Deep Agents: LangChain's open-source agent harness
According to the project README, Deep Agents is an open-source, opinionated agent harness for long-horizon, multi-step work. It includes sub-agents, filesystem access, context management, persistent memory, shell access, human-in-the-loop approval, skills and tools, while allowing components to be extended, overridden or replaced without forking. The project is model-agnostic and supports LLMs with tool calling, including frontier APIs, open-weight models and local models.
The README positions Deep Agents as a batteries-included harness that provides planning, delegation and context management out of the box. Its capability and production-readiness claims have not been independently evaluated in the supplied source.
The batteries-included agent harness.
https://docs.langchain.com/deepagents
The batteries-included agent harness.
Deep Agents is an open source agent harness — an opinionated agent that runs out of the box. Extend, override, or replace any piece.