Managed Deep Agents: the fastest way to ship a production deep agent
Managed Deep Agents is a hosted runtime for creating and operating deep agents, offering durable execution, streaming, memory, and context management. It integrates with LangSmith to store agent definitions and manage context retention, enabling agents to improve from real usage. The API allows programmatic creation, updating, and management of agents, with a private beta focusing on managed primitives for running deep agents in LangSmith. The runtime supports durable threads, streaming runs, and human-in-the-loop workflows, and is designed for long-term execution, tool access, and context preservation.
More from Langchain
Why managed agents are the next big thing in agent building
Managed Deep Agents gives developers a managed way to build, run, and deploy Deep Agents with built-in runtime, streaming, sandboxes, evals, memory, and auth.
langchain.com··Mads Kristian Nylund·AI InfrastructureAI-agents
LangSmith BYOC on AWS is generally available
LangSmith Bring Your Own Cloud is now generally available on AWS, giving Enterprise teams managed observability, evaluation, and deployment inside their own VPC.
langchain.com··Mads Kristian Nylund·AI DevelopmentAI InfrastructureAI Platforms
What is an AI agent?
Learn what AI agents are, how they work in an LLM loop, and where workflows fit so you can build reliable, production-ready autonomous systems.
langchain.com··Mads Kristian Nylund·AI DevelopmentAI InfrastructureAI-agents