LangGraph Store Aerospike

Store LangGraph state and data in Aerospike using the provided AerospikeStore.

Installation

pip install -U langgraph-store-aerospike

Usage

Bring up Aerospike locally using prebuilt Aerospike Docker Image:

docker run -d --name aerospike -p 3000-3002:3000-3002 container.aerospike.com/aerospike/aerospike-server

Point the store at your cluster (Default):
- AEROSPIKE_HOST=127.0.0.1
- AEROSPIKE_PORT=3000
- AEROSPIKE_NAMESPACE=langgraph (default namespace for the store)
- AEROSPIKE_SET=store (default set name)
Compile a LangGraph graph with the store. Nodes reach it through get_store(), so the same long-term memory is shared across every run and every thread (unlike a checkpointer, which is scoped to a single thread):

from typing import TypedDict

import aerospike
from langgraph.config import get_store
from langgraph.graph import START, END, StateGraph

from langgraph.store.aerospike import AerospikeStore

# 1. Connect to Aerospike and build the store.
client = aerospike.client({"hosts": [("127.0.0.1", 3000)]}).connect()
store = AerospikeStore(client=client, namespace="test", set="langgraph_store")

# 2. Define a graph whose node reads and writes long-term memory.
class State(TypedDict):
    user_id: str
    food: str

def remember_preference(state: State) -> State:
    store = get_store()
    namespace = ("users", state["user_id"])

    # Persist something we learned about this user.
    store.put(namespace, key="profile", value={"favorite_food": state["food"]})

    # Read it back (would also be visible in any future run / thread).
    profile = store.get(namespace, key="profile")
    print(profile.value)  # {"favorite_food": "pizza"}
    return state

builder = StateGraph(State)
builder.add_node("remember_preference", remember_preference)
builder.add_edge(START, "remember_preference")
builder.add_edge("remember_preference", END)

# 3. Compile with the Aerospike store and run.
graph = builder.compile(store=store)
graph.invoke({"user_id": "user_123", "food": "pizza"})

The store is also a standalone BaseStore, so you can use it directly outside a graph for the same cross-thread memory:

# Search within a namespace prefix, filtering on stored fields.
results = store.search(("users",), filter={"favorite_food": "pizza"}, limit=10)

# Delete an item.
store.delete(("users", "user_123"), key="profile")

Download files

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

Source Distribution

langgraph_store_aerospike-0.3.0.tar.gz (19.6 kB view details)

Uploaded Jul 8, 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.

langgraph_store_aerospike-0.3.0-py3-none-any.whl (12.4 kB view details)

Uploaded Jul 8, 2026 Python 3

File details

Details for the file langgraph_store_aerospike-0.3.0.tar.gz.

File metadata

Download URL: langgraph_store_aerospike-0.3.0.tar.gz
Upload date: Jul 8, 2026
Size: 19.6 kB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.13

File hashes

Hashes for langgraph_store_aerospike-0.3.0.tar.gz
Algorithm	Hash digest
SHA256	`5a92b1daf172dab9ffa9e51f0ddfa5a81cfaa330d828debf2a19f72b8cb5df94`
MD5	`e19ef546c6340c8518d19ca8e59f9e01`
BLAKE2b-256	`2a5effb2ac1ea54b9f3c28ba6c42dbc32106f46c3f0f5949b44d77a0fff9f108`

See more details on using hashes here.

Provenance

The following attestation bundles were made for langgraph_store_aerospike-0.3.0.tar.gz:

Publisher: release-store.yml on aerospike/langgraph-aerospike

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: langgraph_store_aerospike-0.3.0.tar.gz
- Subject digest: 5a92b1daf172dab9ffa9e51f0ddfa5a81cfaa330d828debf2a19f72b8cb5df94
- Sigstore transparency entry: 2119010353
- Sigstore integration time: Jul 8, 2026
Source repository:
- Permalink: aerospike/langgraph-aerospike@baa8a58d9de991d5c08fa7148334bb93b43c02e7
- Branch / Tag: refs/tags/v0.3.0
- Owner: https://github.com/aerospike
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: release-store.yml@baa8a58d9de991d5c08fa7148334bb93b43c02e7
- Trigger Event: push