The batteries-included agent harness.

Deep Agents is an agent harness. An opinionated, ready-to-run agent out of the box. Instead of wiring prompts, tools, and context management yourself, you get a working agent immediately and customize what you need.

What's included:

• Planning — write_todos for task breakdown and progress tracking
• Filesystem — read_file, write_file, edit_file, ls, glob, grep for working memory
• Sub-agents — task for delegating work with isolated context windows
• Smart defaults — built-in prompt and middleware that make these tools useful out of the box
• Context management — file-based workflows to keep long tasks manageable

Note

Looking for the Python package? See langchain-ai/deepagents.

Quickstart

npm install deepagents
# or
pnpm add deepagents
# or
yarn add deepagents

Important

deepagents declares the LangChain runtime packages as peer dependencies so your app controls their versions and everything resolves to a single shared copy. npm 7+ and pnpm 8+ install these automatically; Yarn users must add them explicitly:

yarn add @langchain/core @langchain/langgraph @langchain/langgraph-checkpoint @langchain/langgraph-sdk langchain langsmith

import { createDeepAgent } from "deepagents";

const agent = createDeepAgent();

const result = await agent.invoke({
  messages: [
    {
      role: "user",
      content: "Research LangGraph and write a summary in summary.md",
    },
  ],
});

The agent can plan, read/write files, and manage longer tasks with sub-agents and filesystem tools.

Tip

For developing, debugging, and deploying AI agents and LLM applications, see LangSmith.

Runtime Entrypoints

deepagents now publishes environment-specific entrypoints:

• deepagents - default Node.js/server entrypoint with the full API.
• deepagents/browser - recommended browser entrypoint (no Node-only exports).
• deepagents/node - optional explicit Node.js entrypoint (same full API as deepagents).

// Browser-safe usage
import { createDeepAgent, StateBackend } from "deepagents/browser";

// Node.js usage (recommended)
import { createDeepAgent, FilesystemBackend } from "deepagents";

// Optional explicit Node.js usage
// import { createDeepAgent, FilesystemBackend } from "deepagents/node";

Customization

Add tools, swap models, and customize prompts as needed:

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

const agent = createDeepAgent({
  model: new ChatOpenAI({ model: "gpt-5", temperature: 0 }),
  tools: [myCustomTool],
  systemPrompt: "You are a research assistant.",
});

A string is placed before the built-in Deep Agent prompt. For full control over prompt assembly, provide a structured configuration:

const agent = createDeepAgent({
  systemPrompt: {
    prefix: "You are the support assistant for Acme.",
    base: null, // Remove the built-in Deep Agent prompt.
    suffix: "Follow Acme's escalation policy.",
  },
});

Structured prompts are assembled as prefix → base → suffix, followed by any model-specific harness profile suffix. Omit base to retain the active base prompt, or set it to null to remove the base entirely.

See the JavaScript Deep Agents docs for full configuration options.

LangGraph Native

createDeepAgent returns a compiled LangGraph graph, so you can use streaming, Studio, checkpointers, and other LangGraph features.

Why Use It

• 100% open source — MIT licensed and extensible
• Provider agnostic — works with tool-calling chat models
• Built on LangGraph — production runtime with streaming and persistence
• Batteries included — planning, file access, sub-agents, and defaults out of the box
• Fast to start — install and run with sensible defaults
• Easy to customize — add tools/models/prompts when you need to

---

Documentation

• docs.langchain.com - Concepts and guides
• Examples - Working agents and patterns
• LangChain Forum - Community discussion and support

Security

Deep Agents follows a "trust the LLM" model. The agent can do anything its tools allow. Enforce boundaries at the tool/sandbox level, not by expecting the model to self-police. See the security policy for more information.