LangChain Launches Managed Deep Agents in Public Beta for One-Command Deployment
hwchase17 · x · 2026-08-08
LangChain has announced that its Managed Deep Agents is now in public beta. The service allows developers to scale agents from prototype to production without managing the underlying infrastructure.
Developers can author an agent in Python or TypeScript, test it locally, and deploy it to a managed runtime with a single command (mda deploy). LangSmith handles the runtime complexities, including persistence, memory mounts, skill loading, and sandbox lifecycle, allowing developers to focus on configuring the model, instructions, tools, and business logic.
Deep Agents itself serves as an open-source, model-agnostic agent harness. It integrates common patterns required for useful agents, such as tool calling, context management, subagent delegation, domain-specific skill loading, and human approval for sensitive actions, providing a reusable foundation for enterprises.
More from coding & agent
- Connected steps are not a workflow: nobody designs the handoff — usehive · 2026-10-16
- Making Blender animations with Opus, Astra and Argon: how you prompt still matters — chongdashu · 2026-10-16
- Running PolyStrata + Cline coding agent on a $0-fancy laptop at ~90 tok/s — rpwoerk · 2026-10-16
- How do you attribute agent gains: model training or infrastructure? — jrxna · 2026-10-16
- Feed Claude your books, blogs and top engineers' code for claude.md — 'it now writes better code than me' — blaizedsouza · 2026-10-16
- Open-source /label plugin auto-names and colors Claude Code sessions in one step — hermanschutte · 2026-10-16