The batteries-included agent harness
About LangChain Deep Agents
Deep Agents is LangChain's open-source agent harness, built on LangGraph, for long-running, multi-step work. It is available as Python and TypeScript libraries, with create_deep_agent as the main entry point.
It rests on three ideas. Planning uses a todo tool to break work into steps and track progress. A virtual filesystem acts as working memory, with tools to read, write, edit, list and search files, and pluggable backends. Subagents are spawned with isolated context windows through a task tool, and inherit the parent's tools by default. Beyond those, the documentation lists context management, including skills, memory, summarisation, context offloading and prompt caching, and human-in-the-loop checkpoints.
It is aimed at developers who want a ready harness for agents that work for a long time, rather than assembling planning, memory and delegation themselves.
Key features
- Open-source harness built on LangGraph
- Planning tool for tracking tasks
- Virtual filesystem as working memory
- Subagents with isolated context
- Skills, memory, summarisation and prompt caching
- Human-in-the-loop checkpoints
- Python and TypeScript
Links
More from LangChain
LangSmith provides tools for debugging, testing, evaluating, and monitoring LLM applications, integrating seamlessly with LangChain for comprehensive AI agent observability
Build resilient agents
The agent engineering platform
An Open-Source Asynchronous Coding Agent
Framework to build resilient language agents as graphs.
LangServe π¦οΈπ LangServe facilitates the deployment of LangChain runnables and chains as a REST API, providing features like automatic schema inference, efficient endpoints, and a playground page, with plans for a hosted version for one-click deployments
All content and agents from LangChain
Frequently asked questions about LangChain Deep Agents
- What is LangChain Deep Agents?
- The batteries-included agent harness. It is listed on botshub under agent orchestration and harnesses.
- Who makes LangChain Deep Agents?
- LangChain Deep Agents is made by LangChain, a company based in United States.
- Is LangChain Deep Agents free or open source?
- LangChain Deep Agents is tagged as open source on botshub. Check the official site for current terms.
- What can LangChain Deep Agents do?
- Key features include open-source harness built on LangGraph, planning tool for tracking tasks, virtual filesystem as working memory, subagents with isolated context and skills, memory, summarisation and prompt caching.
- What are alternatives to LangChain Deep Agents?
- Other agent orchestration and harnesses on botshub include Omnigent, OpenHuman, Hive and QM. See all alternatives to LangChain Deep Agents.
