LangChain

Add Suprflo long-term memory to LangChain chains and agents. Ships in the Python SDK.

Install

pip install "suprflo[langchain]"

What you get

All three are built on the Python SDK MemoryClient:

• SuprfloMemory — a conversation memory that saves each turn to Suprflo and loads the relevant memories back into the prompt. Implements the classic LangChain memory interface (memory_variables, load_memory_variables, save_context, clear), compatible across langchain-core 0.2 → 1.x.
• SuprfloRetriever — a BaseRetriever that returns memories as documents for RAG / retrieval chains.
• create_memory_tools(client, user_id) — LangChain Tools (save_memory, search_memory) to drop into an agent.

Memory in a chain

from suprflo import MemoryClient
from suprflo.integrations.langchain import SuprfloMemory

client = MemoryClient(api_key="YOUR_API_KEY")
memory = SuprfloMemory(client=client, user_id="alice")

# use `memory` wherever a LangChain memory is accepted; it recalls Alice's
# stored facts on load and persists new turns on save.

Retriever for RAG

from suprflo.integrations.langchain import SuprfloRetriever

retriever = SuprfloRetriever(client=client, user_id="alice", top_k=5)
docs = retriever.invoke("dietary restrictions")

Tools for an agent

from suprflo.integrations.langchain import create_memory_tools

tools = create_memory_tools(client, user_id="alice")   # [save_memory, search_memory]
# add `tools` to your LangChain agent's toolset

If langchain-core isn't installed, importing this module raises a clear ImportError telling you to pip install "suprflo[langchain]".