LangGraph Platform is a runtime for deploying and managing long-running, stateful agent workflows in production. It provides APIs for execution, persistence, monitoring, and scaling of agent applications. Agents built with LangGraph or other frameworks can be hosted on the platform and exposed through managed endpoints. Choose from cloud, hybrid, or self-hosted deployments based on your infrastructure requirements. For more details, refer to the Deployment options page.

​
Quickstarts

Run a LangGraph app locally

Test and develop your app using the LangGraph server process locally.

Deploy to cloud

Run your app in a fully managed cloud deployment.

LangGraph Studio

Visualize, debug, and interact with agent workflows. Includes integrations with LangSmith for tracing and evaluation.

​
Features

Streaming Support

Stream token outputs and intermediate states back to the client in real time, reducing wait times during long operations.

Background Runs

Run agents asynchronously for long-duration tasks (minutes to hours), with monitoring via polling endpoints or webhooks.

Burst Handling

Use the built-in task queue to handle bursty request loads without data loss or service disruption.

Interrupt Handling

Manage overlapping or rapid user inputs (“double texting”) without breaking agent state.

Checkpointers & Memory

Persist agent state with built-in checkpointing and memory storage, removing the need for custom solutions.

Human-in-the-Loop

Insert human review or intervention into an agent run through dedicated APIs.