Hi, I’d like to contribute a new library libs/checkpoint-qdrant/ that adds Qdrant as a backend for both the LangGraph checkpoint saver and the long-term memory store. Motivation: Qdrant is widely used in LangGraph-based apps for vector search. Users who already run Qdrant in their stack currently have to introduce a second database (Postgres or SQLite) just for checkpointing. Having a native Qdrant implementation removes that friction. Proposed API: QdrantSaver / AsyncQdrantSaver — checkpoint saver ( langgraph.checkpoint.qdrant ) QdrantStore / AsyncQdrantStore — memory store with optional vector similarity search, namespace filtering, and TTL ( langgraph.store.qdrant ) The implementation follows the same structure and semantics as checkpoint-postgres and checkpoint-sqlite . I have a working implementation ready with 40 tests passing (ruff + mypy clean, tested against both in-memory and real Docker Qdrant). Happy to open a PR as soon as this is approved. Let me know if you’d like me to adjust anything in the API design. Current implementation here: GitHub - gianlucaperna/langgraph at feat/checkpoint-qdrant · GitHub Thanks! 1 post - 1 participant Read full topic