LangChain Introduces Managed Deep Agents

ArticleVictor MoreiraAnnouncement

LangChain has announced Managed Deep Agents, an API-first hosted runtime in LangSmith designed for long-running AI agents. Developers can maintain agent configurations in their own repositories while LangSmith manages execution, state persistence, sandboxes, and context.

Key points

  1. Hosted runtime: Provides durable threads, run streaming, checkpointing, and human-in-the-loop workflows via the /v1/deepagents API.
  2. Deep Agents compatibility: Retains the open-source structure including AGENTS.md, skills/, subagents/, and tools.json.
  3. Persistent state with Context Hub: Offers managed storage for context, user preferences, and working notes across multiple runs.
  4. Automated improvements: LangSmith Engine can inspect execution traces to spot issues and update context files based on real usage.
  5. Tooling and sandboxes: Supports sandbox-backed execution for code execution, shell commands, and file manipulation.
  6. Release status: Initially launched in private beta for design partners, later updated to public beta availability.

Why it matters

Operating production-grade agents often requires significant custom infrastructure for state, observability, and sandboxed code execution. Managed Deep Agents removes this operational overhead by providing a fully managed runtime on top of LangSmith.

Analysis

LangChain targets a critical pain point in enterprise agent adoption: managing the operational lifecycle of long-horizon tasks. By keeping project files declarative and storing execution state within LangSmith, the offering combines the flexibility of an open-source harness with the reliability of managed cloud infrastructure.

Mentioned links

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Article:Jacob Talbot

    LangChain Unveils New Agent Infrastructure and Observability Tools at Interrupt

    At its Interrupt conference, LangChain announced a range of updates to LangSmith, including the autonomous LangSmith Engine, the trace-optimised SmithDB database, Managed Deep Agents, general availability for secure Sandboxes, Context Hub, an LLM Gateway, and updates to LangSmith Fleet.

    AI & LLMs· Announcement

  • Link:langchain.com

    LangChain and LangSmith: Platform for the AI Agent Lifecycle

    LangChain outlines its end-to-end platform for building, testing, deploying, and operating AI agents. Alongside open-source frameworks like LangGraph and Deep Agents, the offering features tools such as LangSmith Engine and an LLM Gateway for governance.

    AI & LLMs· Resource

  • Article:LangChain Inc.

    LangGraph: Low-Level Orchestration for Stateful AI Agents

    LangGraph by LangChain Inc. is an orchestration runtime designed for building and managing long-running, stateful AI agents. It enables developers to combine deterministic, hand-coded logic with LLM-driven steps within a single graph. Operating independently of the core LangChain library, LangGraph emphasises durable execution, state persistence, and human-in-the-loop controls.

    AI & LLMs· Resource

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.