langchain-ai/langgraph · error · InvalidNamespaceError

Root label for namespace cannot be "langgraph". Got

Error message

Root label for namespace cannot be "langgraph". Got: {namespace}

What it means

Reserved-name check at the end of _validate_namespace: the first (root) label of the namespace equals 'langgraph'. That root is reserved for LangGraph's own internal storage namespaces, so user data cannot be placed under it; the full offending namespace is echoed in the message.

Solutions

1. Choose a different root label, e.g. ('memories', user_id) or ('chat', thread_id)
2. Keep application-specific roots like 'docs', 'users', 'agent' instead of 'langgraph'
3. If you need cross-thread agent memory, use a dedicated root such as ('agent', agent_id)

When it happens

Trigger: Thrown at libs/checkpoint/langgraph/checkpoint/store/base/__init__.py:1281 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of langchain-ai/langgraph@38031739e5 (2026-08-26). Data as JSON: /api/errors/bafd60b05109dffe. Report an issue: GitHub.

Appendix: source

Thrown at libs/checkpoint/langgraph/checkpoint/store/base/__init__.py:1281

    if namespace[0] == "langgraph":
        raise InvalidNamespaceError(
            f'Root label for namespace cannot be "langgraph". Got: {namespace}'
        )

View on GitHub (pinned to 38031739e5)