maximem-synap-langchain 0.2.0

Synap memory integration for LangChain

maximem-synap-langchain

Synap memory integration for LangChain.

Install

pip install maximem-synap-langchain

Requires langchain-core>=0.3, maximem-synap>=0.2.0.

What's in the box

• SynapChatMessageHistory — BaseChatMessageHistory for use with RunnableWithMessageHistory. Persists conversation turns to Synap's short-term + long-term memory.
• SynapRetriever — BaseRetriever for RAG pipelines. Returns typed memory items (memories, entities, triples, chunks) via sdk.fetch.
• SynapSearchTool / SynapStoreTool — Agent tools for explicit memory read/write inside a tool-using LangChain agent.
• SynapCallbackHandler — Zero-config callback that auto-records LLM input/output as conversation turns.
• create_synap_node — Helper that builds a LangGraph-compatible node which injects retrieved Synap context into graph state.

Quickstart

from langchain_core.runnables.history import RunnableWithMessageHistory
from maximem_synap import MaximemSynapSDK
from synap_langchain import SynapChatMessageHistory

sdk = MaximemSynapSDK(api_key="sk-...")

def get_history(session_id: str) -> SynapChatMessageHistory:
    return SynapChatMessageHistory(sdk, user_id=session_id, customer_id="acme")

chain_with_memory = RunnableWithMessageHistory(
    chain,
    get_history,
    input_messages_key="input",
    history_messages_key="history",
)

License

Apache-2.0