Deployment

import DeployPy from '/snippets/oss/deploy-py.mdx'; import DeployJs from '/snippets/oss/deploy-js.mdx'; import DeployFrameworksPlatformsReference from '/snippets/langsmith/deploy-frameworks-platforms-reference.mdx';

When you are ready to deploy your LangChain agent to production, choose a hosting model that fits your stack. LangSmith Cloud provides fully managed infrastructure for stateful, long-running agents with persistent state and background execution.

LangSmith offers multiple deployment options beyond Cloud, including hybrid, standalone servers, and self-hosted with control plane. For more information, see the LangSmith Deployment overview.

LangSmith Cloud

This section walks through deploying your agent to LangSmith Cloud from a GitHub repository. LangSmith handles infrastructure, scaling, and operational concerns.

Prerequisites

Before you begin, ensure you have the following:

A GitHub account (opens in a new tab)
A LangSmith account (opens in a new tab) (free to sign up)

Deploy your agent

1. Create a repository on GitHub

Your application's code must reside in a GitHub repository to be deployed on LangSmith. Both public and private repositories are supported. For this quickstart, first make sure your app is LangGraph-compatible by following the local server setup guide (opens in a new tab). Then, push your code to the repository.

Build a data analysis agent from scratch Event streaming