Agents

Alpha Notice: These docs cover the v1-alpha release. Content is incomplete and subject to change.For the latest stable version, see the v0 LangChain Python or LangChain JavaScript docs.

Agents combine language models with tools to create systems that can reason about tasks, decide which tools to use, and iteratively work towards solutions. createAgent() provides a production-ready ReAct (Reasoning + Acting) agent implementation based on the paper ReAct: Synergizing Reasoning and Acting in Language Models. ReAct frames an agent’s behavior as an interleaving of thought -> action -> observation steps, where the model writes out its reasoning, picks a tool, sees the tool’s result, and then repeats. ReAct reduces hallucinations and makes the decision process auditable: the agent can form hypotheses (thought), test them with tools (action), and update its plan based on feedback (observation). A ReAct loop runs until a stop condition - i.e., when the model emits a final answer or an iteration limit is reached.

create_agent() builds a graph-based agent runtime using LangGraph. A graph consists of nodes (steps) and edges (connections) that define how your agent processes information. The agent moves through this graph, executing nodes like the model node (which calls the model), the tools node (which executes tools), or pre/post model hook nodes.Learn more about the graph API.

Core components

Model

The model is the reasoning engine of your agent. It can be specified in multiple ways, supporting both static and dynamic model selection.

Static model

Static models are configured once when creating the agent and remain unchanged throughout execution. This is the most common and straightforward approach. To initialize a static model from a :

import { createAgent } from "langchain";

const agent = createAgent({
    model: "openai:gpt-5",
    tools: []
});

Model identifier strings use the format provider:model (e.g. "openai:gpt-5"). You may want more control over the model configuration, in which case you can initialize a model instance directly using the provider package:

import { createAgent } from "langchain";
import { ChatOpenAI } from "@langchain/openai";

const model = new ChatOpenAI({
    model: "gpt-4o",
    temperature: 0.1,
    maxTokens: 1000,
    timeout: 30
});

const agent = createAgent({
    model,
    tools: []
});

Model instances give you complete control over configuration. Use them when you need to set specific parameters like temperature, max tokens, timeouts, or configure API keys, base URLs, and other provider-specific settings. Refer to the API reference to see available params and methods on your model.

Dynamic model

Dynamic models are selected at based on the current and context. This enables sophisticated routing logic and cost optimization. To use a dynamic model, you need to provide a function that receives the graph state and runtime and returns an instance of BaseChatModel with the tools bound to it using .bindTools(tools), where tools is a subset of the tools parameter.

import { createAgent, AgentState } from "langchain";
import { ChatOpenAI } from "@langchain/openai";

const selectModel = (state: AgentState) => {
    const messageCount = state.messages.length;

    if (messageCount > 10) {
        return new ChatOpenAI({ model: "gpt-4.1" }).bindTools(tools);
    }
    return new ChatOpenAI({ model: "gpt-4o" }).bindTools(tools);
};

const agent = createAgent({
    llm: selectModel,
    tools,
});

For model configuration details, see Models.

Tools

Tools give agents the ability to take actions. Agents go beyond simple model-only tool binding by facilitating:

Multiple tool calls in sequence (triggered by a single prompt)
Parallel tool calls when appropriate
Dynamic tool selection based on previous results
Tool retry logic and error handling
State persistence across tool calls

Tools can be provided to the agent as either:

A list of tools (created with @[tool][@tool] function, or object that represents a built-in provider tool)
A configured ToolNode

Pass a list of tools

Passing a list of tools to the agent will create a ToolNode under the hood. This is the simplest way to set up a tool-calling agent:

import { z } from "zod";
import { createAgent, tool } from "langchain";

const search = tool(
    ({ query }) => {
        return `Results for: ${query}`;
    },
    {
        name: "search",
        description: "Search for information",
        schema: z.object({
        query: z.string().describe("The query to search for"),
        }),
    }
);

const calculate = tool(
    ({ expression }) => {
        return String(eval(expression));
    },
    {
        name: "calculate",
        description: "Perform calculations",
        schema: z.object({
        expression: z.string().describe("The expression to calculate"),
        }),
    }
);

const agent = createAgent({
    model: "openai:gpt-4o",
    tools: [search, calculate],
});

const result = await agent.invoke({
    messages: [
        {
        role: "user",
        content:
            "Find wireless headphones, check if they're in stock, and calculate shipping to New York",
        },
    ],
});

console.log(result);

If an empty tool list is provided, the agent will consist of a single LLM node without tool calling.

Pass a configured ToolNode

Alternatively, you can create a ToolNode directly and pass it to the agent. This allows you to customize the tool node’s behavior, such as handling tool errors:

import { ToolNode, ToolMessage } from "langchain";

const toolNode = new ToolNode([search, calculate], {
    handleToolErrors: (error, toolCall) => {
        return new ToolMessage({
            content: "Please check your input and try again.",
            tool_call_id: toolCall.id
        });
    }
});

To learn more about error handling in ToolNode, see ToolNode.

Tool use in the ReAct loop

Agents follow the ReAct (Reasoning + Acting) pattern, alternating between brief reasoning steps with targeted tool calls and feeding the resulting observations into subsequent decisions until they can deliver a final answer.

Example of ReAct loop

Prompt: Identify the current most popular wireless headphones and verify availability.

================================ Human Message =================================

Find the most popular wireless headphones right now and check if they're in stock

Reasoning: “Popularity is time-sensitive, I need to use the provided search tool.”Acting: Call search_products("wireless headphones")

================================== Ai Message ==================================
Tool Calls:
  search_products (call_abc123)
 Call ID: call_abc123
  Args:
    query: wireless headphones

================================= Tool Message =================================

Found 5 products matching "wireless headphones". Top 5 results: WH-1000XM5, ...

Reasoning: “I need to confirm availability for the top-ranked item before answering.”Acting: Call check_inventory("WH-1000XM5")

================================== Ai Message ==================================
Tool Calls:
  check_inventory (call_def456)
 Call ID: call_def456
  Args:
    product_id: WH-1000XM5

================================= Tool Message =================================

Product WH-1000XM5: 10 units in stock

Reasoning: “I have the most popular model and its stock status. I can now answer the user’s question.”Acting: Produce final answer

================================== Ai Message ==================================

I found wireless headphones (model WH-1000XM5) with 10 units in stock...

To learn more about tools, see Tools.

Prompt

You can shape how your agent approaches tasks by providing a prompt. The prompt parameter can be provided as a string, SystemMessage, or a callable:

const agent = createAgent({
    model,
    tools,
    prompt: "You are a helpful assistant. Be concise and accurate."
});

When no prompt is provided, the agent will infer its task from the messages directly.

Dynamic prompts with middleware

For more advanced use cases where you need to modify the system prompt based on runtime context or agent state, you can use the modifyModelRequest decorator to create a simple custom middleware. Dynamic system prompt is especially useful for personalizing prompts based on user roles, conversation context, or other changing factors:

import { z } from "zod";
import { createAgent } from "langchain";
import { dynamicSystemPromptMiddleware } from "langchain/middleware";

const contextSchema = z.object({
    userRole: z.enum(["expert", "beginner"]),
});

const agent = createAgent({
    model: "openai:gpt-4o",
    tools: [/* ... */],
    contextSchema,
    middleware: [
        dynamicSystemPromptMiddleware<z.infer<typeof contextSchema>>((state, runtime) => {
            const userRole = runtime.context.userRole || "user";
            const basePrompt = "You are a helpful assistant.";

            if (userRole === "expert") {
                return `${basePrompt} Provide detailed technical responses.`;
            } else if (userRole === "beginner") {
                return `${basePrompt} Explain concepts simply and avoid jargon.`;
            }
            return basePrompt;
        }),
    ],
});

// The system prompt will be set dynamically based on context
const result = await agent.invoke(
    { messages: [{ role: "user", content: "Explain machine learning" }] },
    { context: { userRole: "expert" } }
);

For more details on message types and formatting, see Messages. For comprehensive middleware documentation, see Middleware.

Advanced configuration

Structured output

In some situations, you may want the agent to return an output in a specific format. LangChain provides a simple, universal way to do this with the responseFormat parameter.

import { z } from "zod";
import { createAgent } from "langchain";

const ContactInfo = z.object({
    name: z.string(),
    email: z.string(),
    phone: z.string(),
});

const agent = createAgent({
    model: "openai:gpt-4o",
    tools: [],
    responseFormat: ContactInfo,
});

const result = await agent.invoke({
    messages: [
        {
        role: "user",
        content:
            "Extract contact info from: John Doe, john@example.com, (555) 123-4567",
        },
    ],
});

console.log(result.structuredResponse);
/**
 * {
 *   name: 'John Doe',
 *   email: 'john@example.com',
 *   phone: '(555) 123-4567'
 * }
 */

To learn about structured output, see Structured output.

Memory

Agents maintain conversation history automatically through the message state. You can also configure the agent to use a custom state schema to remember additional information during the conversation. Information stored in the state can be thought of as the short-term memory of the agent:

import { z } from "zod";
import { MessagesZodState } from "@langchain/langgraph";
import { createAgent, type BaseMessage } from "langchain";

const customAgentState = z.object({
    messages: MessagesZodState.shape.messages,
    userPreferences: z.record(z.string(), z.string()),
});

const CustomAgentState = createAgent({
    model: "openai:gpt-4o",
    tools: [],
    stateSchema: customAgentState,
});

To learn more about memory, see Memory. For information on implementing long-term memory that persists across sessions, see Long-term memory.

Pre-model hook

Pre-model hook is an optional node that can process state before the model is called. Use cases include message trimming, summarization, and context injection. It must be a callable or a runnable that takes in current graph state and returns a state update in the form of:

const agent = createAgent({
    model: "openai:gpt-4o",
    preModelHook: (state) => {
        return {
            messages: [RemoveMessage({ id: REMOVE_ALL_MESSAGES }), ...state.messages],
        };
    },
});

Example of a pre-model hook that trims messages to fit the context window:

import { createAgent, type AgentState } from "langchain";
import { REMOVE_ALL_MESSAGES } from "@langchain/langgraph";
import { RemoveMessage } from "@langchain/core/messages";

const trimMessages = (state: AgentState) => {
    const messages = state.messages;

    if (messages.length <= 3) {
        return { messages };
    }

    const firstMsg = messages[0];
    const recentMessages = messages.length % 2 === 0
        ? messages.slice(-3)
        : messages.slice(-4);

    const newMessages = [firstMsg, ...recentMessages];

    return {
        messages: [
            new RemoveMessage({ id: REMOVE_ALL_MESSAGES }),
            ...newMessages
        ]
    };
};

const agent = createAgent({
    model: "openai:gpt-4o",
    tools,
    preModelHook: trimMessages,
});

messages must be provided and will be used as an input to the agent node (i.e., the node that calls the LLM). The rest of the keys will be added to the graph state.

If you are returning messages in the pre-model hook, you should overwrite the messages key by doing the following:

import { RemoveMessage } from "@langchain/core/messages";
import { REMOVE_ALL_MESSAGES } from "@langchain/langgraph";

const agent = createAgent({
    // ...
    preModelHook: (state) => {
        // ...
        return {
            messages: [
                RemoveMessage({ id: REMOVE_ALL_MESSAGES }),
                ...state.messages
            ],
        };
    };
});

Post-model hook

Post-model hook is an optional node that can process the model’s response before tool execution. Use cases include validation, guardrails, or other post-processing. It must be a callable or a runnable that takes in current graph state and returns a state update. Example of a post-model hook that filters out confidential information:

import { createAgent, type AgentState, AIMessage, RemoveMessage } from "langchain";
import { REMOVE_ALL_MESSAGES } from "@langchain/langgraph";

const validateResponse = (state: AgentState) => {
    const lastMessage = state.messages.at(-1)?.content as string;
    if (lastMessage.toLowerCase().includes("confidential")) {
        return {
        messages: [
            new RemoveMessage({ id: REMOVE_ALL_MESSAGES }),
            ...state.messages.slice(0, -1),
            new AIMessage("I cannot share confidential information."),
        ],
        };
    }
    return {};
};

const agent = createAgent({
    model: "openai:gpt-4o",
    tools,
    postModelHook: validateResponse,
});

Streaming

We’ve seen how the agent can be called with .invoke to get a final response. If the agent executes multiple steps, this may take a while. To show intermediate progress, we can stream back messages as they occur.

const stream = await agent.stream(
    {
        messages: [new HumanMessage("What's the weather in NYC?")],
    },
    { streamMode: "values" }
);

for await (const chunk of stream) {
    // Each chunk contains the full state at that point
    const latestMessage = chunk.messages.at(-1);
    if (latestMessage?.content) {
        console.log(`Agent: ${latestMessage.content}`);
    } else if (latestMessage?.tool_calls) {
        console.log(`Calling tools: ${latestMessage.tool_calls.map((tc: ToolCall) => tc.name).join(", ")}`);
    }
}

For more details on streaming, see Streaming.

Get started

Core components

Advanced usage

Use in production

Core components

Model

Static model

Dynamic model

Tools

Pass a list of tools

Pass a configured ToolNode

Tool use in the ReAct loop

Prompt

Dynamic prompts with middleware

Advanced configuration

Structured output

Memory

Pre-model hook

Post-model hook

Streaming

Get started

Core components

Advanced usage

Use in production

​Core components

​Model

​Static model

​Dynamic model

​Tools

​Pass a list of tools

​Pass a configured ToolNode

​Tool use in the ReAct loop

​Prompt

​Dynamic prompts with middleware

​Advanced configuration

​Structured output

​Memory

​Pre-model hook

​Post-model hook

​Streaming

Core components

Model

Static model

Dynamic model

Tools

Pass a list of tools

Pass a configured ToolNode

Tool use in the ReAct loop

Prompt

Dynamic prompts with middleware

Advanced configuration

Structured output

Memory

Pre-model hook

Post-model hook

Streaming