explaingit

langchain-ai/deepagents

📈 Trending★ 22,954PythonAudience · developerComplexity · 3/5ActiveLicenseSetup · moderate

TLDR

Ready-to-use AI agent framework that lets language models plan and execute multi-step tasks with access to tools, files, and shell commands.

Mindmap

mindmap
  root((Deep Agents))
    What it does
      Multi-step task planning
      Tool and file access
      Sub-agent delegation
    Key features
      Pre-built agent setup
      CLI interface
      Shell execution
      File system tools
    Use cases
      Automated assistants
      Coding helpers
      Complex workflows
    Tech stack
      Python
      LangGraph
      Language models
    Who uses it
      AI builders
      Automation engineers

Things people build with this

USE CASE 1

Build an automated assistant that reads files, runs commands, and completes tasks without human intervention.

USE CASE 2

Create a coding helper that plans multi-step refactoring or debugging tasks and executes them across your codebase.

USE CASE 3

Set up a CLI tool powered by AI that works like modern coding assistants but with your own language model.

USE CASE 4

Delegate complex workflows to sub-agents that work in parallel on different parts of a larger goal.

Tech stack

PythonTypeScriptLangGraphLanguage models

Getting it running

Difficulty · moderate Time to first run · 30min

Requires API key for language model service (OpenAI, Anthropic, etc.) to run agents.

Use freely for any purpose, including commercial use, as long as you keep the copyright notice.

In plain English

Deep Agents is a ready-to-use AI agent framework built by the LangChain team. An AI agent is a program that uses a language model to plan and carry out multi-step tasks, not just answering a single question, but breaking down a goal, taking actions (like reading files, running commands, searching the web), and working toward a result. The project solves the problem of setup friction: instead of building all the plumbing yourself, connecting a language model to tools, managing conversation history, handling long context windows, Deep Agents gives you a fully wired agent out of the box with one function call. It comes pre-equipped with planning tools (to-do tracking), file system access (read, write, edit files), shell command execution, and the ability to delegate subtasks to separate sub-agents. You would use Deep Agents when building an automated assistant, a coding helper, or any system where you want an AI to complete complex multi-step tasks with access to tools and the file system. It also ships with a command-line interface that works similarly to AI coding tools, powered by your choice of language model. The framework is written in Python (with a TypeScript version available separately), built on LangGraph, works with any language model that supports tool use, and is licensed under MIT.

Copy-paste prompts

Prompt 1
Show me how to set up a Deep Agents agent that can read and edit Python files in my project directory.
Prompt 2
How do I create a sub-agent in Deep Agents that handles a specific subtask while the main agent coordinates?
Prompt 3
Give me a working example of a Deep Agents CLI tool that uses Claude to plan and execute shell commands.
Prompt 4
How do I connect Deep Agents to my own language model API instead of using a default provider?
Prompt 5
Walk me through building an automated assistant with Deep Agents that can search files and summarize their contents.
Open on GitHub → Explain another repo

Generated 2026-05-18 · Model: sonnet-4-6 · Verify against the repo before relying on details.