langgraph dev）和本地 Docker 服务器（langgraph up）。它还描述了在与托管 Studio 前端交互时跟踪的数据。
CLI
LangGraph CLI 是用于构建和运行 LangGraph 应用程序的命令行界面；请参阅 CLI 指南以了解更多信息。 默认情况下，对大多数 CLI 命令的调用在调用时记录单个分析事件。这有助于我们更好地优先改进 CLI 体验。每个遥测事件包含调用进程的操作系统、操作系统版本、Python 版本、CLI 版本、命令名称（dev、up、run 等）以及表示是否向命令传递标志的布尔值。您可以在此处查看完整的分析逻辑。
您可以通过设置 LANGGRAPH_CLI_NO_ANALYTICS=1 来禁用所有 CLI 遥测。
Agent Server
The Agent Server provides a durable execution runtime that relies on persisting checkpoints of your application state, long-term memories, thread metadata, assistants, and similar resources to the local file system or a database. Unless you have deliberately customized the storage location, this information is either written to local disk (forlanggraph dev) or a PostgreSQL database (for langgraph up and in all deployments).
LangSmith Tracing
When running the Agent server (either in-memory or in Docker), LangSmith tracing may be enabled to facilitate faster debugging and offer observability of graph state and LLM prompts in production. You can always disable tracing by settingLANGSMITH_TRACING=false in your server’s runtime environment.
In-memory development server
langgraph dev runs an in-memory development server as a single Python process, designed for quick development and testing. It saves all checkpointing and memory data to disk within a .langgraph_api directory in the current working directory. Apart from the telemetry data described in the CLI section, no data leaves the machine unless you have enabled tracing or your graph code explicitly contacts an external service.
Standalone Server
langgraph up builds your local package into a Docker image and runs the server as the data plane consisting of three containers: the API server, a PostgreSQL container, and a Redis container. All persistent data (checkpoints, assistants, etc.) are stored in the PostgreSQL database. Redis is used as a pubsub connection for real-time streaming of events. You can encrypt all checkpoints before saving to the database by setting a valid LANGGRAPH_AES_KEY environment variable. You can also specify TTLs for checkpoints and cross-thread memories in langgraph.json to control how long data is stored. All persisted threads, memories, and other data can be deleted via the relevant API endpoints.
Additional API calls are made to confirm that the server has a valid license and to track the number of executed runs and tasks. Periodically, the API server validates the provided license key (or API key).
If you’ve disabled tracing, no user data is persisted externally unless your graph code explicitly contacts an external service.
Studio
Studio is a graphical interface for interacting with your Agent Server. It does not persist any private data (the data you send to your server is not sent to LangSmith). Though the Studio interface is served at smith.langchain.com, it is run in your browser and connects directly to your local Agent Server so that no data needs to be sent to LangSmith. If you are logged in, LangSmith does collect some usage analytics to help improve the debugging user experience. This includes:- Page visits and navigation patterns
- User actions (button clicks)
- Browser type and version
- Screen resolution and viewport size
Quick reference
In summary, you can opt-out of server-side telemetry by turning off CLI analytics and disabling tracing.| Variable | Purpose | Default |
|---|---|---|
LANGGRAPH_CLI_NO_ANALYTICS=1 | Disable CLI analytics | Analytics enabled |
LANGSMITH_API_KEY | Enable LangSmith tracing | Tracing disabled |
LANGSMITH_TRACING=false | Disable LangSmith tracing | Depends on environment |