，请参阅 FilesystemBackend。

:::python

from deepagents import create_deep_agent
from deepagents.backends import FilesystemBackend

agent = create_deep_agent(
    model="google_genai:gemini-3.6-flash",
    backend=FilesystemBackend(root_dir=".", virtual_mode=True),
)

from deepagents import create_deep_agent
from deepagents.backends import FilesystemBackend

agent = create_deep_agent(
    model="openai:gpt-5.5",
    backend=FilesystemBackend(root_dir=".", virtual_mode=True),
)

from deepagents import create_deep_agent
from deepagents.backends import FilesystemBackend

agent = create_deep_agent(
    model="anthropic:claude-sonnet-5",
    backend=FilesystemBackend(root_dir=".", virtual_mode=True),
)

from deepagents import create_deep_agent
from deepagents.backends import FilesystemBackend

agent = create_deep_agent(
    model="openrouter:z-ai/glm-5.2",
    backend=FilesystemBackend(root_dir=".", virtual_mode=True),
)

from deepagents import create_deep_agent
from deepagents.backends import FilesystemBackend

agent = create_deep_agent(
    model="fireworks:accounts/fireworks/models/glm-5p2",
    backend=FilesystemBackend(root_dir=".", virtual_mode=True),
)

from deepagents import create_deep_agent
from deepagents.backends import FilesystemBackend

agent = create_deep_agent(
    model="baseten:zai-org/GLM-5.2",
    backend=FilesystemBackend(root_dir=".", virtual_mode=True),
)

from deepagents import create_deep_agent
from deepagents.backends import FilesystemBackend

agent = create_deep_agent(
    model="ollama:north-mini-code-1.0",
    backend=FilesystemBackend(root_dir=".", virtual_mode=True),
)

::::::js

import { createDeepAgent, FilesystemBackend } from "deepagents";

const agent = createDeepAgent({
  model: "google:gemini-3.6-flash",
  backend: new FilesystemBackend({ rootDir: ".", virtualMode: true }),
});

import { createDeepAgent, FilesystemBackend } from "deepagents";

const agent = createDeepAgent({
  model: "openai:gpt-5.5",
  backend: new FilesystemBackend({ rootDir: ".", virtualMode: true }),
});

import { createDeepAgent, FilesystemBackend } from "deepagents";

const agent = createDeepAgent({
  model: "anthropic:claude-sonnet-5",
  backend: new FilesystemBackend({ rootDir: ".", virtualMode: true }),
});

import { createDeepAgent, FilesystemBackend } from "deepagents";

const agent = createDeepAgent({
  model: "openrouter:z-ai/glm-5.2",
  backend: new FilesystemBackend({ rootDir: ".", virtualMode: true }),
});

import { createDeepAgent, FilesystemBackend } from "deepagents";

const agent = createDeepAgent({
  model: "fireworks:accounts/fireworks/models/glm-5p2",
  backend: new FilesystemBackend({ rootDir: ".", virtualMode: true }),
});

import { createDeepAgent, FilesystemBackend } from "deepagents";

const agent = createDeepAgent({
  model: "baseten:zai-org/GLM-5.2",
  backend: new FilesystemBackend({ rootDir: ".", virtualMode: true }),
});

import { createDeepAgent, FilesystemBackend } from "deepagents";

const agent = createDeepAgent({
  model: "ollama:north-mini-code-1.0",
  backend: new FilesystemBackend({ rootDir: ".", virtualMode: true }),
});

:::

将 FilesystemBackend 封装在 CompositeBackend 中，以防止内部智能体数据（卸载的工具结果、对话历史）与您的项目文件一起写入磁盘。请参阅推荐模式。

一种主机上直接执行 shell 命令的文件系统。提供文件系统工具以及用于运行命令的 execute 工具。

此后端授予智能体直接文件系统读写访问权限并且在主机上不受限制地执行 shell 命令。请谨慎使用，仅在适当的环境中使用。更多信息，请参阅 LocalShellBackend。

:::python

from deepagents import create_deep_agent
from deepagents.backends import LocalShellBackend

agent = create_deep_agent(
    model="google_genai:gemini-3.6-flash",
    backend=LocalShellBackend(root_dir=".", virtual_mode=True, env={"PATH": "/usr/bin:/bin"}),
)

from deepagents import create_deep_agent
from deepagents.backends import LocalShellBackend

agent = create_deep_agent(
    model="openai:gpt-5.5",
    backend=LocalShellBackend(root_dir=".", virtual_mode=True, env={"PATH": "/usr/bin:/bin"}),
)

from deepagents import create_deep_agent
from deepagents.backends import LocalShellBackend

agent = create_deep_agent(
    model="anthropic:claude-sonnet-5",
    backend=LocalShellBackend(root_dir=".", virtual_mode=True, env={"PATH": "/usr/bin:/bin"}),
)

from deepagents import create_deep_agent
from deepagents.backends import LocalShellBackend

agent = create_deep_agent(
    model="openrouter:z-ai/glm-5.2",
    backend=LocalShellBackend(root_dir=".", virtual_mode=True, env={"PATH": "/usr/bin:/bin"}),
)

from deepagents import create_deep_agent
from deepagents.backends import LocalShellBackend

agent = create_deep_agent(
    model="fireworks:accounts/fireworks/models/glm-5p2",
    backend=LocalShellBackend(root_dir=".", virtual_mode=True, env={"PATH": "/usr/bin:/bin"}),
)

from deepagents import create_deep_agent
from deepagents.backends import LocalShellBackend

agent = create_deep_agent(
    model="baseten:zai-org/GLM-5.2",
    backend=LocalShellBackend(root_dir=".", virtual_mode=True, env={"PATH": "/usr/bin:/bin"}),
)

from deepagents import create_deep_agent
from deepagents.backends import LocalShellBackend

agent = create_deep_agent(
    model="ollama:north-mini-code-1.0",
    backend=LocalShellBackend(root_dir=".", virtual_mode=True, env={"PATH": "/usr/bin:/bin"}),
)

::::::js

import { createDeepAgent, LocalShellBackend } from "deepagents";

const backend = new LocalShellBackend({ workingDirectory: "." });

const agent = createDeepAgent({
  model: "google:gemini-3.6-flash",
  backend,
});

import { createDeepAgent, LocalShellBackend } from "deepagents";

const backend = new LocalShellBackend({ workingDirectory: "." });

const agent = createDeepAgent({
  model: "openai:gpt-5.5",
  backend,
});

import { createDeepAgent, LocalShellBackend } from "deepagents";

const backend = new LocalShellBackend({ workingDirectory: "." });

const agent = createDeepAgent({
  model: "anthropic:claude-sonnet-5",
  backend,
});

import { createDeepAgent, LocalShellBackend } from "deepagents";

const backend = new LocalShellBackend({ workingDirectory: "." });

const agent = createDeepAgent({
  model: "openrouter:z-ai/glm-5.2",
  backend,
});

import { createDeepAgent, LocalShellBackend } from "deepagents";

const backend = new LocalShellBackend({ workingDirectory: "." });

const agent = createDeepAgent({
  model: "fireworks:accounts/fireworks/models/glm-5p2",
  backend,
});

import { createDeepAgent, LocalShellBackend } from "deepagents";

const backend = new LocalShellBackend({ workingDirectory: "." });

const agent = createDeepAgent({
  model: "baseten:zai-org/GLM-5.2",
  backend,
});

import { createDeepAgent, LocalShellBackend } from "deepagents";

const backend = new LocalShellBackend({ workingDirectory: "." });

const agent = createDeepAgent({
  model: "ollama:north-mini-code-1.0",
  backend,
});

:::

一种提供长期存储的文件系统，该存储 跨线程持久化。:::python

from deepagents import create_deep_agent
from deepagents.backends import StoreBackend
from langgraph.store.memory import InMemoryStore

agent = create_deep_agent(
    model="google_genai:gemini-3.6-flash",
    backend=StoreBackend(
        namespace=lambda rt: (rt.server_info.user.identity,),
    ),
    store=InMemoryStore(),  # Good for local dev; omit for LangSmith Deployment
)

from deepagents import create_deep_agent
from deepagents.backends import StoreBackend
from langgraph.store.memory import InMemoryStore

agent = create_deep_agent(
    model="openai:gpt-5.5",
    backend=StoreBackend(
        namespace=lambda rt: (rt.server_info.user.identity,),
    ),
    store=InMemoryStore(),  # Good for local dev; omit for LangSmith Deployment
)

from deepagents import create_deep_agent
from deepagents.backends import StoreBackend
from langgraph.store.memory import InMemoryStore

agent = create_deep_agent(
    model="anthropic:claude-sonnet-5",
    backend=StoreBackend(
        namespace=lambda rt: (rt.server_info.user.identity,),
    ),
    store=InMemoryStore(),  # Good for local dev; omit for LangSmith Deployment
)

from deepagents import create_deep_agent
from deepagents.backends import StoreBackend
from langgraph.store.memory import InMemoryStore

agent = create_deep_agent(
    model="openrouter:z-ai/glm-5.2",
    backend=StoreBackend(
        namespace=lambda rt: (rt.server_info.user.identity,),
    ),
    store=InMemoryStore(),  # Good for local dev; omit for LangSmith Deployment
)

from deepagents import create_deep_agent
from deepagents.backends import StoreBackend
from langgraph.store.memory import InMemoryStore

agent = create_deep_agent(
    model="fireworks:accounts/fireworks/models/glm-5p2",
    backend=StoreBackend(
        namespace=lambda rt: (rt.server_info.user.identity,),
    ),
    store=InMemoryStore(),  # Good for local dev; omit for LangSmith Deployment
)

from deepagents import create_deep_agent
from deepagents.backends import StoreBackend
from langgraph.store.memory import InMemoryStore

agent = create_deep_agent(
    model="baseten:zai-org/GLM-5.2",
    backend=StoreBackend(
        namespace=lambda rt: (rt.server_info.user.identity,),
    ),
    store=InMemoryStore(),  # Good for local dev; omit for LangSmith Deployment
)

from deepagents import create_deep_agent
from deepagents.backends import StoreBackend
from langgraph.store.memory import InMemoryStore

agent = create_deep_agent(
    model="ollama:north-mini-code-1.0",
    backend=StoreBackend(
        namespace=lambda rt: (rt.server_info.user.identity,),
    ),
    store=InMemoryStore(),  # Good for local dev; omit for LangSmith Deployment
)

::::::js

import { createDeepAgent, StoreBackend } from "deepagents";
import { InMemoryStore } from "@langchain/langgraph";

const store = new InMemoryStore(); // Good for local dev; omit for LangSmith Deployment

const agent = createDeepAgent({
  model: "google:gemini-3.6-flash",
  backend: new StoreBackend({
    namespace: (rt) => [rt.serverInfo.user.identity],
  }),
  store,
});

import { createDeepAgent, StoreBackend } from "deepagents";
import { InMemoryStore } from "@langchain/langgraph";

const store = new InMemoryStore(); // Good for local dev; omit for LangSmith Deployment

const agent = createDeepAgent({
  model: "openai:gpt-5.5",
  backend: new StoreBackend({
    namespace: (rt) => [rt.serverInfo.user.identity],
  }),
  store,
});

import { createDeepAgent, StoreBackend } from "deepagents";
import { InMemoryStore } from "@langchain/langgraph";

const store = new InMemoryStore(); // Good for local dev; omit for LangSmith Deployment

const agent = createDeepAgent({
  model: "anthropic:claude-sonnet-5",
  backend: new StoreBackend({
    namespace: (rt) => [rt.serverInfo.user.identity],
  }),
  store,
});

import { createDeepAgent, StoreBackend } from "deepagents";
import { InMemoryStore } from "@langchain/langgraph";

const store = new InMemoryStore(); // Good for local dev; omit for LangSmith Deployment

const agent = createDeepAgent({
  model: "openrouter:z-ai/glm-5.2",
  backend: new StoreBackend({
    namespace: (rt) => [rt.serverInfo.user.identity],
  }),
  store,
});

import { createDeepAgent, StoreBackend } from "deepagents";
import { InMemoryStore } from "@langchain/langgraph";

const store = new InMemoryStore(); // Good for local dev; omit for LangSmith Deployment

const agent = createDeepAgent({
  model: "fireworks:accounts/fireworks/models/glm-5p2",
  backend: new StoreBackend({
    namespace: (rt) => [rt.serverInfo.user.identity],
  }),
  store,
});

import { createDeepAgent, StoreBackend } from "deepagents";
import { InMemoryStore } from "@langchain/langgraph";

const store = new InMemoryStore(); // Good for local dev; omit for LangSmith Deployment

const agent = createDeepAgent({
  model: "baseten:zai-org/GLM-5.2",
  backend: new StoreBackend({
    namespace: (rt) => [rt.serverInfo.user.identity],
  }),
  store,
});

import { createDeepAgent, StoreBackend } from "deepagents";
import { InMemoryStore } from "@langchain/langgraph";

const store = new InMemoryStore(); // Good for local dev; omit for LangSmith Deployment

const agent = createDeepAgent({
  model: "ollama:north-mini-code-1.0",
  backend: new StoreBackend({
    namespace: (rt) => [rt.serverInfo.user.identity],
  }),
  store,
});

:::

部署到 LangSmith 部署时，请省略 store 参数。平台会自动为您的智能体配置存储。

namespace 参数控制数据隔离。对于多用户部署，始终设置一个命名空间工厂以按用户或租户隔离数据。

LangSmith Hub 仓库中的持久文件系统存储。:::python

from deepagents import create_deep_agent
from deepagents.backends import ContextHubBackend

agent = create_deep_agent(
    model="google_genai:gemini-3.6-flash",
    backend=ContextHubBackend("my-agent"),
)

from deepagents import create_deep_agent
from deepagents.backends import ContextHubBackend

agent = create_deep_agent(
    model="openai:gpt-5.5",
    backend=ContextHubBackend("my-agent"),
)

from deepagents import create_deep_agent
from deepagents.backends import ContextHubBackend

agent = create_deep_agent(
    model="anthropic:claude-sonnet-5",
    backend=ContextHubBackend("my-agent"),
)

from deepagents import create_deep_agent
from deepagents.backends import ContextHubBackend

agent = create_deep_agent(
    model="openrouter:z-ai/glm-5.2",
    backend=ContextHubBackend("my-agent"),
)

from deepagents import create_deep_agent
from deepagents.backends import ContextHubBackend

agent = create_deep_agent(
    model="fireworks:accounts/fireworks/models/glm-5p2",
    backend=ContextHubBackend("my-agent"),
)

from deepagents import create_deep_agent
from deepagents.backends import ContextHubBackend

agent = create_deep_agent(
    model="baseten:zai-org/GLM-5.2",
    backend=ContextHubBackend("my-agent"),
)

from deepagents import create_deep_agent
from deepagents.backends import ContextHubBackend

agent = create_deep_agent(
    model="ollama:north-mini-code-1.0",
    backend=ContextHubBackend("my-agent"),
)

:::更多详情，请参阅 ContextHubBackend。

一种灵活的后端，您可以在其中指定文件系统中的不同路由，以指向不同的后端。:::python

from deepagents import create_deep_agent
from deepagents.backends import CompositeBackend, StateBackend, StoreBackend
from langgraph.store.memory import InMemoryStore

agent = create_deep_agent(
    model="google_genai:gemini-3.6-flash",
    backend=CompositeBackend(
        default=StateBackend(),
        routes={
            "/memories/": StoreBackend(namespace=lambda _rt: ("memories",)),
        },
    ),
    store=InMemoryStore(),  # Store passed to create_deep_agent, not backend
)

from deepagents import create_deep_agent
from deepagents.backends import CompositeBackend, StateBackend, StoreBackend
from langgraph.store.memory import InMemoryStore

agent = create_deep_agent(
    model="openai:gpt-5.5",
    backend=CompositeBackend(
        default=StateBackend(),
        routes={
            "/memories/": StoreBackend(namespace=lambda _rt: ("memories",)),
        },
    ),
    store=InMemoryStore(),  # Store passed to create_deep_agent, not backend
)

from deepagents import create_deep_agent
from deepagents.backends import CompositeBackend, StateBackend, StoreBackend
from langgraph.store.memory import InMemoryStore

agent = create_deep_agent(
    model="anthropic:claude-sonnet-5",
    backend=CompositeBackend(
        default=StateBackend(),
        routes={
            "/memories/": StoreBackend(namespace=lambda _rt: ("memories",)),
        },
    ),
    store=InMemoryStore(),  # Store passed to create_deep_agent, not backend
)

from deepagents import create_deep_agent
from deepagents.backends import CompositeBackend, StateBackend, StoreBackend
from langgraph.store.memory import InMemoryStore

agent = create_deep_agent(
    model="openrouter:z-ai/glm-5.2",
    backend=CompositeBackend(
        default=StateBackend(),
        routes={
            "/memories/": StoreBackend(namespace=lambda _rt: ("memories",)),
        },
    ),
    store=InMemoryStore(),  # Store passed to create_deep_agent, not backend
)

from deepagents import create_deep_agent
from deepagents.backends import CompositeBackend, StateBackend, StoreBackend
from langgraph.store.memory import InMemoryStore

agent = create_deep_agent(
    model="fireworks:accounts/fireworks/models/glm-5p2",
    backend=CompositeBackend(
        default=StateBackend(),
        routes={
            "/memories/": StoreBackend(namespace=lambda _rt: ("memories",)),
        },
    ),
    store=InMemoryStore(),  # Store passed to create_deep_agent, not backend
)

from deepagents import create_deep_agent
from deepagents.backends import CompositeBackend, StateBackend, StoreBackend
from langgraph.store.memory import InMemoryStore

agent = create_deep_agent(
    model="baseten:zai-org/GLM-5.2",
    backend=CompositeBackend(
        default=StateBackend(),
        routes={
            "/memories/": StoreBackend(namespace=lambda _rt: ("memories",)),
        },
    ),
    store=InMemoryStore(),  # Store passed to create_deep_agent, not backend
)

from deepagents import create_deep_agent
from deepagents.backends import CompositeBackend, StateBackend, StoreBackend
from langgraph.store.memory import InMemoryStore

agent = create_deep_agent(
    model="ollama:north-mini-code-1.0",
    backend=CompositeBackend(
        default=StateBackend(),
        routes={
            "/memories/": StoreBackend(namespace=lambda _rt: ("memories",)),
        },
    ),
    store=InMemoryStore(),  # Store passed to create_deep_agent, not backend
)

::::::js

import {
  createDeepAgent,
  CompositeBackend,
  StateBackend,
  StoreBackend,
} from "deepagents";
import { InMemoryStore } from "@langchain/langgraph";

const store = new InMemoryStore();

const agent = createDeepAgent({
  model: "google:gemini-3.6-flash",
  backend: new CompositeBackend(new StateBackend(), {
    "/memories/": new StoreBackend({
      namespace: () => ["memories"],
    }),
  }),
  store,
});

import {
  createDeepAgent,
  CompositeBackend,
  StateBackend,
  StoreBackend,
} from "deepagents";
import { InMemoryStore } from "@langchain/langgraph";

const store = new InMemoryStore();

const agent = createDeepAgent({
  model: "openai:gpt-5.5",
  backend: new CompositeBackend(new StateBackend(), {
    "/memories/": new StoreBackend({
      namespace: () => ["memories"],
    }),
  }),
  store,
});

import {
  createDeepAgent,
  CompositeBackend,
  StateBackend,
  StoreBackend,
} from "deepagents";
import { InMemoryStore } from "@langchain/langgraph";

const store = new InMemoryStore();

const agent = createDeepAgent({
  model: "anthropic:claude-sonnet-5",
  backend: new CompositeBackend(new StateBackend(), {
    "/memories/": new StoreBackend({
      namespace: () => ["memories"],
    }),
  }),
  store,
});

import {
  createDeepAgent,
  CompositeBackend,
  StateBackend,
  StoreBackend,
} from "deepagents";
import { InMemoryStore } from "@langchain/langgraph";

const store = new InMemoryStore();

const agent = createDeepAgent({
  model: "openrouter:z-ai/glm-5.2",
  backend: new CompositeBackend(new StateBackend(), {
    "/memories/": new StoreBackend({
      namespace: () => ["memories"],
    }),
  }),
  store,
});

import {
  createDeepAgent,
  CompositeBackend,
  StateBackend,
  StoreBackend,
} from "deepagents";
import { InMemoryStore } from "@langchain/langgraph";

const store = new InMemoryStore();

const agent = createDeepAgent({
  model: "fireworks:accounts/fireworks/models/glm-5p2",
  backend: new CompositeBackend(new StateBackend(), {
    "/memories/": new StoreBackend({
      namespace: () => ["memories"],
    }),
  }),
  store,
});

import {
  createDeepAgent,
  CompositeBackend,
  StateBackend,
  StoreBackend,
} from "deepagents";
import { InMemoryStore } from "@langchain/langgraph";

const store = new InMemoryStore();

const agent = createDeepAgent({
  model: "baseten:zai-org/GLM-5.2",
  backend: new CompositeBackend(new StateBackend(), {
    "/memories/": new StoreBackend({
      namespace: () => ["memories"],
    }),
  }),
  store,
});

import {
  createDeepAgent,
  CompositeBackend,
  StateBackend,
  StoreBackend,
} from "deepagents";
import { InMemoryStore } from "@langchain/langgraph";

const store = new InMemoryStore();

const agent = createDeepAgent({
  model: "ollama:north-mini-code-1.0",
  backend: new CompositeBackend(new StateBackend(), {
    "/memories/": new StoreBackend({
      namespace: () => ["memories"],
    }),
  }),
  store,
});

:::

更多信息，请参阅后端。

沙盒

沙盒是特殊的后端，它们在隔离环境中运行智能体代码，拥有自己的文件系统和用于 shell 命令的 execute 工具。当您希望深度智能体在本地机器上不更改任何内容的情况下写入文件、安装依赖项和运行命令时，请使用沙盒后端。您通过在创建深度智能体时将沙盒后端传递给 backend 来配置沙盒： :::python

pip install langsmith

uv add langsmith

from deepagents import create_deep_agent
from deepagents.backends import LangSmithSandbox
from langchain_anthropic import ChatAnthropic
from langsmith.sandbox import SandboxClient

client = SandboxClient()
ls_sandbox = client.create_sandbox()
backend = LangSmithSandbox(sandbox=ls_sandbox)

agent = create_deep_agent(
    model=ChatAnthropic(model="claude-sonnet-4-6"),
    system_prompt="You are a Python coding assistant with sandbox access.",
    backend=backend,
)
try:
    result = agent.invoke(
        {
            "messages": [
                {
                    "role": "user",
                    "content": "Create a small Python package and run pytest",
                }
            ]
        }
    )
finally:
    client.delete_sandbox(ls_sandbox.name)

pip install langchain-daytona

uv add langchain-daytona

from daytona import Daytona
from deepagents import create_deep_agent
from langchain_anthropic import ChatAnthropic
from langchain_daytona import DaytonaSandbox

sandbox = Daytona().create()
backend = DaytonaSandbox(sandbox=sandbox)

agent = create_deep_agent(
    model=ChatAnthropic(model="claude-sonnet-4-6"),
    system_prompt="You are a Python coding assistant with sandbox access.",
    backend=backend,
)

try:
    result = agent.invoke(
        {
            "messages": [
                {
                    "role": "user",
                    "content": "Create a small Python package and run pytest",
                }
            ]
        }
    )
finally:
    sandbox.stop()

pip install langchain-e2b

uv add langchain-e2b

from e2b import Sandbox
from deepagents import create_deep_agent
from langchain_anthropic import ChatAnthropic
from langchain_e2b import E2BSandbox

e2b_sandbox = Sandbox.create()
backend = E2BSandbox(sandbox=e2b_sandbox)

agent = create_deep_agent(
    model=ChatAnthropic(model="claude-sonnet-4-6"),
    system_prompt="You are a Python coding assistant with sandbox access.",
    backend=backend,
)

try:
    result = agent.invoke(
        {
            "messages": [
                {
                    "role": "user",
                    "content": "Create a small Python package and run pytest",
                }
            ]
        }
    )
finally:
    e2b_sandbox.kill()

pip install langchain-modal

uv add langchain-modal

import modal
from deepagents import create_deep_agent
from langchain_anthropic import ChatAnthropic
from langchain_modal import ModalSandbox

app = modal.App.lookup("your-app")
modal_sandbox = modal.Sandbox.create(app=app)
backend = ModalSandbox(sandbox=modal_sandbox)

agent = create_deep_agent(
    model=ChatAnthropic(model="claude-sonnet-4-6"),
    system_prompt="You are a Python coding assistant with sandbox access.",
    backend=backend,
)
try:
    result = agent.invoke(
        {
            "messages": [
                {
                    "role": "user",
                    "content": "Create a small Python package and run pytest",
                }
            ]
        }
    )
finally:
    modal_sandbox.terminate()

pip install langchain-runloop

uv add langchain-runloop

import os

from deepagents import create_deep_agent
from langchain_anthropic import ChatAnthropic
from langchain_runloop import RunloopSandbox
from runloop_api_client import RunloopSDK

client = RunloopSDK(bearer_token=os.environ["RUNLOOP_API_KEY"])

devbox = client.devbox.create()
backend = RunloopSandbox(devbox=devbox)

agent = create_deep_agent(
    model=ChatAnthropic(model="claude-sonnet-4-6"),
    system_prompt="You are a Python coding assistant with sandbox access.",
    backend=backend,
)

try:
    result = agent.invoke(
        {
            "messages": [
                {
                    "role": "user",
                    "content": "Create a small Python package and run pytest",
                }
            ]
        }
    )
finally:
    devbox.shutdown()

pip install langchain-vercel-sandbox

uv add langchain-vercel-sandbox

from deepagents import create_deep_agent
from langchain_anthropic import ChatAnthropic
from langchain_vercel_sandbox import VercelSandbox
from vercel.sandbox import Sandbox

sandbox = Sandbox.create(runtime="python3.13")
backend = VercelSandbox(sandbox=sandbox)

agent = create_deep_agent(
    model=ChatAnthropic(model="claude-sonnet-4-6"),
    system_prompt="You are a Python coding assistant with sandbox access.",
    backend=backend,
)

try:
    result = agent.invoke(
        {
            "messages": [
                {
                    "role": "user",
                    "content": "Create a small Python package and run pytest",
                }
            ]
        }
    )
finally:
    sandbox.stop()

::: :::js

import { createDeepAgent, LangSmithSandbox } from "deepagents";
import { ChatAnthropic } from "@langchain/anthropic";
import { SandboxClient } from "langsmith/sandbox";

const client = new SandboxClient();
const lsSandbox = await client.createSandbox();

try {
  const agent = createDeepAgent({
    model: new ChatAnthropic({ model: "claude-opus-4-8" }),
    systemPrompt: "You are a coding assistant with sandbox access.",
    backend: new LangSmithSandbox({ sandbox: lsSandbox }),
  });

  const result = await agent.invoke({
    messages: [
      {
        role: "user",
        content: "Create a hello world Python script and run it",
      },
    ],
  });
} finally {
  await client.deleteSandbox(lsSandbox.name);
}

::: 更多信息，请参阅沙盒。

人机交互

某些工具操作可能敏感，需要在执行前获得人工批准。您可以配置每个工具的批准： :::python

from langchain.tools import tool
from deepagents import create_deep_agent
from langgraph.checkpoint.memory import MemorySaver


@tool
def remove_file(path: str) -> str:
    """Delete a file from the filesystem."""
    return f"Deleted {path}"


@tool
def fetch_file(path: str) -> str:
    """Read a file from the filesystem."""
    return f"Contents of {path}"


@tool
def notify_email(to: str, subject: str, body: str) -> str:
    """Send an email."""
    return f"Sent email to {to}"


# Checkpointer is REQUIRED for human-in-the-loop
checkpointer = MemorySaver()

agent = create_deep_agent(
    model="google_genai:gemini-3.6-flash",
    tools=[remove_file, fetch_file, notify_email],
    interrupt_on={
        "remove_file": True,  # Default: approve, edit, reject, respond
        "fetch_file": False,  # No interrupts needed
        "notify_email": {"allowed_decisions": ["approve", "reject"]},  # No editing
    },
    checkpointer=checkpointer,  # Required!
)

from langchain.tools import tool
from deepagents import create_deep_agent
from langgraph.checkpoint.memory import MemorySaver


@tool
def remove_file(path: str) -> str:
    """Delete a file from the filesystem."""
    return f"Deleted {path}"


@tool
def fetch_file(path: str) -> str:
    """Read a file from the filesystem."""
    return f"Contents of {path}"


@tool
def notify_email(to: str, subject: str, body: str) -> str:
    """Send an email."""
    return f"Sent email to {to}"


# Checkpointer is REQUIRED for human-in-the-loop
checkpointer = MemorySaver()

agent = create_deep_agent(
    model="openai:gpt-5.5",
    tools=[remove_file, fetch_file, notify_email],
    interrupt_on={
        "remove_file": True,  # Default: approve, edit, reject, respond
        "fetch_file": False,  # No interrupts needed
        "notify_email": {"allowed_decisions": ["approve", "reject"]},  # No editing
    },
    checkpointer=checkpointer,  # Required!
)

from langchain.tools import tool
from deepagents import create_deep_agent
from langgraph.checkpoint.memory import MemorySaver


@tool
def remove_file(path: str) -> str:
    """Delete a file from the filesystem."""
    return f"Deleted {path}"


@tool
def fetch_file(path: str) -> str:
    """Read a file from the filesystem."""
    return f"Contents of {path}"


@tool
def notify_email(to: str, subject: str, body: str) -> str:
    """Send an email."""
    return f"Sent email to {to}"


# Checkpointer is REQUIRED for human-in-the-loop
checkpointer = MemorySaver()

agent = create_deep_agent(
    model="anthropic:claude-sonnet-5",
    tools=[remove_file, fetch_file, notify_email],
    interrupt_on={
        "remove_file": True,  # Default: approve, edit, reject, respond
        "fetch_file": False,  # No interrupts needed
        "notify_email": {"allowed_decisions": ["approve", "reject"]},  # No editing
    },
    checkpointer=checkpointer,  # Required!
)

from langchain.tools import tool
from deepagents import create_deep_agent
from langgraph.checkpoint.memory import MemorySaver


@tool
def remove_file(path: str) -> str:
    """Delete a file from the filesystem."""
    return f"Deleted {path}"


@tool
def fetch_file(path: str) -> str:
    """Read a file from the filesystem."""
    return f"Contents of {path}"


@tool
def notify_email(to: str, subject: str, body: str) -> str:
    """Send an email."""
    return f"Sent email to {to}"


# Checkpointer is REQUIRED for human-in-the-loop
checkpointer = MemorySaver()

agent = create_deep_agent(
    model="openrouter:z-ai/glm-5.2",
    tools=[remove_file, fetch_file, notify_email],
    interrupt_on={
        "remove_file": True,  # Default: approve, edit, reject, respond
        "fetch_file": False,  # No interrupts needed
        "notify_email": {"allowed_decisions": ["approve", "reject"]},  # No editing
    },
    checkpointer=checkpointer,  # Required!
)

from langchain.tools import tool
from deepagents import create_deep_agent
from langgraph.checkpoint.memory import MemorySaver


@tool
def remove_file(path: str) -> str:
    """Delete a file from the filesystem."""
    return f"Deleted {path}"


@tool
def fetch_file(path: str) -> str:
    """Read a file from the filesystem."""
    return f"Contents of {path}"


@tool
def notify_email(to: str, subject: str, body: str) -> str:
    """Send an email."""
    return f"Sent email to {to}"


# Checkpointer is REQUIRED for human-in-the-loop
checkpointer = MemorySaver()

agent = create_deep_agent(
    model="fireworks:accounts/fireworks/models/glm-5p2",
    tools=[remove_file, fetch_file, notify_email],
    interrupt_on={
        "remove_file": True,  # Default: approve, edit, reject, respond
        "fetch_file": False,  # No interrupts needed
        "notify_email": {"allowed_decisions": ["approve", "reject"]},  # No editing
    },
    checkpointer=checkpointer,  # Required!
)

from langchain.tools import tool
from deepagents import create_deep_agent
from langgraph.checkpoint.memory import MemorySaver


@tool
def remove_file(path: str) -> str:
    """Delete a file from the filesystem."""
    return f"Deleted {path}"


@tool
def fetch_file(path: str) -> str:
    """Read a file from the filesystem."""
    return f"Contents of {path}"


@tool
def notify_email(to: str, subject: str, body: str) -> str:
    """Send an email."""
    return f"Sent email to {to}"


# Checkpointer is REQUIRED for human-in-the-loop
checkpointer = MemorySaver()

agent = create_deep_agent(
    model="baseten:zai-org/GLM-5.2",
    tools=[remove_file, fetch_file, notify_email],
    interrupt_on={
        "remove_file": True,  # Default: approve, edit, reject, respond
        "fetch_file": False,  # No interrupts needed
        "notify_email": {"allowed_decisions": ["approve", "reject"]},  # No editing
    },
    checkpointer=checkpointer,  # Required!
)

from langchain.tools import tool
from deepagents import create_deep_agent
from langgraph.checkpoint.memory import MemorySaver


@tool
def remove_file(path: str) -> str:
    """Delete a file from the filesystem."""
    return f"Deleted {path}"


@tool
def fetch_file(path: str) -> str:
    """Read a file from the filesystem."""
    return f"Contents of {path}"


@tool
def notify_email(to: str, subject: str, body: str) -> str:
    """Send an email."""
    return f"Sent email to {to}"


# Checkpointer is REQUIRED for human-in-the-loop
checkpointer = MemorySaver()

agent = create_deep_agent(
    model="ollama:north-mini-code-1.0",
    tools=[remove_file, fetch_file, notify_email],
    interrupt_on={
        "remove_file": True,  # Default: approve, edit, reject, respond
        "fetch_file": False,  # No interrupts needed
        "notify_email": {"allowed_decisions": ["approve", "reject"]},  # No editing
    },
    checkpointer=checkpointer,  # Required!
)

::: :::js

import { tool } from "langchain";
import { createDeepAgent } from "deepagents";
import { MemorySaver } from "@langchain/langgraph";
import { z } from "zod";

const removeFile = tool(
  async ({ path }: { path: string }) => {
    return `Deleted ${path}`;
  },
  {
    name: "remove_file",
    description: "Delete a file from the filesystem.",
    schema: z.object({
      path: z.string(),
    }),
  },
);

const fetchFile = tool(
  async ({ path }: { path: string }) => {
    return `Contents of ${path}`;
  },
  {
    name: "fetch_file",
    description: "Read a file from the filesystem.",
    schema: z.object({
      path: z.string(),
    }),
  },
);

const notifyEmail = tool(
  async ({
    to,
    subject,
    body,
  }: {
    to: string;
    subject: string;
    body: string;
  }) => {
    return `Sent email to ${to}`;
  },
  {
    name: "notify_email",
    description: "Send an email.",
    schema: z.object({
      to: z.string(),
      subject: z.string(),
      body: z.string(),
    }),
  },
);

// Checkpointer is REQUIRED for human-in-the-loop
const checkpointer = new MemorySaver();

const agent = createDeepAgent({
  model: "google:gemini-3.6-flash",
  tools: [removeFile, fetchFile, notifyEmail],
  interruptOn: {
    remove_file: true, // Default: approve, edit, reject, respond
    fetch_file: false, // No interrupts needed
    notify_email: { allowedDecisions: ["approve", "reject"] }, // No editing
  },
  checkpointer, // Required!
});

::: 您可以在工具调用以及工具调用内部配置智能体和子智能体的中断。更多信息，请参阅 Human-in-the-loop。

技能

您可以使用 skills 为您的深度智能体提供新的能力和专业知识。虽然 tools 往往涵盖较低级别的功能，如原生文件系统操作，但技能可以包含完成任务的详细说明、参考资料和其他资源，例如模板。这些文件仅在智能体确定该技能对当前提示有用时才会被加载。这种渐进式披露减少了智能体在启动时需要考虑的 Token 数量和上下文。示例技能，请参阅 Deep Agents example skills。要将技能添加到您的深度智能体，请将它们作为参数传递给 create_deep_agent： :::python

StateBackend
StoreBackend
FilesystemBackend

from urllib.request import urlopen
from deepagents import create_deep_agent
from deepagents.backends import StateBackend
from deepagents.backends.utils import create_file_data
from langgraph.checkpoint.memory import MemorySaver

checkpointer = MemorySaver()
backend = StateBackend()

skill_url = "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/libs/code/examples/skills/langgraph-docs/SKILL.md"
with urlopen(skill_url) as response:
    skill_content = response.read().decode('utf-8')

skills_files = {
    "/skills/langgraph-docs/SKILL.md": create_file_data(skill_content),
}

agent = create_deep_agent(
    model="google_genai:gemini-3.6-flash",
    backend=backend,
    skills=["/skills/"],
    checkpointer=checkpointer,
)

result = agent.invoke(
    {
        "messages": [{"role": "user", "content": "What is langgraph?"}],
        # Seed the default StateBackend's in-state filesystem (virtual paths must start with "/").
        "files": skills_files,
    },
    config={"configurable": {"thread_id": "12345"}},
)

from urllib.request import urlopen
from deepagents import create_deep_agent
from deepagents.backends import StateBackend
from deepagents.backends.utils import create_file_data
from langgraph.checkpoint.memory import MemorySaver

checkpointer = MemorySaver()
backend = StateBackend()

skill_url = "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/libs/code/examples/skills/langgraph-docs/SKILL.md"
with urlopen(skill_url) as response:
    skill_content = response.read().decode('utf-8')

skills_files = {
    "/skills/langgraph-docs/SKILL.md": create_file_data(skill_content),
}

agent = create_deep_agent(
    model="openai:gpt-5.5",
    backend=backend,
    skills=["/skills/"],
    checkpointer=checkpointer,
)

result = agent.invoke(
    {
        "messages": [{"role": "user", "content": "What is langgraph?"}],
        # Seed the default StateBackend's in-state filesystem (virtual paths must start with "/").
        "files": skills_files,
    },
    config={"configurable": {"thread_id": "12345"}},
)

from urllib.request import urlopen
from deepagents import create_deep_agent
from deepagents.backends import StateBackend
from deepagents.backends.utils import create_file_data
from langgraph.checkpoint.memory import MemorySaver

checkpointer = MemorySaver()
backend = StateBackend()

skill_url = "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/libs/code/examples/skills/langgraph-docs/SKILL.md"
with urlopen(skill_url) as response:
    skill_content = response.read().decode('utf-8')

skills_files = {
    "/skills/langgraph-docs/SKILL.md": create_file_data(skill_content),
}

agent = create_deep_agent(
    model="anthropic:claude-sonnet-5",
    backend=backend,
    skills=["/skills/"],
    checkpointer=checkpointer,
)

result = agent.invoke(
    {
        "messages": [{"role": "user", "content": "What is langgraph?"}],
        # Seed the default StateBackend's in-state filesystem (virtual paths must start with "/").
        "files": skills_files,
    },
    config={"configurable": {"thread_id": "12345"}},
)

from urllib.request import urlopen
from deepagents import create_deep_agent
from deepagents.backends import StateBackend
from deepagents.backends.utils import create_file_data
from langgraph.checkpoint.memory import MemorySaver

checkpointer = MemorySaver()
backend = StateBackend()

skill_url = "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/libs/code/examples/skills/langgraph-docs/SKILL.md"
with urlopen(skill_url) as response:
    skill_content = response.read().decode('utf-8')

skills_files = {
    "/skills/langgraph-docs/SKILL.md": create_file_data(skill_content),
}

agent = create_deep_agent(
    model="openrouter:z-ai/glm-5.2",
    backend=backend,
    skills=["/skills/"],
    checkpointer=checkpointer,
)

result = agent.invoke(
    {
        "messages": [{"role": "user", "content": "What is langgraph?"}],
        # Seed the default StateBackend's in-state filesystem (virtual paths must start with "/").
        "files": skills_files,
    },
    config={"configurable": {"thread_id": "12345"}},
)

from urllib.request import urlopen
from deepagents import create_deep_agent
from deepagents.backends import StateBackend
from deepagents.backends.utils import create_file_data
from langgraph.checkpoint.memory import MemorySaver

checkpointer = MemorySaver()
backend = StateBackend()

skill_url = "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/libs/code/examples/skills/langgraph-docs/SKILL.md"
with urlopen(skill_url) as response:
    skill_content = response.read().decode('utf-8')

skills_files = {
    "/skills/langgraph-docs/SKILL.md": create_file_data(skill_content),
}

agent = create_deep_agent(
    model="fireworks:accounts/fireworks/models/glm-5p2",
    backend=backend,
    skills=["/skills/"],
    checkpointer=checkpointer,
)

result = agent.invoke(
    {
        "messages": [{"role": "user", "content": "What is langgraph?"}],
        # Seed the default StateBackend's in-state filesystem (virtual paths must start with "/").
        "files": skills_files,
    },
    config={"configurable": {"thread_id": "12345"}},
)

from urllib.request import urlopen
from deepagents import create_deep_agent
from deepagents.backends import StateBackend
from deepagents.backends.utils import create_file_data
from langgraph.checkpoint.memory import MemorySaver

checkpointer = MemorySaver()
backend = StateBackend()

skill_url = "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/libs/code/examples/skills/langgraph-docs/SKILL.md"
with urlopen(skill_url) as response:
    skill_content = response.read().decode('utf-8')

skills_files = {
    "/skills/langgraph-docs/SKILL.md": create_file_data(skill_content),
}

agent = create_deep_agent(
    model="baseten:zai-org/GLM-5.2",
    backend=backend,
    skills=["/skills/"],
    checkpointer=checkpointer,
)

result = agent.invoke(
    {
        "messages": [{"role": "user", "content": "What is langgraph?"}],
        # Seed the default StateBackend's in-state filesystem (virtual paths must start with "/").
        "files": skills_files,
    },
    config={"configurable": {"thread_id": "12345"}},
)

from urllib.request import urlopen
from deepagents import create_deep_agent
from deepagents.backends import StateBackend
from deepagents.backends.utils import create_file_data
from langgraph.checkpoint.memory import MemorySaver

checkpointer = MemorySaver()
backend = StateBackend()

skill_url = "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/libs/code/examples/skills/langgraph-docs/SKILL.md"
with urlopen(skill_url) as response:
    skill_content = response.read().decode('utf-8')

skills_files = {
    "/skills/langgraph-docs/SKILL.md": create_file_data(skill_content),
}

agent = create_deep_agent(
    model="ollama:north-mini-code-1.0",
    backend=backend,
    skills=["/skills/"],
    checkpointer=checkpointer,
)

result = agent.invoke(
    {
        "messages": [{"role": "user", "content": "What is langgraph?"}],
        # Seed the default StateBackend's in-state filesystem (virtual paths must start with "/").
        "files": skills_files,
    },
    config={"configurable": {"thread_id": "12345"}},
)

from urllib.request import urlopen
from deepagents import create_deep_agent
from deepagents.backends import StoreBackend
from langgraph.store.memory import InMemoryStore

store = InMemoryStore()
backend = StoreBackend(
    namespace=lambda _rt: ("filesystem",),
    store=store,
)

skill_url = "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/libs/code/examples/skills/langgraph-docs/SKILL.md"
with urlopen(skill_url) as response:
    skill_content = response.read().decode('utf-8')

backend.upload_files(
    [("/skills/langgraph-docs/SKILL.md", skill_content.encode("utf-8"))]
)

agent = create_deep_agent(
    model="google_genai:gemini-3.6-flash",
    backend=backend,
    store=store,
    skills=["/skills/"],
)

result = agent.invoke(
    {"messages": [{"role": "user", "content": "What is langgraph?"}]},
    config={"configurable": {"thread_id": "12345"}},
)

from urllib.request import urlopen
from deepagents import create_deep_agent
from deepagents.backends.filesystem import FilesystemBackend
from langgraph.checkpoint.memory import MemorySaver

# Checkpointer is REQUIRED for human-in-the-loop
checkpointer = MemorySaver()

skill_url = "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/libs/code/examples/skills/langgraph-docs/SKILL.md"
with urlopen(skill_url) as response:
    skill_content = response.read().decode('utf-8')

backend = FilesystemBackend(root_dir="/Users/user/{project}", virtual_mode=True)
backend.upload_files(
    [("/skills/langgraph-docs/SKILL.md", skill_content.encode("utf-8"))]
)

agent = create_deep_agent(
    model="google_genai:gemini-3.6-flash",
    backend=backend,
    skills=["/skills/"],
    interrupt_on={
        "write_file": True,
        "read_file": False,
        "edit_file": True,
    },
    checkpointer=checkpointer,  # Required for filesystem operations!
)

result = agent.invoke(
    {"messages": [{"role": "user", "content": "What is langgraph?"}]},
    config={"configurable": {"thread_id": "12345"}},
)

::: :::js

StateBackend
StoreBackend
FilesystemBackend

import { createDeepAgent, StateBackend, type FileData } from "deepagents";
import { MemorySaver } from "@langchain/langgraph";

const checkpointer = new MemorySaver();
const backend = new StateBackend();

function createFileData(content: string): FileData {
  const now = new Date().toISOString();
  return {
    content: content.split("\n"),
    created_at: now,
    modified_at: now,
  };
}

const skillsFiles: Record<string, FileData> = {};
const skillUrl =
  "https://raw.githubusercontent.com/langchain-ai/deepagentsjs/refs/heads/main/examples/skills/langgraph-docs/SKILL.md";
const response = await fetch(skillUrl);
const skillContent = await response.text();

skillsFiles["/skills/langgraph-docs/SKILL.md"] = createFileData(skillContent);

const agent = await createDeepAgent({
  model: "anthropic:claude-sonnet-4-6",
  backend,
  checkpointer, // Required !
  // IMPORTANT: deepagents skill source paths are virtual (POSIX) paths relative to the backend root.
  skills: ["/skills/"],
});

const config = { configurable: { thread_id: `thread-${Date.now()}` } };
const result = await agent.invoke(
  {
    messages: [{ role: "user", content: "what is langraph?" }],
    files: skillsFiles,
  },
  config,
);

View example trace

为此示例打开一个公开的 LangSmith 运行。

import { createDeepAgent, StoreBackend } from "deepagents";
import { InMemoryStore, MemorySaver } from "@langchain/langgraph";

const checkpointer = new MemorySaver();
const store = new InMemoryStore();
const backend = new StoreBackend({
  namespace: () => ["filesystem"],
  store,
});

const skillUrl =
  "https://raw.githubusercontent.com/langchain-ai/deepagentsjs/refs/heads/main/examples/skills/langgraph-docs/SKILL.md";

const response = await fetch(skillUrl);
const skillContent = await response.text();

await backend.uploadFiles([
  ["/skills/langgraph-docs/SKILL.md", new TextEncoder().encode(skillContent)],
]);

const agent = await createDeepAgent({
  model: "anthropic:claude-sonnet-4-6",
  backend,
  store,
  checkpointer,
  // IMPORTANT: deepagents skill source paths are virtual (POSIX) paths relative to the backend root.
  skills: ["/skills/"],
});

const config = {
  recursionLimit: 50,
  configurable: { thread_id: `thread-${Date.now()}` },
};
const result = await agent.invoke(
  { messages: [{ role: "user", content: "what is langraph?" }] },
  config,
);

View example trace

为此示例打开一个公开的 LangSmith 运行。

import { createDeepAgent, FilesystemBackend } from "deepagents";
import { MemorySaver } from "@langchain/langgraph";

const checkpointer = new MemorySaver();

const skillUrl =
  "https://raw.githubusercontent.com/langchain-ai/deepagentsjs/refs/heads/main/examples/skills/langgraph-docs/SKILL.md";
const response = await fetch(skillUrl);
const skillContent = await response.text();

let backend = new FilesystemBackend({
  rootDir: process.cwd(),
  virtualMode: true,
});
await backend.uploadFiles([
  ["/skills/langgraph-docs/SKILL.md", new TextEncoder().encode(skillContent)],
]);

const agent = await createDeepAgent({
  model: "anthropic:claude-sonnet-4-6",
  backend,
  // IMPORTANT: deepagents skill source paths are virtual (POSIX) paths relative to the backend root.
  skills: ["/skills/"],
  interruptOn: {
    read_file: true,
    write_file: true,
    delete_file: true,
  },
  checkpointer, // Required for filesystem operations!
});

const config = { configurable: { thread_id: `thread-${Date.now()}` } };
const result = await agent.invoke(
  { messages: [{ role: "user", content: "what is langraph?" }] },
  config,
);

View example trace

为此示例打开一个公开的 LangSmith 运行。

:::

记忆

使用 AGENTS.md 文件为您的深度智能体提供额外上下文。

要生成编码智能体通过 AGENTS.md 发现的仓库维基，请参阅 OpenWiki。

在创建您的深度智能体时，您可以将一个或多个文件路径传递给 memory 参数： :::python

StateBackend
StoreBackend
FilesystemBackend

from urllib.request import urlopen

from deepagents import create_deep_agent
from deepagents.backends.utils import create_file_data
from langgraph.checkpoint.memory import MemorySaver

with urlopen(
    "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md"
) as response:
    agents_md = response.read().decode("utf-8")
checkpointer = MemorySaver()

agent = create_deep_agent(
    model="google_genai:gemini-3.6-flash",
    memory=[
        "/AGENTS.md"
    ],
    checkpointer=checkpointer,
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "Please tell me what's in your memory files.",
            }
        ],
        # Seed the default StateBackend's in-state filesystem (virtual paths must start with "/").
        "files": {"/AGENTS.md": create_file_data(agents_md)},
    },
    config={"configurable": {"thread_id": "123456"}},
)

from urllib.request import urlopen

from deepagents import create_deep_agent
from deepagents.backends.utils import create_file_data
from langgraph.checkpoint.memory import MemorySaver

with urlopen(
    "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md"
) as response:
    agents_md = response.read().decode("utf-8")
checkpointer = MemorySaver()

agent = create_deep_agent(
    model="openai:gpt-5.5",
    memory=[
        "/AGENTS.md"
    ],
    checkpointer=checkpointer,
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "Please tell me what's in your memory files.",
            }
        ],
        # Seed the default StateBackend's in-state filesystem (virtual paths must start with "/").
        "files": {"/AGENTS.md": create_file_data(agents_md)},
    },
    config={"configurable": {"thread_id": "123456"}},
)

from urllib.request import urlopen

from deepagents import create_deep_agent
from deepagents.backends.utils import create_file_data
from langgraph.checkpoint.memory import MemorySaver

with urlopen(
    "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md"
) as response:
    agents_md = response.read().decode("utf-8")
checkpointer = MemorySaver()

agent = create_deep_agent(
    model="anthropic:claude-sonnet-5",
    memory=[
        "/AGENTS.md"
    ],
    checkpointer=checkpointer,
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "Please tell me what's in your memory files.",
            }
        ],
        # Seed the default StateBackend's in-state filesystem (virtual paths must start with "/").
        "files": {"/AGENTS.md": create_file_data(agents_md)},
    },
    config={"configurable": {"thread_id": "123456"}},
)

from urllib.request import urlopen

from deepagents import create_deep_agent
from deepagents.backends.utils import create_file_data
from langgraph.checkpoint.memory import MemorySaver

with urlopen(
    "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md"
) as response:
    agents_md = response.read().decode("utf-8")
checkpointer = MemorySaver()

agent = create_deep_agent(
    model="openrouter:z-ai/glm-5.2",
    memory=[
        "/AGENTS.md"
    ],
    checkpointer=checkpointer,
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "Please tell me what's in your memory files.",
            }
        ],
        # Seed the default StateBackend's in-state filesystem (virtual paths must start with "/").
        "files": {"/AGENTS.md": create_file_data(agents_md)},
    },
    config={"configurable": {"thread_id": "123456"}},
)

from urllib.request import urlopen

from deepagents import create_deep_agent
from deepagents.backends.utils import create_file_data
from langgraph.checkpoint.memory import MemorySaver

with urlopen(
    "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md"
) as response:
    agents_md = response.read().decode("utf-8")
checkpointer = MemorySaver()

agent = create_deep_agent(
    model="fireworks:accounts/fireworks/models/glm-5p2",
    memory=[
        "/AGENTS.md"
    ],
    checkpointer=checkpointer,
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "Please tell me what's in your memory files.",
            }
        ],
        # Seed the default StateBackend's in-state filesystem (virtual paths must start with "/").
        "files": {"/AGENTS.md": create_file_data(agents_md)},
    },
    config={"configurable": {"thread_id": "123456"}},
)

from urllib.request import urlopen

from deepagents import create_deep_agent
from deepagents.backends.utils import create_file_data
from langgraph.checkpoint.memory import MemorySaver

with urlopen(
    "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md"
) as response:
    agents_md = response.read().decode("utf-8")
checkpointer = MemorySaver()

agent = create_deep_agent(
    model="baseten:zai-org/GLM-5.2",
    memory=[
        "/AGENTS.md"
    ],
    checkpointer=checkpointer,
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "Please tell me what's in your memory files.",
            }
        ],
        # Seed the default StateBackend's in-state filesystem (virtual paths must start with "/").
        "files": {"/AGENTS.md": create_file_data(agents_md)},
    },
    config={"configurable": {"thread_id": "123456"}},
)

from urllib.request import urlopen

from deepagents import create_deep_agent
from deepagents.backends.utils import create_file_data
from langgraph.checkpoint.memory import MemorySaver

with urlopen(
    "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md"
) as response:
    agents_md = response.read().decode("utf-8")
checkpointer = MemorySaver()

agent = create_deep_agent(
    model="ollama:north-mini-code-1.0",
    memory=[
        "/AGENTS.md"
    ],
    checkpointer=checkpointer,
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "Please tell me what's in your memory files.",
            }
        ],
        # Seed the default StateBackend's in-state filesystem (virtual paths must start with "/").
        "files": {"/AGENTS.md": create_file_data(agents_md)},
    },
    config={"configurable": {"thread_id": "123456"}},
)

from urllib.request import urlopen

from deepagents import create_deep_agent
from deepagents.backends import StoreBackend
from deepagents.backends.utils import create_file_data
from langgraph.store.memory import InMemoryStore

with urlopen(
    "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md"
) as response:
    agents_md = response.read().decode("utf-8")

# Create the store and add the file to it
store = InMemoryStore()
file_data = create_file_data(agents_md)
store.put(
    namespace=("filesystem",),
    key="/AGENTS.md",
    value=file_data,
)

agent = create_deep_agent(
    model="google_genai:gemini-3.6-flash",
    backend=StoreBackend(namespace=lambda _rt: ("filesystem",)),
    store=store,
    memory=["/AGENTS.md"],
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "Please tell me what's in your memory files.",
            }
        ],
        "files": {"/AGENTS.md": create_file_data(agents_md)},
    },
    config={"configurable": {"thread_id": "12345"}},
)

from urllib.request import urlopen

from deepagents import create_deep_agent
from deepagents.backends import StoreBackend
from deepagents.backends.utils import create_file_data
from langgraph.store.memory import InMemoryStore

with urlopen(
    "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md"
) as response:
    agents_md = response.read().decode("utf-8")

# Create the store and add the file to it
store = InMemoryStore()
file_data = create_file_data(agents_md)
store.put(
    namespace=("filesystem",),
    key="/AGENTS.md",
    value=file_data,
)

agent = create_deep_agent(
    model="openai:gpt-5.5",
    backend=StoreBackend(namespace=lambda _rt: ("filesystem",)),
    store=store,
    memory=["/AGENTS.md"],
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "Please tell me what's in your memory files.",
            }
        ],
        "files": {"/AGENTS.md": create_file_data(agents_md)},
    },
    config={"configurable": {"thread_id": "12345"}},
)

from urllib.request import urlopen

from deepagents import create_deep_agent
from deepagents.backends import StoreBackend
from deepagents.backends.utils import create_file_data
from langgraph.store.memory import InMemoryStore

with urlopen(
    "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md"
) as response:
    agents_md = response.read().decode("utf-8")

# Create the store and add the file to it
store = InMemoryStore()
file_data = create_file_data(agents_md)
store.put(
    namespace=("filesystem",),
    key="/AGENTS.md",
    value=file_data,
)

agent = create_deep_agent(
    model="anthropic:claude-sonnet-5",
    backend=StoreBackend(namespace=lambda _rt: ("filesystem",)),
    store=store,
    memory=["/AGENTS.md"],
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "Please tell me what's in your memory files.",
            }
        ],
        "files": {"/AGENTS.md": create_file_data(agents_md)},
    },
    config={"configurable": {"thread_id": "12345"}},
)

from urllib.request import urlopen

from deepagents import create_deep_agent
from deepagents.backends import StoreBackend
from deepagents.backends.utils import create_file_data
from langgraph.store.memory import InMemoryStore

with urlopen(
    "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md"
) as response:
    agents_md = response.read().decode("utf-8")

# Create the store and add the file to it
store = InMemoryStore()
file_data = create_file_data(agents_md)
store.put(
    namespace=("filesystem",),
    key="/AGENTS.md",
    value=file_data,
)

agent = create_deep_agent(
    model="openrouter:z-ai/glm-5.2",
    backend=StoreBackend(namespace=lambda _rt: ("filesystem",)),
    store=store,
    memory=["/AGENTS.md"],
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "Please tell me what's in your memory files.",
            }
        ],
        "files": {"/AGENTS.md": create_file_data(agents_md)},
    },
    config={"configurable": {"thread_id": "12345"}},
)

from urllib.request import urlopen

from deepagents import create_deep_agent
from deepagents.backends import StoreBackend
from deepagents.backends.utils import create_file_data
from langgraph.store.memory import InMemoryStore

with urlopen(
    "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md"
) as response:
    agents_md = response.read().decode("utf-8")

# Create the store and add the file to it
store = InMemoryStore()
file_data = create_file_data(agents_md)
store.put(
    namespace=("filesystem",),
    key="/AGENTS.md",
    value=file_data,
)

agent = create_deep_agent(
    model="fireworks:accounts/fireworks/models/glm-5p2",
    backend=StoreBackend(namespace=lambda _rt: ("filesystem",)),
    store=store,
    memory=["/AGENTS.md"],
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "Please tell me what's in your memory files.",
            }
        ],
        "files": {"/AGENTS.md": create_file_data(agents_md)},
    },
    config={"configurable": {"thread_id": "12345"}},
)

from urllib.request import urlopen

from deepagents import create_deep_agent
from deepagents.backends import StoreBackend
from deepagents.backends.utils import create_file_data
from langgraph.store.memory import InMemoryStore

with urlopen(
    "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md"
) as response:
    agents_md = response.read().decode("utf-8")

# Create the store and add the file to it
store = InMemoryStore()
file_data = create_file_data(agents_md)
store.put(
    namespace=("filesystem",),
    key="/AGENTS.md",
    value=file_data,
)

agent = create_deep_agent(
    model="baseten:zai-org/GLM-5.2",
    backend=StoreBackend(namespace=lambda _rt: ("filesystem",)),
    store=store,
    memory=["/AGENTS.md"],
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "Please tell me what's in your memory files.",
            }
        ],
        "files": {"/AGENTS.md": create_file_data(agents_md)},
    },
    config={"configurable": {"thread_id": "12345"}},
)

from urllib.request import urlopen

from deepagents import create_deep_agent
from deepagents.backends import StoreBackend
from deepagents.backends.utils import create_file_data
from langgraph.store.memory import InMemoryStore

with urlopen(
    "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md"
) as response:
    agents_md = response.read().decode("utf-8")

# Create the store and add the file to it
store = InMemoryStore()
file_data = create_file_data(agents_md)
store.put(
    namespace=("filesystem",),
    key="/AGENTS.md",
    value=file_data,
)

agent = create_deep_agent(
    model="ollama:north-mini-code-1.0",
    backend=StoreBackend(namespace=lambda _rt: ("filesystem",)),
    store=store,
    memory=["/AGENTS.md"],
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "Please tell me what's in your memory files.",
            }
        ],
        "files": {"/AGENTS.md": create_file_data(agents_md)},
    },
    config={"configurable": {"thread_id": "12345"}},
)

from deepagents import create_deep_agent
from deepagents.backends import FilesystemBackend
from langgraph.checkpoint.memory import MemorySaver

# Checkpointer is REQUIRED for human-in-the-loop
checkpointer = MemorySaver()

agent = create_deep_agent(
    model="google_genai:gemini-3.6-flash",
    backend=FilesystemBackend(root_dir="/Users/user/{project}"),
    memory=[
        "./AGENTS.md"
    ],
    interrupt_on={
        "write_file": True,  # Default: approve, edit, reject
        "read_file": False,  # No interrupts needed
        "edit_file": True,   # Default: approve, edit, reject
    },
    checkpointer=checkpointer,  # Required!
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "Please tell me what's in your memory files.",
            }
        ],
    },
    config={"configurable": {"thread_id": "12345"}},
)

from deepagents import create_deep_agent
from deepagents.backends import FilesystemBackend
from langgraph.checkpoint.memory import MemorySaver

# Checkpointer is REQUIRED for human-in-the-loop
checkpointer = MemorySaver()

agent = create_deep_agent(
    model="openai:gpt-5.5",
    backend=FilesystemBackend(root_dir="/Users/user/{project}"),
    memory=[
        "./AGENTS.md"
    ],
    interrupt_on={
        "write_file": True,  # Default: approve, edit, reject
        "read_file": False,  # No interrupts needed
        "edit_file": True,   # Default: approve, edit, reject
    },
    checkpointer=checkpointer,  # Required!
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "Please tell me what's in your memory files.",
            }
        ],
    },
    config={"configurable": {"thread_id": "12345"}},
)

from deepagents import create_deep_agent
from deepagents.backends import FilesystemBackend
from langgraph.checkpoint.memory import MemorySaver

# Checkpointer is REQUIRED for human-in-the-loop
checkpointer = MemorySaver()

agent = create_deep_agent(
    model="anthropic:claude-sonnet-5",
    backend=FilesystemBackend(root_dir="/Users/user/{project}"),
    memory=[
        "./AGENTS.md"
    ],
    interrupt_on={
        "write_file": True,  # Default: approve, edit, reject
        "read_file": False,  # No interrupts needed
        "edit_file": True,   # Default: approve, edit, reject
    },
    checkpointer=checkpointer,  # Required!
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "Please tell me what's in your memory files.",
            }
        ],
    },
    config={"configurable": {"thread_id": "12345"}},
)

from deepagents import create_deep_agent
from deepagents.backends import FilesystemBackend
from langgraph.checkpoint.memory import MemorySaver

# Checkpointer is REQUIRED for human-in-the-loop
checkpointer = MemorySaver()

agent = create_deep_agent(
    model="openrouter:z-ai/glm-5.2",
    backend=FilesystemBackend(root_dir="/Users/user/{project}"),
    memory=[
        "./AGENTS.md"
    ],
    interrupt_on={
        "write_file": True,  # Default: approve, edit, reject
        "read_file": False,  # No interrupts needed
        "edit_file": True,   # Default: approve, edit, reject
    },
    checkpointer=checkpointer,  # Required!
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "Please tell me what's in your memory files.",
            }
        ],
    },
    config={"configurable": {"thread_id": "12345"}},
)

from deepagents import create_deep_agent
from deepagents.backends import FilesystemBackend
from langgraph.checkpoint.memory import MemorySaver

# Checkpointer is REQUIRED for human-in-the-loop
checkpointer = MemorySaver()

agent = create_deep_agent(
    model="fireworks:accounts/fireworks/models/glm-5p2",
    backend=FilesystemBackend(root_dir="/Users/user/{project}"),
    memory=[
        "./AGENTS.md"
    ],
    interrupt_on={
        "write_file": True,  # Default: approve, edit, reject
        "read_file": False,  # No interrupts needed
        "edit_file": True,   # Default: approve, edit, reject
    },
    checkpointer=checkpointer,  # Required!
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "Please tell me what's in your memory files.",
            }
        ],
    },
    config={"configurable": {"thread_id": "12345"}},
)

from deepagents import create_deep_agent
from deepagents.backends import FilesystemBackend
from langgraph.checkpoint.memory import MemorySaver

# Checkpointer is REQUIRED for human-in-the-loop
checkpointer = MemorySaver()

agent = create_deep_agent(
    model="baseten:zai-org/GLM-5.2",
    backend=FilesystemBackend(root_dir="/Users/user/{project}"),
    memory=[
        "./AGENTS.md"
    ],
    interrupt_on={
        "write_file": True,  # Default: approve, edit, reject
        "read_file": False,  # No interrupts needed
        "edit_file": True,   # Default: approve, edit, reject
    },
    checkpointer=checkpointer,  # Required!
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "Please tell me what's in your memory files.",
            }
        ],
    },
    config={"configurable": {"thread_id": "12345"}},
)

from deepagents import create_deep_agent
from deepagents.backends import FilesystemBackend
from langgraph.checkpoint.memory import MemorySaver

# Checkpointer is REQUIRED for human-in-the-loop
checkpointer = MemorySaver()

agent = create_deep_agent(
    model="ollama:north-mini-code-1.0",
    backend=FilesystemBackend(root_dir="/Users/user/{project}"),
    memory=[
        "./AGENTS.md"
    ],
    interrupt_on={
        "write_file": True,  # Default: approve, edit, reject
        "read_file": False,  # No interrupts needed
        "edit_file": True,   # Default: approve, edit, reject
    },
    checkpointer=checkpointer,  # Required!
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "Please tell me what's in your memory files.",
            }
        ],
    },
    config={"configurable": {"thread_id": "12345"}},
)

::: :::js

StateBackend
StoreBackend
Filesystem

import { createDeepAgent, type FileData } from "deepagents";
import { MemorySaver } from "@langchain/langgraph";

const AGENTS_MD_URL =
  "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md";

async function fetchText(url: string): Promise<string> {
  const res = await fetch(url);
  if (!res.ok) {
    throw new Error(`Failed to fetch ${url}: ${res.status} ${res.statusText}`);
  }
  return await res.text();
}

const agentsMd = await fetchText(AGENTS_MD_URL);
const checkpointer = new MemorySaver();

function createFileData(content: string): FileData {
  const now = new Date().toISOString();
  return {
    content,
    mimeType: "text/plain",
    created_at: now,
    modified_at: now,
  };
}

const agent = await createDeepAgent({
  model: "google:gemini-3.6-flash",
  memory: ["/AGENTS.md"],
  checkpointer: checkpointer,
});

const result = await agent.invoke(
  {
    messages: [
      {
        role: "user",
        content: "Please tell me what's in your memory files.",
      },
    ],
    // Seed the default StateBackend's in-state filesystem (virtual paths must start with "/").
    files: { "/AGENTS.md": createFileData(agentsMd) },
  },
  { configurable: { thread_id: "12345" } },
);

import { createDeepAgent, type FileData } from "deepagents";
import { MemorySaver } from "@langchain/langgraph";

const AGENTS_MD_URL =
  "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md";

async function fetchText(url: string): Promise<string> {
  const res = await fetch(url);
  if (!res.ok) {
    throw new Error(`Failed to fetch ${url}: ${res.status} ${res.statusText}`);
  }
  return await res.text();
}

const agentsMd = await fetchText(AGENTS_MD_URL);
const checkpointer = new MemorySaver();

function createFileData(content: string): FileData {
  const now = new Date().toISOString();
  return {
    content,
    mimeType: "text/plain",
    created_at: now,
    modified_at: now,
  };
}

const agent = await createDeepAgent({
  model: "openai:gpt-5.5",
  memory: ["/AGENTS.md"],
  checkpointer: checkpointer,
});

const result = await agent.invoke(
  {
    messages: [
      {
        role: "user",
        content: "Please tell me what's in your memory files.",
      },
    ],
    // Seed the default StateBackend's in-state filesystem (virtual paths must start with "/").
    files: { "/AGENTS.md": createFileData(agentsMd) },
  },
  { configurable: { thread_id: "12345" } },
);

import { createDeepAgent, type FileData } from "deepagents";
import { MemorySaver } from "@langchain/langgraph";

const AGENTS_MD_URL =
  "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md";

async function fetchText(url: string): Promise<string> {
  const res = await fetch(url);
  if (!res.ok) {
    throw new Error(`Failed to fetch ${url}: ${res.status} ${res.statusText}`);
  }
  return await res.text();
}

const agentsMd = await fetchText(AGENTS_MD_URL);
const checkpointer = new MemorySaver();

function createFileData(content: string): FileData {
  const now = new Date().toISOString();
  return {
    content,
    mimeType: "text/plain",
    created_at: now,
    modified_at: now,
  };
}

const agent = await createDeepAgent({
  model: "anthropic:claude-sonnet-5",
  memory: ["/AGENTS.md"],
  checkpointer: checkpointer,
});

const result = await agent.invoke(
  {
    messages: [
      {
        role: "user",
        content: "Please tell me what's in your memory files.",
      },
    ],
    // Seed the default StateBackend's in-state filesystem (virtual paths must start with "/").
    files: { "/AGENTS.md": createFileData(agentsMd) },
  },
  { configurable: { thread_id: "12345" } },
);

import { createDeepAgent, type FileData } from "deepagents";
import { MemorySaver } from "@langchain/langgraph";

const AGENTS_MD_URL =
  "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md";

async function fetchText(url: string): Promise<string> {
  const res = await fetch(url);
  if (!res.ok) {
    throw new Error(`Failed to fetch ${url}: ${res.status} ${res.statusText}`);
  }
  return await res.text();
}

const agentsMd = await fetchText(AGENTS_MD_URL);
const checkpointer = new MemorySaver();

function createFileData(content: string): FileData {
  const now = new Date().toISOString();
  return {
    content,
    mimeType: "text/plain",
    created_at: now,
    modified_at: now,
  };
}

const agent = await createDeepAgent({
  model: "openrouter:z-ai/glm-5.2",
  memory: ["/AGENTS.md"],
  checkpointer: checkpointer,
});

const result = await agent.invoke(
  {
    messages: [
      {
        role: "user",
        content: "Please tell me what's in your memory files.",
      },
    ],
    // Seed the default StateBackend's in-state filesystem (virtual paths must start with "/").
    files: { "/AGENTS.md": createFileData(agentsMd) },
  },
  { configurable: { thread_id: "12345" } },
);

import { createDeepAgent, type FileData } from "deepagents";
import { MemorySaver } from "@langchain/langgraph";

const AGENTS_MD_URL =
  "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md";

async function fetchText(url: string): Promise<string> {
  const res = await fetch(url);
  if (!res.ok) {
    throw new Error(`Failed to fetch ${url}: ${res.status} ${res.statusText}`);
  }
  return await res.text();
}

const agentsMd = await fetchText(AGENTS_MD_URL);
const checkpointer = new MemorySaver();

function createFileData(content: string): FileData {
  const now = new Date().toISOString();
  return {
    content,
    mimeType: "text/plain",
    created_at: now,
    modified_at: now,
  };
}

const agent = await createDeepAgent({
  model: "fireworks:accounts/fireworks/models/glm-5p2",
  memory: ["/AGENTS.md"],
  checkpointer: checkpointer,
});

const result = await agent.invoke(
  {
    messages: [
      {
        role: "user",
        content: "Please tell me what's in your memory files.",
      },
    ],
    // Seed the default StateBackend's in-state filesystem (virtual paths must start with "/").
    files: { "/AGENTS.md": createFileData(agentsMd) },
  },
  { configurable: { thread_id: "12345" } },
);

import { createDeepAgent, type FileData } from "deepagents";
import { MemorySaver } from "@langchain/langgraph";

const AGENTS_MD_URL =
  "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md";

async function fetchText(url: string): Promise<string> {
  const res = await fetch(url);
  if (!res.ok) {
    throw new Error(`Failed to fetch ${url}: ${res.status} ${res.statusText}`);
  }
  return await res.text();
}

const agentsMd = await fetchText(AGENTS_MD_URL);
const checkpointer = new MemorySaver();

function createFileData(content: string): FileData {
  const now = new Date().toISOString();
  return {
    content,
    mimeType: "text/plain",
    created_at: now,
    modified_at: now,
  };
}

const agent = await createDeepAgent({
  model: "baseten:zai-org/GLM-5.2",
  memory: ["/AGENTS.md"],
  checkpointer: checkpointer,
});

const result = await agent.invoke(
  {
    messages: [
      {
        role: "user",
        content: "Please tell me what's in your memory files.",
      },
    ],
    // Seed the default StateBackend's in-state filesystem (virtual paths must start with "/").
    files: { "/AGENTS.md": createFileData(agentsMd) },
  },
  { configurable: { thread_id: "12345" } },
);

import { createDeepAgent, type FileData } from "deepagents";
import { MemorySaver } from "@langchain/langgraph";

const AGENTS_MD_URL =
  "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md";

async function fetchText(url: string): Promise<string> {
  const res = await fetch(url);
  if (!res.ok) {
    throw new Error(`Failed to fetch ${url}: ${res.status} ${res.statusText}`);
  }
  return await res.text();
}

const agentsMd = await fetchText(AGENTS_MD_URL);
const checkpointer = new MemorySaver();

function createFileData(content: string): FileData {
  const now = new Date().toISOString();
  return {
    content,
    mimeType: "text/plain",
    created_at: now,
    modified_at: now,
  };
}

const agent = await createDeepAgent({
  model: "ollama:north-mini-code-1.0",
  memory: ["/AGENTS.md"],
  checkpointer: checkpointer,
});

const result = await agent.invoke(
  {
    messages: [
      {
        role: "user",
        content: "Please tell me what's in your memory files.",
      },
    ],
    // Seed the default StateBackend's in-state filesystem (virtual paths must start with "/").
    files: { "/AGENTS.md": createFileData(agentsMd) },
  },
  { configurable: { thread_id: "12345" } },
);

View example trace

为此示例打开一个公开的 LangSmith 运行。

import { createDeepAgent, StoreBackend, type FileData } from "deepagents";
import { InMemoryStore, MemorySaver } from "@langchain/langgraph";

const AGENTS_MD_URL =
  "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md";

async function fetchText(url: string): Promise<string> {
  const res = await fetch(url);
  if (!res.ok) {
    throw new Error(`Failed to fetch ${url}: ${res.status} ${res.statusText}`);
  }
  return await res.text();
}

const agentsMd = await fetchText(AGENTS_MD_URL);

function createFileData(content: string): FileData {
  const now = new Date().toISOString();
  return {
    content,
    mimeType: "text/plain",
    created_at: now,
    modified_at: now,
  };
}

const store = new InMemoryStore();
const fileData = createFileData(agentsMd);
await store.put(["filesystem"], "/AGENTS.md", fileData);

const checkpointer = new MemorySaver();

const agent = await createDeepAgent({
  model: "google:gemini-3.6-flash",
  backend: new StoreBackend({
    namespace: () => ["filesystem"],
  }),
  store: store,
  checkpointer: checkpointer,
  memory: ["/AGENTS.md"],
});

const result = await agent.invoke(
  {
    messages: [
      {
        role: "user",
        content: "Please tell me what's in your memory files.",
      },
    ],
  },
  { configurable: { thread_id: "12345" } },
);

import { createDeepAgent, StoreBackend, type FileData } from "deepagents";
import { InMemoryStore, MemorySaver } from "@langchain/langgraph";

const AGENTS_MD_URL =
  "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md";

async function fetchText(url: string): Promise<string> {
  const res = await fetch(url);
  if (!res.ok) {
    throw new Error(`Failed to fetch ${url}: ${res.status} ${res.statusText}`);
  }
  return await res.text();
}

const agentsMd = await fetchText(AGENTS_MD_URL);

function createFileData(content: string): FileData {
  const now = new Date().toISOString();
  return {
    content,
    mimeType: "text/plain",
    created_at: now,
    modified_at: now,
  };
}

const store = new InMemoryStore();
const fileData = createFileData(agentsMd);
await store.put(["filesystem"], "/AGENTS.md", fileData);

const checkpointer = new MemorySaver();

const agent = await createDeepAgent({
  model: "openai:gpt-5.5",
  backend: new StoreBackend({
    namespace: () => ["filesystem"],
  }),
  store: store,
  checkpointer: checkpointer,
  memory: ["/AGENTS.md"],
});

const result = await agent.invoke(
  {
    messages: [
      {
        role: "user",
        content: "Please tell me what's in your memory files.",
      },
    ],
  },
  { configurable: { thread_id: "12345" } },
);

import { createDeepAgent, StoreBackend, type FileData } from "deepagents";
import { InMemoryStore, MemorySaver } from "@langchain/langgraph";

const AGENTS_MD_URL =
  "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md";

async function fetchText(url: string): Promise<string> {
  const res = await fetch(url);
  if (!res.ok) {
    throw new Error(`Failed to fetch ${url}: ${res.status} ${res.statusText}`);
  }
  return await res.text();
}

const agentsMd = await fetchText(AGENTS_MD_URL);

function createFileData(content: string): FileData {
  const now = new Date().toISOString();
  return {
    content,
    mimeType: "text/plain",
    created_at: now,
    modified_at: now,
  };
}

const store = new InMemoryStore();
const fileData = createFileData(agentsMd);
await store.put(["filesystem"], "/AGENTS.md", fileData);

const checkpointer = new MemorySaver();

const agent = await createDeepAgent({
  model: "anthropic:claude-sonnet-5",
  backend: new StoreBackend({
    namespace: () => ["filesystem"],
  }),
  store: store,
  checkpointer: checkpointer,
  memory: ["/AGENTS.md"],
});

const result = await agent.invoke(
  {
    messages: [
      {
        role: "user",
        content: "Please tell me what's in your memory files.",
      },
    ],
  },
  { configurable: { thread_id: "12345" } },
);

import { createDeepAgent, StoreBackend, type FileData } from "deepagents";
import { InMemoryStore, MemorySaver } from "@langchain/langgraph";

const AGENTS_MD_URL =
  "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md";

async function fetchText(url: string): Promise<string> {
  const res = await fetch(url);
  if (!res.ok) {
    throw new Error(`Failed to fetch ${url}: ${res.status} ${res.statusText}`);
  }
  return await res.text();
}

const agentsMd = await fetchText(AGENTS_MD_URL);

function createFileData(content: string): FileData {
  const now = new Date().toISOString();
  return {
    content,
    mimeType: "text/plain",
    created_at: now,
    modified_at: now,
  };
}

const store = new InMemoryStore();
const fileData = createFileData(agentsMd);
await store.put(["filesystem"], "/AGENTS.md", fileData);

const checkpointer = new MemorySaver();

const agent = await createDeepAgent({
  model: "openrouter:z-ai/glm-5.2",
  backend: new StoreBackend({
    namespace: () => ["filesystem"],
  }),
  store: store,
  checkpointer: checkpointer,
  memory: ["/AGENTS.md"],
});

const result = await agent.invoke(
  {
    messages: [
      {
        role: "user",
        content: "Please tell me what's in your memory files.",
      },
    ],
  },
  { configurable: { thread_id: "12345" } },
);

import { createDeepAgent, StoreBackend, type FileData } from "deepagents";
import { InMemoryStore, MemorySaver } from "@langchain/langgraph";

const AGENTS_MD_URL =
  "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md";

async function fetchText(url: string): Promise<string> {
  const res = await fetch(url);
  if (!res.ok) {
    throw new Error(`Failed to fetch ${url}: ${res.status} ${res.statusText}`);
  }
  return await res.text();
}

const agentsMd = await fetchText(AGENTS_MD_URL);

function createFileData(content: string): FileData {
  const now = new Date().toISOString();
  return {
    content,
    mimeType: "text/plain",
    created_at: now,
    modified_at: now,
  };
}

const store = new InMemoryStore();
const fileData = createFileData(agentsMd);
await store.put(["filesystem"], "/AGENTS.md", fileData);

const checkpointer = new MemorySaver();

const agent = await createDeepAgent({
  model: "fireworks:accounts/fireworks/models/glm-5p2",
  backend: new StoreBackend({
    namespace: () => ["filesystem"],
  }),
  store: store,
  checkpointer: checkpointer,
  memory: ["/AGENTS.md"],
});

const result = await agent.invoke(
  {
    messages: [
      {
        role: "user",
        content: "Please tell me what's in your memory files.",
      },
    ],
  },
  { configurable: { thread_id: "12345" } },
);

import { createDeepAgent, StoreBackend, type FileData } from "deepagents";
import { InMemoryStore, MemorySaver } from "@langchain/langgraph";

const AGENTS_MD_URL =
  "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md";

async function fetchText(url: string): Promise<string> {
  const res = await fetch(url);
  if (!res.ok) {
    throw new Error(`Failed to fetch ${url}: ${res.status} ${res.statusText}`);
  }
  return await res.text();
}

const agentsMd = await fetchText(AGENTS_MD_URL);

function createFileData(content: string): FileData {
  const now = new Date().toISOString();
  return {
    content,
    mimeType: "text/plain",
    created_at: now,
    modified_at: now,
  };
}

const store = new InMemoryStore();
const fileData = createFileData(agentsMd);
await store.put(["filesystem"], "/AGENTS.md", fileData);

const checkpointer = new MemorySaver();

const agent = await createDeepAgent({
  model: "baseten:zai-org/GLM-5.2",
  backend: new StoreBackend({
    namespace: () => ["filesystem"],
  }),
  store: store,
  checkpointer: checkpointer,
  memory: ["/AGENTS.md"],
});

const result = await agent.invoke(
  {
    messages: [
      {
        role: "user",
        content: "Please tell me what's in your memory files.",
      },
    ],
  },
  { configurable: { thread_id: "12345" } },
);

import { createDeepAgent, StoreBackend, type FileData } from "deepagents";
import { InMemoryStore, MemorySaver } from "@langchain/langgraph";

const AGENTS_MD_URL =
  "https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/examples/text-to-sql-agent/AGENTS.md";

async function fetchText(url: string): Promise<string> {
  const res = await fetch(url);
  if (!res.ok) {
    throw new Error(`Failed to fetch ${url}: ${res.status} ${res.statusText}`);
  }
  return await res.text();
}

const agentsMd = await fetchText(AGENTS_MD_URL);

function createFileData(content: string): FileData {
  const now = new Date().toISOString();
  return {
    content,
    mimeType: "text/plain",
    created_at: now,
    modified_at: now,
  };
}

const store = new InMemoryStore();
const fileData = createFileData(agentsMd);
await store.put(["filesystem"], "/AGENTS.md", fileData);

const checkpointer = new MemorySaver();

const agent = await createDeepAgent({
  model: "ollama:north-mini-code-1.0",
  backend: new StoreBackend({
    namespace: () => ["filesystem"],
  }),
  store: store,
  checkpointer: checkpointer,
  memory: ["/AGENTS.md"],
});

const result = await agent.invoke(
  {
    messages: [
      {
        role: "user",
        content: "Please tell me what's in your memory files.",
      },
    ],
  },
  { configurable: { thread_id: "12345" } },
);

View example trace

为此示例打开一个公开的 LangSmith 运行。

import { createDeepAgent, FilesystemBackend } from "deepagents";
import { MemorySaver } from "@langchain/langgraph";

// Checkpointer is REQUIRED for human-in-the-loop
const checkpointer = new MemorySaver();

const agent = await createDeepAgent({
  model: "google:gemini-3.6-flash",
  backend: new FilesystemBackend({ rootDir: "/Users/user/{project}" }),
  memory: ["./AGENTS.md", "./.deepagents/AGENTS.md"],
  interruptOn: {
    read_file: true,
    write_file: true,
    delete_file: true,
  },
  checkpointer, // Required!
});

import { createDeepAgent, FilesystemBackend } from "deepagents";
import { MemorySaver } from "@langchain/langgraph";

// Checkpointer is REQUIRED for human-in-the-loop
const checkpointer = new MemorySaver();

const agent = await createDeepAgent({
  model: "openai:gpt-5.5",
  backend: new FilesystemBackend({ rootDir: "/Users/user/{project}" }),
  memory: ["./AGENTS.md", "./.deepagents/AGENTS.md"],
  interruptOn: {
    read_file: true,
    write_file: true,
    delete_file: true,
  },
  checkpointer, // Required!
});

import { createDeepAgent, FilesystemBackend } from "deepagents";
import { MemorySaver } from "@langchain/langgraph";

// Checkpointer is REQUIRED for human-in-the-loop
const checkpointer = new MemorySaver();

const agent = await createDeepAgent({
  model: "anthropic:claude-sonnet-5",
  backend: new FilesystemBackend({ rootDir: "/Users/user/{project}" }),
  memory: ["./AGENTS.md", "./.deepagents/AGENTS.md"],
  interruptOn: {
    read_file: true,
    write_file: true,
    delete_file: true,
  },
  checkpointer, // Required!
});

import { createDeepAgent, FilesystemBackend } from "deepagents";
import { MemorySaver } from "@langchain/langgraph";

// Checkpointer is REQUIRED for human-in-the-loop
const checkpointer = new MemorySaver();

const agent = await createDeepAgent({
  model: "openrouter:z-ai/glm-5.2",
  backend: new FilesystemBackend({ rootDir: "/Users/user/{project}" }),
  memory: ["./AGENTS.md", "./.deepagents/AGENTS.md"],
  interruptOn: {
    read_file: true,
    write_file: true,
    delete_file: true,
  },
  checkpointer, // Required!
});

import { createDeepAgent, FilesystemBackend } from "deepagents";
import { MemorySaver } from "@langchain/langgraph";

// Checkpointer is REQUIRED for human-in-the-loop
const checkpointer = new MemorySaver();

const agent = await createDeepAgent({
  model: "fireworks:accounts/fireworks/models/glm-5p2",
  backend: new FilesystemBackend({ rootDir: "/Users/user/{project}" }),
  memory: ["./AGENTS.md", "./.deepagents/AGENTS.md"],
  interruptOn: {
    read_file: true,
    write_file: true,
    delete_file: true,
  },
  checkpointer, // Required!
});

import { createDeepAgent, FilesystemBackend } from "deepagents";
import { MemorySaver } from "@langchain/langgraph";

// Checkpointer is REQUIRED for human-in-the-loop
const checkpointer = new MemorySaver();

const agent = await createDeepAgent({
  model: "baseten:zai-org/GLM-5.2",
  backend: new FilesystemBackend({ rootDir: "/Users/user/{project}" }),
  memory: ["./AGENTS.md", "./.deepagents/AGENTS.md"],
  interruptOn: {
    read_file: true,
    write_file: true,
    delete_file: true,
  },
  checkpointer, // Required!
});

import { createDeepAgent, FilesystemBackend } from "deepagents";
import { MemorySaver } from "@langchain/langgraph";

// Checkpointer is REQUIRED for human-in-the-loop
const checkpointer = new MemorySaver();

const agent = await createDeepAgent({
  model: "ollama:north-mini-code-1.0",
  backend: new FilesystemBackend({ rootDir: "/Users/user/{project}" }),
  memory: ["./AGENTS.md", "./.deepagents/AGENTS.md"],
  interruptOn: {
    read_file: true,
    write_file: true,
    delete_file: true,
  },
  checkpointer, // Required!
});

::: :::python

配置文件

一个 harness profile 是一个可重用的每个模型配置的包，create_deep_agent 在选择匹配的模型时自动应用。当您希望行为遵循模型而不是调用位置时，配置文件是正确的工具，例如为 Claude 的指令风格调整的系统提示词后缀、为 GPT 重写的工具描述或仅在特定提供者中才有意义的额外中间件。单个配置文件可以包含：自定义基础系统提示词 (base_system_prompt)、附加的后缀 (system_prompt_suffix)、工具描述覆盖、要排除的工具或中间件、要注入的额外中间件以及自动添加的通用子智能体的编辑。

from deepagents import HarnessProfile, register_harness_profile

# Append a system-prompt suffix whenever gpt-5.5 is selected.
register_harness_profile(
    "openai:gpt-5.5",
    HarnessProfile(system_prompt_suffix="Respond in under 100 words."),
)

有关注册密钥、合并语义和插件打包，请参阅 Profiles。一个更窄的配套 API，provider profiles，为提供者打包模型构造参数（API 密钥、超时设置、重试设置）。 :::

结构化输出

深度智能体支持结构化输出。 :::python 您可以通过将期望的结构化输出模式作为response_format参数传递给create_deep_agent()的调用来设置。当模型生成结构化数据时，它会被捕获、验证，并返回在深度智能体状态的’structured_response’键中。

import os
from typing import Literal

from pydantic import BaseModel, Field
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,
    )


class WeatherReport(BaseModel):
    """A structured weather report with current conditions and forecast."""
    location: str = Field(description="The location for this weather report")
    temperature: float = Field(description="Current temperature in Celsius")
    condition: str = Field(
        description="Current weather condition (e.g., sunny, cloudy, rainy)"
    )
    humidity: int = Field(description="Humidity percentage")
    wind_speed: float = Field(description="Wind speed in km/h")
    forecast: str = Field(description="Brief forecast for the next 24 hours")


agent = create_deep_agent(
    model=model,
    response_format=WeatherReport,
    tools=[internet_search],
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "What's the weather like in San Francisco?",
            }
        ]
    }
)

print(result["structured_response"])
# location='San Francisco, California' temperature=18.3 condition='Sunny' humidity=48 wind_speed=7.6 forecast='Pleasant sunny conditions expected to continue with temperatures around 64°F (18°C) during the day, dropping to around 52°F (11°C) at night. Clear skies with minimal precipitation expected.'

View example trace

为此示例打开一个公开的 LangSmith 运行。

::: :::js 您可以通过将期望的结构化输出模式作为responseFormat参数传递给createDeepAgent()的调用来设置。将模式包装在toolStrategy()或providerStrategy()等策略中，这些策略来自langchain。当模型生成结构化数据时，它会被捕获、验证，并返回在智能体状态的’structuredResponse’键中。

import { tool, toolStrategy } from "langchain";
import { TavilySearch } from "@langchain/tavily";
import { createDeepAgent } from "deepagents";
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),
      topic: z
        .enum(["general", "news", "finance"])
        .optional()
        .default("general"),
      includeRawContent: z.boolean().optional().default(false),
    }),
  },
);

const weatherReportSchema = z.object({
  location: z.string().describe("The location for this weather report"),
  temperature: z.number().describe("Current temperature in Celsius"),
  condition: z
    .string()
    .describe("Current weather condition (e.g., sunny, cloudy, rainy)"),
  humidity: z.number().describe("Humidity percentage"),
  windSpeed: z.number().describe("Wind speed in km/h"),
  forecast: z.string().describe("Brief forecast for the next 24 hours"),
});

const agent = await createDeepAgent({
  responseFormat: toolStrategy(weatherReportSchema),
  tools: [internetSearch],
});

const result = await agent.invoke({
  messages: [
    {
      role: "user",
      content: "What's the weather like in San Francisco?",
    },
  ],
});

console.log(result.structuredResponse);
// {
//   location: 'San Francisco, California',
//   temperature: 18.3,
//   condition: 'Sunny',
//   humidity: 48,
//   windSpeed: 7.6,
//   forecast: 'Clear skies with temperatures remaining mild. High of 18°C (64°F) during the day, dropping to around 11°C (52°F) at night.'
// }

View example trace

为此示例打开一个公开的 LangSmith 运行。

::: 有关更多信息及示例，请参阅响应格式。

高级

:::python create_deep_agent在@[create_agent]之上预组装了一个中间件栈。要构建一个完全自定义的智能体——选择要包含的确切功能——请参阅配置 harness。 ::: :::js createDeepAgent在createAgent之上预组装了一个中间件栈。要构建一个完全自定义的智能体——选择要包含的确切功能——请参阅配置 harness。 :::

官方原文：src/oss/deepagents/customization.mdx · 非官方翻译，译文由 AI 生成，以英文原文为准。

​模型

​工具

​MCP 工具

​系统提示词

​中间件

​Deep Agents 堆栈

​裸栈模式

​全栈

​同步子智能体栈

​预构建的中间件

​提供商特定的中间件

​自定义中间件

​覆盖默认中间件实例

​示例

​示例

​解释器

​子代理

​后端

​沙盒

​人机交互

​技能

View example trace

View example trace

View example trace

​记忆

View example trace

View example trace

​配置文件

​结构化输出

View example trace

View example trace

​高级

模型

工具

MCP 工具

系统提示词

中间件

Deep Agents 堆栈

裸栈模式

全栈

同步子智能体栈

预构建的中间件

提供商特定的中间件

自定义中间件

覆盖默认中间件实例

示例

示例

解释器

子代理

后端

沙盒

人机交互

技能

记忆

配置文件

结构化输出

高级