> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-5e9cc07a-preview-docscl-1781043860-248c713.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Deep Agents overview

> Build agents that can plan, use subagents, and leverage file systems for complex tasks

The easiest way to start building agents and applications powered by LLMs—with built-in capabilities for task planning, file systems for context management, subagent-spawning, and long-term memory.
You can use deep agents for any task, including complex, multi-step tasks.

Deep Agents is an ["agent harness"](/oss/javascript/concepts/products#agent-harnesses-like-the-deep-agents-sdk). It is the same core tool calling loop as other agent frameworks, but with built-in capabilities that make agents reliable for real tasks:

<CardGroup cols={2}>
  <Card title="Take actions in an environment" icon="bolt">
    Take actions via tools, read and write files, execute code
  </Card>

  <Card title="Connect to your data" icon="database">
    Load memories, skills, and domain knowledge at the right moment
  </Card>

  <Card title="Manage growing context" icon="scissors">
    Summarize history and offload large results across long runs
  </Card>

  <Card title="Parallelize tasks" icon="sitemap">
    Delegate to general or specialized subagents running in isolated context windows
  </Card>

  <Card title="Stay in the loop" icon="user">
    Pause for human approval at critical decision points
  </Card>

  <Card title="Improve over time" icon="rocket">
    Update memory, skills, and prompts based on real usage
  </Card>
</CardGroup>

See [Harness capabilities](/oss/javascript/deepagents/harness) for a full breakdown of each component.

[`deepagents`](https://www.npmjs.com/package/deepagents) is a standalone library built on top of [LangChain](/oss/javascript/langchain/)'s core building blocks for agents and using [LangGraph](/oss/javascript/langgraph/)'s tooling for running agents in production.

[LangChain](/oss/javascript/langchain/) is the framework that provides the core building blocks for your agents.
To learn more about the differences between LangChain, LangGraph, and Deep Agents, see [Frameworks, runtimes, and harnesses](/oss/javascript/concepts/products). For a side-by-side comparison with Anthropic's harness, see [Deep Agents vs. Claude Agent SDK](/oss/javascript/deepagents/comparison).

## <Icon icon="wand" /> Create a deep agent

```ts theme={null}
import * as z from "zod";
// npm install deepagents langchain @langchain/core
import { createDeepAgent } from "deepagents";
import { tool } from "langchain";

const getWeather = tool(
  ({ city }) => `It's always sunny in ${city}!`,
  {
    name: "get_weather",
    description: "Get the weather for a given city",
    schema: z.object({
      city: z.string(),
    }),
  },
);

const agent = createDeepAgent({
  tools: [getWeather],
  systemPrompt: "You are a helpful assistant",
});

console.log(
  await agent.invoke({
    messages: [{ role: "user", content: "What's the weather in Tokyo?" }],
  })
);
```

See the [Quickstart](/oss/javascript/deepagents/quickstart/) and [Customization guide](/oss/javascript/deepagents/customization/) to get started building your own agents and applications with Deep Agents.

<Tip>
  Trace requests, debug agent behavior, and evaluate outputs with [LangSmith](https://smith.langchain.com?utm_source=docs\&utm_medium=cta\&utm_campaign=langsmith-signup\&utm_content=oss-deepagents-overview). Follow the [observability quickstart](/langsmith/observability-quickstart) to get set up. When ready for production, see [Going to production](/oss/javascript/deepagents/going-to-production) for LangSmith deployment options.
</Tip>

## Core capabilities

Use the **Deep Agents SDK** to build agents that handle complex, multi-step tasks across **any [model provider](/oss/javascript/deepagents/models)**. The SDK ships with the following built-in capabilities:

<Card title="Planning and task decomposition" icon="timeline">
  A built-in [`write_todos`](/oss/javascript/langchain/middleware/built-in#to-do-list) tool lets agents break down complex tasks into discrete steps, track progress, and adapt plans as new information emerges.
</Card>

<Card title="Context management" icon="scissors">
  Built-in [context compression](/oss/javascript/deepagents/context-engineering#context-compression) offloads large tool inputs and results to the [virtual filesystem](/oss/javascript/deepagents/harness#virtual-filesystem-access) and [summarizes](/oss/javascript/deepagents/context-engineering#summarization) older messages to keep agents effective across extended sessions.
</Card>

<Card title="Tools and MCP" icon="tool">
  Pass custom functions, LangChain tools, or tools from any [MCP server](/oss/javascript/deepagents/tools#mcp-tools) to `create_deep_agent`. Deep Agents fully support the [Model Context Protocol (MCP)](/oss/javascript/langchain/mcp), letting you connect to databases, APIs, file systems, and more through a standard interface.
</Card>

<Card title="Pluggable filesystem backends" icon="plug">
  Swap the virtual filesystem via [pluggable backends](/oss/javascript/deepagents/backends): in-memory state, local disk, LangGraph store, composite routing, or a custom backend with [permission rules](/oss/javascript/deepagents/permissions) for read and write access.
</Card>

<Card title="Shell execution" icon="terminal">
  Shell-capable backends add an `execute` tool for tests, builds, git operations, and system tasks. Use [`LocalShellBackend`](/oss/javascript/deepagents/backends#localshellbackend-local-shell) on the host for local development, or a [sandbox backend](/oss/javascript/deepagents/sandboxes) when you need isolation from your host system.
</Card>

<Card title="Interpreters" icon="code">
  Add an [interpreter](/oss/javascript/deepagents/interpreters) to run JavaScript in an in-memory runtime. Interpreters let agents compose tools programmatically, orchestrate subagents, and transform structured data without a full shell environment.
</Card>

<Card title="Subagent spawning" icon="users-group">
  A built-in `task` tool spawns general-purpose or specialized [subagents](/oss/javascript/deepagents/subagents) for context isolation on subtasks. For long-running or parallel work, [async subagents](/oss/javascript/deepagents/async-subagents) run in the background with progress checks, follow-ups, and cancellation.
</Card>

<Card title="Streaming" icon="broadcast">
  [Event streaming](/oss/javascript/deepagents/event-streaming) exposes agent runs as typed projections for messages, tool calls, values, and output. Deep Agents add `stream.subagents` so each delegated task gets its own handle with independent message, tool-call, and nested subagent streams.
</Card>

<Card title="Long-term memory" icon="database">
  Persist memory across threads and conversations using LangGraph's [Memory Store](/oss/javascript/langgraph/persistence#memory-store).
</Card>

<Card title="Filesystem permissions" icon="lock">
  Declare [permission rules](/oss/javascript/deepagents/permissions) that control which files and directories agents can read or write. Subagents can inherit or override the parent's rules.
</Card>

<Card title="Human-in-the-loop" icon="user-check">
  Configure [human approval](/oss/javascript/deepagents/human-in-the-loop) for sensitive tool operations using LangGraph's interrupt capabilities.
</Card>

<Card title="Skills" icon="puzzle">
  Extend agents with reusable [skills](/oss/javascript/deepagents/skills) that provide specialized workflows, domain knowledge, and custom instructions.
</Card>

<Card title="Smart defaults" icon="wand">
  Ships with opinionated system prompts that teach the model to plan before acting, verify work, and manage context. Customize or replace the defaults as needed.
</Card>

For building custom agents without these builtin capabilities, consider using LangChain's [`createAgent`](/oss/javascript/langchain/agents) or building a custom [LangGraph](/oss/javascript/langgraph/overview) workflow.

## Get started

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/oss/javascript/deepagents/quickstart">
    Build your first deep agent
  </Card>

  <Card title="Customization" icon="adjustments" href="/oss/javascript/deepagents/customization">
    Learn about customization options
  </Card>

  <Card title="Tools and MCP" icon="tool" href="/oss/javascript/deepagents/tools">
    Connect custom functions, APIs, and MCP servers
  </Card>

  <Card title="Models" icon="cpu" href="/oss/javascript/deepagents/models">
    Configure models and providers
  </Card>

  <Card title="Backends" icon="plug" href="/oss/javascript/deepagents/backends">
    Choose and configure pluggable filesystem backends
  </Card>

  <Card title="Interpreters" icon="code" href="/oss/javascript/deepagents/interpreters">
    Compose tools and transform data in QuickJS
  </Card>

  <Card title="Permissions" icon="lock" href="/oss/javascript/deepagents/permissions">
    Control filesystem access with permission rules
  </Card>

  <Card title="Human-in-the-loop" icon="user-check" href="/oss/javascript/deepagents/human-in-the-loop">
    Configure approval for sensitive operations
  </Card>

  <Card title="Code" icon="terminal" href="/oss/javascript/deepagents/code/overview">
    Use Deep Agents Code
  </Card>

  <Card title="Reference" icon="external-link" href="https://reference.langchain.com/javascript/modules/deepagents.html">
    See the `deepagents` API reference
  </Card>
</CardGroup>

***

<div className="source-links">
  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>

  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/deepagents/overview.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>