Assemble production agent harnesses with DeepAgents

Use DeepAgents to build long-running task agents with a batteries-included harness for planning, tools, and workflow structure.

Prerequisites

DeepAgents, model provider credentials, workflow tools

Installation

Use the upstream install or setup path that matches your environment:

• uv add deepagents

Requirements and caveats from upstream:

• python
• The agent can plan, read/write files, and manage its own context. Add your own tools, swap models, customize prompts, configure sub-agents, and more. See the [documentation](https://docs.langchain.com/oss/python/deepa...

Basic usage or getting-started notes:

• Shell access — run commands in your sandbox of choice

• Human-in-the-loop — approve, edit, or reject tool calls before they run

• from deepagents import create_deep_agent

• Source: https://github.com/langchain-ai/deepagents

• Extracted from upstream docs: https://raw.githubusercontent.com/langchain-ai/deepagents/HEAD/README.md

Documentation

• https://github.com/langchain-ai/deepagents

Source

• Agent Skill Exchange