The batteries-included agent harness.

Using an LLM to call tools in a loop is the simplest form of an agent. This architecture, however, can yield agents that are "shallow" and fail to plan and act over longer, more complex tasks. Applications like "Deep Research", "Manus", and "Claude Code" have gotten around this limitation by implementing a combination of four things: a **planning tool**, **sub agents**, access to a **file system**, and a **detailed prompt**. `deepagents` is a TypeScript package that implements these in a general purpose way so that you can easily create a Deep Agent for your application. > 💡 **Tip:** Looking for the Python version of this package? See [langchain-ai/deepagents](https://github.com/langchain-ai/deepagents)

[Documentation](https://docs.langchain.com/oss/javascript/deepagents/overview) | [Examples](./examples) | [Report Bug](https://github.com/langchain-ai/deepagentsjs/issues) | [Request Feature](https://github.com/langchain-ai/deepagentsjs/issues)

## 📖 Overview Using an LLM to call tools in a loop is the simplest form of an agent. However, this architecture can yield agents that are "shallow" and fail to plan and act over longer, more complex tasks. Applications like **Deep Research**, **Manus**, and **Claude Code** have overcome this limitation by implementing a combination of four key components: 1. **Planning Tool** - Strategic task decomposition 2. **Sub-Agents** - Specialized agents for subtasks 3. **File System Access** - Persistent state and memory 4. **Detailed Prompts** - Context-rich instructions **Deep Agents** is a TypeScript package that implements these patterns in a general-purpose way, enabling you to easily create sophisticated agents for your applications. ## ✨ Features - 🎯 **Task Planning & Decomposition** - Break complex tasks into manageable steps - 🤖 **Sub-Agent Architecture** - Delegate specialized work to focused agents - 💾 **File System Integration** - Persistent memory and state management - 🌊 **Streaming Support** - Real-time updates, token streaming, and progress tracking - 🔄 **LangGraph Powered** - Built on the robust LangGraph framework - 📝 **TypeScript First** - Full type safety and IntelliSense support - 🔌 **Extensible** - Easy to customize and extend for your use case ## Installation ```bash # npm npm install deepagents # yarn yarn add deepagents # pnpm pnpm add deepagents ``` ## Usage (To run the example below, you will need to `npm install @langchain/tavily`). Make sure to set `TAVILY_API_KEY` in your environment. You can generate one [here](https://www.tavily.com/). ```typescript import { tool } from "langchain"; import { TavilySearch } from "@langchain/tavily"; import { createDeepAgent } from "deepagents"; import { z } from "zod"; // Web search tool 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,