Skip to main content

Antfly memory for LangGraph

Persistent, namespaced long-term memory for LangGraph agents using Antfly. Supports sync/async operations, namespace enumeration, filtering and optional semantic search. Python 3.11 or newer. Apache-2.0 licensed.

Stable release: 0.1.0. Uses the matching stable langchain-antfly package and published antfly-sdk>=0.2.1,<0.3. Antfly 0.3.0-rc.5 is the tested server baseline. See the server setup.

Install

pip install langgraph-store-antfly==0.1.0

This installs the Python adapters and their dependencies. It does not install or start the Antfly server. Plain key/value memory needs no embedding model.

Remember a preference

import os

from antfly import AntflyClient
from langgraph_store_antfly import AntflyStore

with AntflyClient(
    base_url=os.environ["ANTFLY_URL"], token=os.getenv("ANTFLY_TOKEN")
) as client:
    # Create once for this example; on later runs, attach instead.
    store = AntflyStore.create(client=client, table="agent_preferences")
    store.put(("users", "alice"), "drink", {"value": "tea"})

    # A new instance reads the same persisted records.
    attached = AntflyStore(client=client, table="agent_preferences")
    print(attached.get(("users", "alice"), "drink").value)
    assert attached.get(("users", "bob"), "drink") is None

For cleanup, drop the example's dedicated table with client.drop_table("agent_preferences") inside the client context. Select namespaces from trusted application identity; namespaces separate records but do not replace server authorization. Client lifetimes belong to the caller.

Use inside an agent

Pass the store to LangChain's create_agent(store=...) and access it in tools through ToolRuntime.store. The two-user agent example demonstrates that composition with trusted user context and sync/async execution. Install the example's LangChain and chat-provider dependencies separately.

See the memory recipes for semantic indexing, search, and async operations, and the validation report for tested versions and restart/isolation evidence.

This is long-term memory storage. It does not implement a LangGraph execution checkpointer or per-item TTL.

Metadata

Release files for langgraph-store-antfly 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for langgraph-store-antfly 0.1.0
File Size Uploaded Provenance Actions
langgraph_store_antfly-0.1.0.tar.gz 12.8 kB With provenance Details for langgraph_store_antfly-0.1.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for langgraph-store-antfly 0.1.0
File Interpreter ABI Platform Actions
langgraph_store_antfly-0.1.0-py3-none-any.whl Python 3 none any Details for langgraph_store_antfly-0.1.0-py3-none-any.whl

Total release size: 26.8 kB

Release files / langgraph_store_antfly-0.1.0.tar.gz

Download URL langgraph_store_antfly-0.1.0.tar.gz
Size 12.8 kB
Tags Source
SHA-256 checksum
How to use checksums
ad5079a04dd4c3997f2208b00a6950f1594662cffef710cea9e608c2328c1422
BLAKE2b-256 checksum
How to use checksums
8fb9c75508ffc6f23aa114dca8678981133518220de99083ae2c7a9e76b7ceec
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 17, 2026.

Transparency log

Release files / langgraph_store_antfly-0.1.0-py3-none-any.whl

Download URL langgraph_store_antfly-0.1.0-py3-none-any.whl
Size 14.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
4da287f57538e53c54fbededf30e8e2f2ec46c23c1f9649208f120c52912e10e
BLAKE2b-256 checksum
How to use checksums
4a451883f036516080942eff52167200ad1ae580fcea47e6ce2314a54cf9493f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 17, 2026.

Transparency log

Security for langgraph-store-antfly 0.1.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for langgraph_store_antfly-0.1.0.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 17, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page