langchain-ai/deepagents

Deep Agents is an agent harness. An opinionated, ready-to-run agent out of the box. Instead of wiring up 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 reading and writing context
• Shell access — execute for running commands (with sandboxing)
• Sub-agents — task for delegating work with isolated context windows
• Smart defaults — Prompts that teach the model how to use these tools effectively
• Context management — Auto-summarization when conversations get long, large outputs saved to files

[!NOTE] Looking for the JS/TS library? Check out deepagents.js.

Quickstart

1
2
3

pip install deepagents
# or
uv add deepagents

1
2
3
4

from deepagents import create_deep_agent

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

The agent can plan, read/write files, and manage its own context. Add tools, customize prompts, or swap models as needed.

[!TIP] For developing, debugging, and deploying AI agents and LLM applications, see LangSmith.

Customization

Add your own tools, swap models, customize prompts, configure sub-agents, and more. See the documentation for full details.

1
2
3
4
5
6
7

from langchain.chat_models import init_chat_model

agent = create_deep_agent(
    model=init_chat_model("openai:gpt-4o"),
    tools=[my_custom_tool],
    system_prompt="You are a research assistant.",
)

MCP is supported via langchain-mcp-adapters.

Deep Agents CLI

1

curl -LsSf https://raw.githubusercontent.com/langchain-ai/deepagents/main/libs/cli/scripts/install.sh | bash

Web search, remote sandboxes, persistent memory, human-in-the-loop approval, and more. See the CLI README for the full feature set.

LangGraph Native

create_deep_agent returns a compiled LangGraph graph. Use it with streaming, Studio, checkpointers, or any LangGraph feature.

FAQ

Why should I use this?

• 100% open source — MIT licensed, fully extensible
• Provider agnostic — Works with any Large Language Model that supports tool calling, including both frontier and open models
• Built on LangGraph — Production-ready runtime with streaming, persistence, and checkpointing
• Batteries included — Planning, file access, sub-agents, and context management work out of the box
• Get started in seconds — uv add deepagents and you have a working agent
• Customize in minutes — Add tools, swap models, tune prompts when you need to

Documentation

• docs.langchain.com – Comprehensive documentation, including conceptual overviews and guides
• reference.langchain.com/python – API reference docs for Deep Agents packages
• Chat LangChain – Chat with the LangChain documentation and get answers to your questions

Discussions: Visit the LangChain Forum to connect with the community and share all of your technical questions, ideas, and feedback.

Additional resources

• Examples — Working agents and patterns
• Contributing Guide – Learn how to contribute to LangChain projects and find good first issues.
• Code of Conduct – Our community guidelines and standards for participation.

Acknowledgements

This project was primarily inspired by Claude Code, and initially was largely an attempt to see what made Claude Code general purpose, and make it even more so.

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.