## TL;DR

Create your checkpointer once at startup and reuse it across requests, never inside a per-request object. If memory must survive restarts or multiple processes, use a persistent checkpointer such as the sqlite or postgres saver instead of MemorySaver. Keep passing the same thread_id in config on every invoke, because persistence is keyed on it, and verify with a two-turn test: tell the agent your name, then ask it back in a fresh call.

## Fix

Create your checkpointer once at startup and reuse it across requests, never inside a per-request object. If memory must survive restarts or multiple processes, use a persistent checkpointer such as the sqlite or postgres saver instead of MemorySaver. Keep passing the same thread_id in config on every invoke, because persistence is keyed on it, and verify with a two-turn test: tell the agent your name, then ask it back in a fresh call.

Context: GitHub issue langchain-ai/langgraph#2146 documents why thread memory silently vanishes. The reporter compiled with MemorySaver and passed a thread_id, but the agent still forgot everything between calls. The maintainer's answer: MemorySaver is an in-memory checkpointer, so re-instantiating the wrapper class on every request wipes all stored thread state. The fix is creating the checkpointer once outside the request-scoped class, or switching to a checkpointer that writes to a file or database like the sqlite or postgres variants.

## Matched source
Source: Published skill
Original query: "LangGraph MemorySaver is in-memory, so recreating it per request wipes thread state"
Key terms: langgraph, memory, memorysaver, recreating, request, state, thread, wipes

## When to use this

- Use this when your task, error, or question matches the title above and the setup in the Fix section.

## When not to use this

- Skip it when the error text, tool, or situation is different. Forcing a mismatched fix usually costs more time than searching again.

## Compatibility

The original write-up does not pin tool versions. Treat the commands and UI paths above as reflecting the author's setup, and check your tool's own docs if your version looks different.

---

## Vectle citations

- Exact version: <https://vectle.com/skills/skl_XZFCT_irJfiUULgdVVgI_A/versions/skv_XfK0KM1snl-Z_TRqGGcrMQ>
- Canonical HTML skill page: <https://vectle.com/skills/skl_XZFCT_irJfiUULgdVVgI_A>
- Current Markdown URL: <https://vectle.com/skills/skl_XZFCT_irJfiUULgdVVgI_A/markdown>

## Selected public attribution and original notices/references

```json
{
  "author": "issueatlas",
  "client": null,
  "notices_and_references": [
    "https://github.com/langchain-ai/langgraph/issues/2146"
  ]
}
```