> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-5e9cc07a-preview-fjmorr-1781210627-2c9ae2d.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# LangSmith Deployment

> Deploy and manage agents with durable execution, real-time streaming, and horizontal scaling.

<div class="home-page mx-auto max-w-8xl px-0 lg:px-5" style={{ paddingBottom: "8rem" }}>
  <div class="mdx-content prose prose-gray dark:prose-invert mx-4 pt-10">
    # LangSmith Deployment

    LangSmith Deployment is a workflow orchestration runtime purpose-built for agent workloads. It provides the managed infrastructure agents need to run reliably in production at scale, supporting the full lifecycle from local development to deployment.

    ## Get started

    <Steps>
      <Step title="Create an account" icon="user-plus">
        Sign up at [smith.langchain.com](https://smith.langchain.com?utm_source=docs\&utm_medium=cta\&utm_campaign=langsmith-signup\&utm_content=snippets-langsmith-account-api-key-quickstart) (no credit card required).
        You can log in with **Google**, **GitHub**, or **email**.
      </Step>

      <Step title="Create an API key" icon="key">
        Go to your [Settings page](https://smith.langchain.com/settings) → **API Keys** → **Create API Key**.
        Copy the key and save it securely.
      </Step>

      <Step title="Choose your integration" icon="plug">
        LangSmith works with many frameworks and providers. Browse [available integrations](/langsmith/integrations) to connect your stack.
      </Step>
    </Steps>

    ## Deployable products

    LangSmith Deployment is framework-agnostic which means you can deploy agents built with:

    <CardGroup cols={2}>
      <Card title="Deep Agents" cta="Open quickstart" href="/langsmith/managed-deep-agents-overview" icon="robot">
        Create, run, and operate Managed Deep Agents through the private preview API.
      </Card>

      <Card title="LangGraph (and LangChain)" cta="Open quickstart" href="/langsmith/deployment-quickstart" icon="chart-dots-3">
        Use the LangGraph CLI and app templates to deploy a LangGraph application to LangSmith.
      </Card>

      <Card title="Google ADK" cta="View guide" href="/langsmith/deploy-google-adk" icon="google">
        Deploy Google Agent Development Kit (ADK) agent as a LangGraph with the `deployments-wrap-sdk` package.
      </Card>

      <Card title="Other frameworks" cta="View guide" href="/langsmith/deploy-other-frameworks" icon="packages">
        Use the LangGraph Functional API to deploy Strands, CrewAI, and other agent frameworks.
      </Card>
    </CardGroup>

    ## Deployment environments

    You can run the same [Agent Server](/langsmith/agent-server) runtime in several hosting models. A **standalone server** is the lightest option: you run containers yourself without the LangSmith [control plane](/langsmith/control-plane). For managed deployments through the UI and APIs, use **Cloud** or **Self-hosted** (full platform in your infrastructure).

    <CardGroup cols={3}>
      <Card title="Cloud" cta="View guide" href="/langsmith/deploy-to-cloud" icon="cloud">
        Fully managed by LangChain, running on AWS and GCP. Create deployments from GitHub in the LangSmith UI or with [`langgraph deploy`](/langsmith/cli#deploy). Requires a [Plus plan or above](https://www.langchain.com/pricing).
      </Card>

      <Card title="Standalone server" cta="View guide" href="/langsmith/deploy-standalone-server" icon="server">
        Deploy Agent Server with Docker, Compose, or Kubernetes. Bring your own PostgreSQL, Redis, and LangSmith license; no control plane. Optional [LangSmith tracing](/langsmith/observability) to Cloud or a self-hosted instance.
      </Card>

      <Card title="Self-hosted" cta="View guide" href="/langsmith/self-hosted" icon="buildings">
        Run the full LangSmith platform, including the control plane and data plane, in your cloud (for example on Kubernetes). Requires [Enterprise plan](https://www.langchain.com/pricing). Integrates observability, evaluation, and agent deployment in one private stack.
      </Card>
    </CardGroup>

    Same runtime, same APIs. What changes is who manages the infrastructure.
    For a feature-level comparison and infrastructure setup, see [Platform setup](/langsmith/platform-setup).

    ## Deployment capabilities

    Once an agent is deployed, you work with [Agent Server](/langsmith/assistants)’s execution model: **assistants** for configuration, **threads** for state, and **runs** for workloads.

    <CardGroup cols={2}>
      <Card title="Core capabilities" cta="Start building" href="/langsmith/streaming" icon="bolt">
        Stream to users, pause for human review, handle concurrent input, and connect via MCP and A2A.
      </Card>

      <Card title="Studio" cta="Develop with Studio" href="/langsmith/studio" icon="window">
        Use an interactive environment for developing and debugging agents.
      </Card>

      <Card title="Advanced configuration" cta="Configure your server" href="/langsmith/auth" icon="lock">
        Authentication, encryption, custom routes, and short- and long-term memory stores.
      </Card>

      <Card title="Agent composition" cta="Connect agents" href="/langsmith/use-remote-graph" icon="book">
        RemoteGraph lets any agent call other deployed agents with MCP and A2A.
      </Card>
    </CardGroup>

    <Card title="Find and fix failures with Engine" icon="https://mintcdn.com/langchain-5e9cc07a-preview-fjmorr-1781210627-2c9ae2d/ozNMha90F2BT6pPP/images/brand/engine-icon-no-bg-dark.svg?fit=max&auto=format&n=ozNMha90F2BT6pPP&q=85&s=c06a0be561614caa72864a6d1ccce960" href="/langsmith/engine-overview" arrow="true" width="63" height="63" data-path="images/brand/engine-icon-no-bg-dark.svg">
      Once agents are in production, use LangSmith Engine to detect recurring failures in their traces, diagnose root causes, and resolve them.
    </Card>

    ### Reference & operations

    #### Tutorials

    * [Collect user feedback for Agent Server runs](/langsmith/agent-server-feedback): Attach end-user feedback to runs and traces
    * [Deploy other frameworks (e.g., Strands, CrewAI)](/langsmith/deploy-other-frameworks): Wrap existing agents with Functional API and deploy
    * [Implement generative user interfaces with LangGraph](/langsmith/generative-ui-react): Stream UI elements to a React client
    * [Implement a CI/CD pipeline](/langsmith/cicd-pipeline-example): Automate tests, evaluations, and deployments with GitHub Actions

    #### Securing and customizing your server

    * [Custom auth](/langsmith/auth): Authentication and multi-tenant access control
    * [Server customization](/langsmith/custom-routes): Custom routes, [middleware](/langsmith/custom-middleware), [lifespan hooks](/langsmith/custom-lifespan), [encryption](/langsmith/encryption)

    #### Operations

    * [CI/CD pipelines](/langsmith/cicd-pipeline-example)
    * [TTL configuration](/langsmith/configure-ttl) for state and thread management
    * [Semantic search](/langsmith/semantic-search)
  </div>
</div>

***

<div className="source-links">
  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>

  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/langsmith/deployment.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>