Uploaded September 2026 | Updated November 2026, 1 day ago
Deep Agents is LangChain's open source harness for building complex agents. This short covers what the harness handles for you: controlling what context the agent sees and when, with built-in file systems, skills, subagents, and summarization. It also adds sandboxes for running untrusted code, human-in-the-loop gating on sensitive actions, and authorization checks before an agent acts. Every piece is swappable, so the same agent runs on your laptop, in a sandbox, or in the cloud without changing any code.
Deep Agents is LangChain's open source harness for building complex agents. This short covers what the harness handles for you: controlling what context the agent sees and when, with built-in file systems, skills, subagents, and summarization. It also adds sandboxes for running untrusted code, human-in-the-loop gating on sensitive actions, and authorization checks before an agent acts. Every piece is swappable, so the same agent runs on your laptop, in a sandbox, or in the cloud without changing any code.










