mentedb-langchain

MenteDB integration for LangChain and LangGraph. Gives your agents persistent, cognitive memory that goes beyond simple vector retrieval.

Installation

pip install mentedb-langchain

Components

MenteDBMemory

A LangChain compatible memory backend that stores conversation context in MenteDB. Unlike buffer or summary memory, MenteDBMemory uses hybrid search (vector similarity, tag filtering, temporal decay) to assemble the most relevant context for each turn.

from mentedb_langchain import MenteDBMemory
from langchain.chains import ConversationChain
from langchain_openai import ChatOpenAI

memory = MenteDBMemory(
    data_dir="./agent-memory",
    agent_id="my-agent",
    token_budget=4096,
)

chain = ConversationChain(
    llm=ChatOpenAI(),
    memory=memory,
)

chain.predict(input="What database should I use for time series data?")
chain.predict(input="Tell me more about that recommendation")

MenteDBRetriever

A LangChain compatible retriever that uses MenteDB hybrid search. Supports optional tag filtering and agent scoping to narrow results.

from mentedb_langchain import MenteDBRetriever
from langchain.chains import RetrievalQA
from langchain_openai import ChatOpenAI

retriever = MenteDBRetriever(
    data_dir="./agent-memory",
    k=10,
    tags=["backend", "architecture"],
)

chain = RetrievalQA.from_chain_type(
    llm=ChatOpenAI(),
    retriever=retriever,
)

chain.invoke("What were the key decisions about our database migration?")

MenteDBChatHistory

Persistent chat history with cognitive tracking. MenteDB stores messages alongside reasoning trajectories, knowledge gaps, and contradiction signals so the agent's memory improves over time.

from mentedb_langchain import MenteDBChatHistory

history = MenteDBChatHistory(
    session_id="session-123",
    data_dir="./agent-memory",
)

history.add_user_message("What database should I use?")
history.add_ai_message("I recommend PostgreSQL for your use case.")

messages = history.messages

Usage with LangGraph

MenteDB works naturally with LangGraph. Use MenteDBMemory as a checkpointer or context source within graph nodes:

from mentedb_langchain import MenteDBMemory

memory = MenteDBMemory(data_dir="./graph-memory", agent_id="planner")

def plan_node(state):
    context = memory.load_memory_variables({"input": state["task"]})
    # Use context to inform planning
    return {**state, "context": context}

def reflect_node(state):
    memory.save_context(
        inputs={"input": state["task"]},
        outputs={"output": state["result"]},
    )
    return state

Configuration

All components accept data_dir to specify where MenteDB stores its data. For multi agent setups, use agent_id to isolate each agent's memory space.

Parameter	Default	Description
`data_dir`	`./mentedb-data`	Path to the MenteDB data directory
`agent_id`	`None`	Optional agent identifier for memory isolation
`token_budget`	`4096`	Maximum tokens for assembled context (MenteDBMemory)
`k`	`10`	Number of results to return (MenteDBRetriever)
`tags`	`None`	Tag filter for retrieval (MenteDBRetriever)

License

Apache 2.0

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mentedb_langchain-0.13.1.tar.gz (3.8 kB view details)

Uploaded Jul 15, 2026 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

mentedb_langchain-0.13.1-py3-none-any.whl (5.2 kB view details)

Uploaded Jul 15, 2026 Python 3

File details

Details for the file mentedb_langchain-0.13.1.tar.gz.

File metadata

Download URL: mentedb_langchain-0.13.1.tar.gz
Upload date: Jul 15, 2026
Size: 3.8 kB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for mentedb_langchain-0.13.1.tar.gz
Algorithm	Hash digest
SHA256	`674c3410328dc564174442b0ca2f62e84593e9108dca80b0467791475ed73607`
MD5	`77b7d33f1f8dd6b2e9f4aaf8603bf291`
BLAKE2b-256	`bbfc059d6f6ce05278ab0e9f5884b291a505fb4e5f23aea209016db26a4bef3e`

See more details on using hashes here.

Provenance

The following attestation bundles were made for mentedb_langchain-0.13.1.tar.gz:

Publisher: publish-sdks.yml on nambok/mentedb

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: mentedb_langchain-0.13.1.tar.gz
- Subject digest: 674c3410328dc564174442b0ca2f62e84593e9108dca80b0467791475ed73607
- Sigstore transparency entry: 2171742326
- Sigstore integration time: Jul 15, 2026
Source repository:
- Permalink: nambok/mentedb@5667ca979b701996857026647a42fac425bf6d8d
- Branch / Tag: refs/heads/main
- Owner: https://github.com/nambok
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish-sdks.yml@5667ca979b701996857026647a42fac425bf6d8d
- Trigger Event: workflow_dispatch