Sandbox::https://docs.langchain.com/oss/javascript/langgraph/functional-api

The Functional API wraps ordinary functions with LangGraph runtime features (persistence, memory, human-in-the-loop, and streaming). Use it when you already have existing code or are using a different framework and want to deploy it on LangSmith without rewriting that agent as a graph. Prefer the Graph API for building new agents. This page is the concept reference for entrypoints, tasks, checkpointing, and resume rules. For the wrap-and-deploy how-to, see Deploy other frameworks. The Functional API uses two building blocks:

entrypoint: Encapsulates workflow logic and manages execution, interrupts, and checkpointing.
task: Marks a discrete unit of work (for example, an API call). Tasks return a Promise that you await inside the entrypoint.

When to use the Functional API

Build	Use
New LangGraph agents and workflows	Graph API
Existing agent in another framework (Claude Agent SDK, Strands, CrewAI, AutoGen, and similar) that you want on LangSmith Agent Server	Functional API via Deploy other frameworks

Compared with the Graph API, the Functional API uses ordinary language control flow (if / else, loops, and calls), keeps values scoped to the entrypoint and tasks instead of a shared state schema, saves task results on the entrypoint checkpoint rather than after each super-step, and has no static graph visualization.

Entrypoint

The entrypoint function creates a workflow from a function. It manages long-running work and interrupts.

Definition

Pass a checkpointer when you need persistence or human-in-the-loop. Identify each run with a thread_id in config. A thread is the durable identity for one conversation or workflow run. An entrypoint is created by calling entrypoint with configuration and a function. The function must accept a single positional argument as the workflow input. To pass multiple values, use an object as that argument. The result is a workflow object. Call invoke to run it.

import { MemorySaver, entrypoint } from "@langchain/langgraph";

const checkpointer = new MemorySaver();

const myWorkflow = entrypoint(
  { checkpointer, name: "workflow" },
  async (name: string): Promise<string> => {
    return `Hello, ${name}`;
  }
);

const config = { configurable: { thread_id: "1" } };
await myWorkflow.invoke("Alice", config); // "Hello, Alice"

Serialization Entrypoint inputs and outputs must be JSON-serializable when a checkpointer is configured. See Serialization.

Run and resume

Call invoke for a final result. For streams, see Streaming. Resume after interrupt by passing a resume value in Command. For recipes, see Interrupts. After an error, resume the same thread_id with null.

Short-term memory

When an entrypoint has a checkpointer, successive invocations on the same thread id store state in checkpoints. Call getPreviousState inside the entrypoint. It returns the last value saved on this thread. On the first run it is undefined. To save a different value for the next run, use entrypoint.final.

Injectable parameters

You can skip this until you add memory or custom streaming. The entrypoint function can take a second config argument. LangGraph also provides helpers you call inside the function:

Helper	Description
getPreviousState	The return value from the previous invocation on the same thread (requires a checkpointer). See short-term memory.
config	A `LangGraphRunnableConfig` object with run-time configuration values.
config.store	A store instance for long-term memory.
config.writer	A writer for custom streaming. See Streaming.

Requesting injectable parameters

import {
  MemorySaver,
  InMemoryStore,
  entrypoint,
  getPreviousState,
} from "@langchain/langgraph";
import type { LangGraphRunnableConfig } from "@langchain/langgraph";

const checkpointer = new MemorySaver();
const store = new InMemoryStore();

const myWorkflow = entrypoint(
  { checkpointer, store, name: "workflow" },
  async (
    someInput: Record<string, unknown>,
    config: LangGraphRunnableConfig
  ) => {
    const previous = getPreviousState();
    const memoryStore = config.store;
    const writer = config.writer;
    return { previous, someInput };
  }
);

Task

A task is a discrete unit of work (for example, an API call or data step). Tasks have two key properties:

Concurrent execution: Calling a task starts it immediately. The entrypoint blocks only when you wait for the result, so independent tasks can overlap.
Checkpointing: Task results are saved so resume can restore them. See persistence.

Definition

Define tasks with the task function:

import { task } from "@langchain/langgraph";

const slowComputation = task("slowComputation", async (inputValue: number) => {
  // Long-running or side-effecting work
  return inputValue * 2;
});

Serialization: Task outputs must be JSON-serializable to support checkpointing.

Execution

Call tasks only from an entrypoint, another task, or a Graph API node. Do not call them from application code outside the workflow. Calling a task returns a Promise. Await it inside the entrypoint:

import { MemorySaver, entrypoint, task } from "@langchain/langgraph";

const checkpointer = new MemorySaver();

const slowComputation = task("slowComputation", async (inputValue: number) => {
  return inputValue * 2;
});

const myWorkflow = entrypoint(
  { checkpointer, name: "workflow" },
  async (someInput: number): Promise<number> => {
    return await slowComputation(someInput);
  }
);

When to use a task

Use tasks when you need:

Checkpointing: Save a long-running result so resume does not recompute it.
Human-in-the-loop: Wrap work you should not redo after a pause in a task, for example an LLM call. Resume after an interrupt restores the result. For randomness, see Determinism.
Parallel execution: Run independent I/O-bound work concurrently.
Observability: Track discrete steps in LangSmith.
Retries: Apply retry policies to discrete units of work. See Fault tolerance.

Resume and checkpointing

Resume replay depends on serialization, determinism, and idempotency.

Serialization

Two rules apply when a checkpointer is configured:

entrypoint inputs and outputs must be JSON-serializable.
task outputs must be JSON-serializable.

Use primitives such as objects, arrays, strings, numbers, and booleans. Serialization is what makes task results and intermediate values restorable for human-in-the-loop, fault tolerance, and parallel execution. Non-serializable values raise a runtime error when a checkpointer is configured.

Determinism

Resume does not continue from the exact line where execution stopped. Execution returns to a checkpoint boundary and replays forward until it hits the pause again. For the Functional API, replay starts at the beginning of the entrypoint. LangGraph restores completed task and subgraph results from the checkpointer instead of recomputing them. That preserves step order across pauses, including for long-running or non-deterministic task outputs. For human-in-the-loop, put non-deterministic work (for example, random values) and side effects (for example, file writes or API calls) in tasks. Different runs can produce different results. Resuming a specific thread should replay the same persisted task and subgraph results. Guidelines:

Avoid repeating work: Give each side effect in an entrypoint its own task so resume restores outputs instead of re-running them.
Encapsulate non-deterministic operations: Keep values that change between attempts (random numbers, wall-clock time) inside tasks.
Use idempotent operations: For partial failures and retries, see Idempotency.

Idempotency

Idempotency means running the same operation more than once has the same effect as running it once. Place API calls and other writes inside tasks, and design those tasks to be safe if they run again. On resume, LangGraph restores completed task results. A task that started but did not finish may run again, so use idempotency keys or check existing results before writing.

Pause for human review

This workflow writes an essay and interrupts for human review:

import { MemorySaver, entrypoint, task, interrupt } from "@langchain/langgraph";

const writeEssay = task("writeEssay", async (topic: string) => {
  // Placeholder for a long-running task.
  await new Promise((resolve) => setTimeout(resolve, 1000));
  return `An essay about topic: ${topic}`;
});

const workflow = entrypoint(
  { checkpointer: new MemorySaver(), name: "workflow" },
  async (topic: string) => {
    const essay = await writeEssay(topic);
    const isApproved = interrupt({
      // Any JSON-serializable payload. Surfaces as an Interrupt when streaming.
      essay,
      action: "Please approve/reject the essay",
    });

    return {
      essay,
      isApproved,
    };
  }
);

Invoke with a topic such as "cat". The run writes the essay, then pauses at interrupt. The pause can last indefinitely. Resume starts at the beginning of the entrypoint. The writeEssay task result is restored, not recomputed. For stream, resume, and tool-call review, see Interrupts.

Common pitfalls

Handling side effects

Put side effects (writing a file, sending an email) in tasks so resume does not run them again.

Incorrect
Correct

The file write runs in the entrypoint, so resume executes it a second time.

import { MemorySaver, entrypoint, interrupt } from "@langchain/langgraph";
import fs from "fs";

const checkpointer = new MemorySaver();

const myWorkflow = entrypoint(
  { checkpointer, name: "workflow" },
  async (inputs: Record<string, any>) => {
    // Runs again on resume.
    fs.writeFileSync("output.txt", "Side effect executed");
    const value = interrupt("question");
    return value;
  }
);

The side effect lives in a task, so resume restores the checkpointed result.

import { MemorySaver, entrypoint, task, interrupt } from "@langchain/langgraph";
import * as fs from "fs";

const checkpointer = new MemorySaver();

const writeToFile = task("writeToFile", async () => {
  fs.writeFileSync("output.txt", "Side effect executed");
});

const myWorkflow = entrypoint(
  { checkpointer, name: "workflow" },
  async (inputs: Record<string, any>) => {
    await writeToFile();
    const value = interrupt("question");
    return value;
  }
);

Non-deterministic control flow

Encapsulate time and randomness in tasks so resume returns the same values.

In a task: Get random number (5) → interrupt → resume → (returns 5 again) → …
Not in a task: Get random number (5) → interrupt → resume → get new random number (7) → …

With multiple interrupt calls, LangGraph matches resume values by index to each interrupt. If resume changes the order of interrupts, a resume value can attach to the wrong interrupt. See Determinism.

Incorrect
Correct

Reading the clock in the entrypoint can change which branch runs on resume.

import { MemorySaver, entrypoint, task, interrupt } from "@langchain/langgraph";

const checkpointer = new MemorySaver();

const slowTask = task("slowTask", async (x: number) => x);

const myWorkflow = entrypoint(
  { checkpointer, name: "workflow" },
  async (inputs: { t0: number }) => {
    const t1 = Date.now();

    const deltaT = t1 - inputs.t0;

    if (deltaT > 1000) {
      const result = await slowTask(1);
      const value = interrupt("question");
      return { result, value };
    } else {
      const result = await slowTask(2);
      const value = interrupt("question");
      return { result, value };
    }
  }
);

Read the clock inside a task so resume restores the same timestamp and branch.

import { MemorySaver, entrypoint, task, interrupt } from "@langchain/langgraph";

const checkpointer = new MemorySaver();

const slowTask = task("slowTask", async (x: number) => x);
const getTime = task("getTime", async () => Date.now());

const myWorkflow = entrypoint(
  { checkpointer, name: "workflow" },
  async (inputs: { t0: number }) => {
    const t1 = await getTime();

    const deltaT = t1 - inputs.t0;

    if (deltaT > 1000) {
      const result = await slowTask(1);
      const value = interrupt("question");
      return { result, value };
    } else {
      const result = await slowTask(2);
      const value = interrupt("question");
      return { result, value };
    }
  }
);

Learn more

Connect these docs to your agent of choice via MCP for real-time answers.

Edit this page on GitHub or file an issue.

Get started

Capabilities

Patterns

Build with the Graph API

Deployment

Frontend

Advanced

Functional API overview

When to use the Functional API

Entrypoint

Definition

Run and resume

Short-term memory

Injectable parameters

Task

Definition

Execution

When to use a task

Resume and checkpointing

Serialization

Determinism

Idempotency

Pause for human review

Common pitfalls

Handling side effects

Non-deterministic control flow

Learn more