redis-agent-memory

Developer-friendly & type-safe Python SDK specifically catered to leverage redis-agent-memory API.

Summary

Redis Agent Memory API: API for storing, retrieving, and searching Redis Agent Memory session memory and long-term memory.

Authentication depends on your deployment. Use the credential issued for your Agent Memory service or store. For self-managed deployments, see the self-managed Agent Memory guide for authentication options.

For more information about the API: Redis Agent Memory documentation

Documentation

• Developer guide
• Python SDK quickstart
• REST API reference (HTTP endpoints and schemas, not Python method pages)
• REST API quickstart

Recent changes

Namespace resources (since 0.4.0). Create and manage namespaces with list_namespaces, create_namespace, get_namespace, update_namespace, and delete_namespace. Bind a session or long-term memory to a namespace resource with namespace_ref.

Legacy namespace labels. The flat namespace string is deprecated. It does not create or resolve a namespace resource. Do not send it together with namespace_ref. New integrations should use namespace resources.

HTTP 424. When a memory or model-provider dependency cannot complete the request, the SDK raises MemoryFailedDependencyErrorResponseContent. FailedDependencyErrorResponseContent still represents other 424 failed-dependency errors.

SDK Installation

The SDK can be installed with uv, pip, or poetry package managers.

uv

uv is a fast Python package installer and resolver, designed as a drop-in replacement for pip and pip-tools. It's recommended for its speed and modern Python tooling capabilities.

uv add redis-agent-memory

PIP

PIP is the default package installer for Python, enabling easy installation and management of packages from PyPI via the command line.

pip install redis-agent-memory

Poetry

Poetry is a modern tool that simplifies dependency management and package publishing by using a single pyproject.toml file to handle project metadata and dependencies.

poetry add redis-agent-memory

Shell and script usage with uv

You can use this SDK in a Python shell with uv and the uvx command that comes with it like so:

uvx --from redis-agent-memory python

It's also possible to write a standalone Python script without needing to set up a whole project like so:

#!/usr/bin/env -S uv run --script
# /// script
# requires-python = ">=3.10"
# dependencies = [
#     "redis-agent-memory",
# ]
# ///

from redis_agent_memory import AgentMemory

sdk = AgentMemory(
  # SDK arguments
)

# Rest of script here...

Once that is saved to a file, you can run it with uv run script.py where script.py can be replaced with the actual file name.

IDE Support

PyCharm

Generally, the SDK will work well with most IDEs out of the box. However, when using PyCharm, you can enjoy much better integration with Pydantic by installing an additional plugin.

• PyCharm Pydantic Plugin

SDK Example Usage

Create a namespace

Create a shared root namespace. Replace ns-product in the following examples with the returned namespace ID.

# Synchronous Example
from redis_agent_memory import AgentMemory, models


with AgentMemory(
    "https://api.example.com",
    store_id="<id>",
    api_key="<AGENT_MEMORY_API_KEY>",
) as agent_memory:

    res = agent_memory.create_namespace(request={
        "name": "product",
        "scope": models.NamespaceScope.SHARED,
    })

    # Handle response
    print(res)

The same SDK client can also be used to make asynchronous requests by importing asyncio.

# Asynchronous Example
import asyncio
from redis_agent_memory import AgentMemory, models

async def main():

    async with AgentMemory(
        "https://api.example.com",
        store_id="<id>",
        api_key="<AGENT_MEMORY_API_KEY>",
    ) as agent_memory:

        res = await agent_memory.create_namespace_async(request={
            "name": "product",
            "scope": models.NamespaceScope.SHARED,
        })

        # Handle response
        print(res)

asyncio.run(main())

Add a session event

Append a chat turn. The server extracts long-term memory from the session asynchronously. Optionally bind the session with namespaceRef so extracted memories land in that namespace.

# Synchronous Example
from redis_agent_memory import AgentMemory, models
from redis_agent_memory.utils import parse_datetime


with AgentMemory(
    "https://api.example.com",
    store_id="<id>",
    api_key="<AGENT_MEMORY_API_KEY>",
) as agent_memory:

    res = agent_memory.add_session_event(actor_id="user-42", role=models.MessageRole.USER, content=[
        {
            "text": "What were the action items from last week's meeting?",
        },
    ], created_at=parse_datetime("2024-03-15T10:00:00Z"), session_id="session-user42-20240315", namespace_ref={
        "namespace_id": "ns-product",
    })

    # Handle response
    print(res)

The same SDK client can also be used to make asynchronous requests by importing asyncio.

# Asynchronous Example
import asyncio
from redis_agent_memory import AgentMemory, models
from redis_agent_memory.utils import parse_datetime

async def main():

    async with AgentMemory(
        "https://api.example.com",
        store_id="<id>",
        api_key="<AGENT_MEMORY_API_KEY>",
    ) as agent_memory:

        res = await agent_memory.add_session_event_async(actor_id="user-42", role=models.MessageRole.USER, content=[
            {
                "text": "What were the action items from last week's meeting?",
            },
        ], created_at=parse_datetime("2024-03-15T10:00:00Z"), session_id="session-user42-20240315", namespace_ref={
            "namespace_id": "ns-product",
        })

        # Handle response
        print(res)

asyncio.run(main())

Get session memory

Read the conversation for a session -- this should contain the messages you added:

# Synchronous Example
from redis_agent_memory import AgentMemory


with AgentMemory(
    "https://api.example.com",
    store_id="<id>",
    api_key="<AGENT_MEMORY_API_KEY>",
) as agent_memory:

    res = agent_memory.get_session_memory(session_id="session-user42-20240315")

    # Handle response
    print(res)

The same SDK client can also be used to make asynchronous requests by importing asyncio.

# Asynchronous Example
import asyncio
from redis_agent_memory import AgentMemory

async def main():

    async with AgentMemory(
        "https://api.example.com",
        store_id="<id>",
        api_key="<AGENT_MEMORY_API_KEY>",
    ) as agent_memory:

        res = await agent_memory.get_session_memory_async(session_id="session-user42-20240315")

        # Handle response
        print(res)

asyncio.run(main())

Search long-term memory

Search long-term memory the server extracted or you created manually. In this example, we limit the search to the namespace identified by namespaceRef.

# Synchronous Example
from redis_agent_memory import AgentMemory


with AgentMemory(
    "https://api.example.com",
    store_id="<id>",
    api_key="<AGENT_MEMORY_API_KEY>",
) as agent_memory:

    res = agent_memory.search_long_term_memory(request={
        "text": "preferred theme",
        "filter_": {
            "namespace_ref": {
                "eq": "ns-product",
            },
        },
    })

    # Handle response
    print(res)

The same SDK client can also be used to make asynchronous requests by importing asyncio.

# Asynchronous Example
import asyncio
from redis_agent_memory import AgentMemory

async def main():

    async with AgentMemory(
        "https://api.example.com",
        store_id="<id>",
        api_key="<AGENT_MEMORY_API_KEY>",
    ) as agent_memory:

        res = await agent_memory.search_long_term_memory_async(request={
            "text": "preferred theme",
            "filter_": {
                "namespace_ref": {
                    "eq": "ns-product",
                },
            },
        })

        # Handle response
        print(res)

asyncio.run(main())

Create long-term memories

Optionally write long-term memories yourself instead of waiting for extraction.

# Synchronous Example
from redis_agent_memory import AgentMemory


with AgentMemory(
    "https://api.example.com",
    store_id="<id>",
    api_key="<AGENT_MEMORY_API_KEY>",
) as agent_memory:

    res = agent_memory.bulk_create_long_term_memories(memories=[
        {
            "id": "mem-1",
            "text": "The user prefers dark mode",
            "owner_id": "user-1",
            "namespace_ref": {
                "namespace_id": "ns-product",
            },
        },
    ])

    # Handle response
    print(res)

The same SDK client can also be used to make asynchronous requests by importing asyncio.

# Asynchronous Example
import asyncio
from redis_agent_memory import AgentMemory

async def main():

    async with AgentMemory(
        "https://api.example.com",
        store_id="<id>",
        api_key="<AGENT_MEMORY_API_KEY>",
    ) as agent_memory:

        res = await agent_memory.bulk_create_long_term_memories_async(memories=[
            {
                "id": "mem-1",
                "text": "The user prefers dark mode",
                "owner_id": "user-1",
                "namespace_ref": {
                    "namespace_id": "ns-product",
                },
            },
        ])

        # Handle response
        print(res)

asyncio.run(main())

Move long-term memories

Optionally move existing memories into a namespace.

# Synchronous Example
from redis_agent_memory import AgentMemory


with AgentMemory(
    "https://api.example.com",
    store_id="<id>",
    api_key="<AGENT_MEMORY_API_KEY>",
) as agent_memory:

    res = agent_memory.move_long_term_memories(memory_ids=[
        "mem-1",
    ], namespace_ref={
        "namespace_id": "ns-product",
    })

    # Handle response
    print(res)

The same SDK client can also be used to make asynchronous requests by importing asyncio.

# Asynchronous Example
import asyncio
from redis_agent_memory import AgentMemory

async def main():

    async with AgentMemory(
        "https://api.example.com",
        store_id="<id>",
        api_key="<AGENT_MEMORY_API_KEY>",
    ) as agent_memory:

        res = await agent_memory.move_long_term_memories_async(memory_ids=[
            "mem-1",
        ], namespace_ref={
            "namespace_id": "ns-product",
        })

        # Handle response
        print(res)

asyncio.run(main())

Authentication

Per-Client Security Schemes

This SDK supports the following security scheme globally:

Name	Type	Scheme	Environment Variable
api_key	http	HTTP Bearer	AGENT_MEMORY_API_KEY

To authenticate with the API the api_key parameter must be set when initializing the SDK client instance. For example:

from redis_agent_memory import AgentMemory


with AgentMemory(
    "https://api.example.com",
    api_key="<AGENT_MEMORY_API_KEY>",
) as agent_memory:

    res = agent_memory.health()

    # Handle response
    print(res)

Available Resources and Operations

Available methods

AgentMemory SDK

• health - Return information about the operational status of the service.
• store_health - Returns read-only health for applicable store-scoped RAM features.
• bulk_delete_long_term_memories - Deletes long-term memories in bulk by their IDs.
• bulk_create_long_term_memories - Creates long-term memories in bulk.
• move_long_term_memories - Moves long-term memories to one existing namespace resource. Returns 409 when the destination namespace is archived.
• search_long_term_memory - Runs a semantic search on long-term memory with filtering options.
• get_long_term_memory - Returns a long-term memory by its ID.
• update_long_term_memory - Partially updates a long-term memory by its ID.
• update_long_term_memory_fields - Atomically updates a custom-typed long-term memory's text and/or attributes, scoped to the caller's bound memory type. Used by the custom-extraction worker.
• list_namespaces - Lists namespace roots or direct children.
• create_namespace - Creates a namespace resource as a root, direct child, or explicit hierarchy path. Returns 409 when an active or archived namespace already occupies the requested location.
• delete_namespace - Deletes an empty leaf namespace. Returns 409 when the namespace has children or memory placements, or when it changed concurrently.
• get_namespace - Gets one namespace by its canonical ID.
• update_namespace - Renames or archives a namespace. Returns 409 when the namespace changed concurrently, an active or archived sibling already uses the requested name, or the namespace is archived.
• list_sessions - Returns a paginated list of session IDs for a store.
• add_session_event - Appends a single event to a session. Creates the session if it does not exist. If sessionId is omitted, the server generates one.
• delete_session_memory - Deletes the session memory for a session.
• get_session_memory - Returns the session memory for a session.
• delete_session_event - Deletes a single event from a session by event ID.
• get_session_event - Returns a single event from a session by event ID.

Global Parameters

A parameter is configured globally. This parameter may be set on the SDK client instance itself during initialization. When configured as an option during SDK initialization, This global value will be used as the default on the operations that use it. When such operations are called, there is a place in each to override the global value, if needed.

For example, you can set storeId to "<id>" at SDK initialization and then you do not have to pass the same value on calls to operations like store_health. But if you want to do so you may, which will locally override the global setting. See the example code below for a demonstration.

Available Globals

The following global parameter is available. Global parameters can also be set via environment variable.

Name	Type	Description	Environment
store_id	str	The store_id parameter.	AGENT_MEMORY_STORE_ID

Example

from redis_agent_memory import AgentMemory


with AgentMemory(
    "https://api.example.com",
    store_id="<id>",
    api_key="<AGENT_MEMORY_API_KEY>",
) as agent_memory:

    res = agent_memory.store_health()

    # Handle response
    print(res)

Retries

Some of the endpoints in this SDK support retries. If you use the SDK without any configuration, it will fall back to the default retry strategy provided by the API. However, the default retry strategy can be overridden on a per-operation basis, or across the entire SDK.

To change the default retry strategy for a single API call, simply provide a RetryConfig object to the call:

from redis_agent_memory import AgentMemory
from redis_agent_memory.utils import BackoffStrategy, RetryConfig


with AgentMemory(
    "https://api.example.com",
    api_key="<AGENT_MEMORY_API_KEY>",
) as agent_memory:

    res = agent_memory.health(,
        RetryConfig("backoff", BackoffStrategy(1, 50, 1.1, 100), False))

    # Handle response
    print(res)

If you'd like to override the default retry strategy for all operations that support retries, you can use the retry_config optional parameter when initializing the SDK:

from redis_agent_memory import AgentMemory
from redis_agent_memory.utils import BackoffStrategy, RetryConfig


with AgentMemory(
    "https://api.example.com",
    retry_config=RetryConfig("backoff", BackoffStrategy(1, 50, 1.1, 100), False),
    api_key="<AGENT_MEMORY_API_KEY>",
) as agent_memory:

    res = agent_memory.health()

    # Handle response
    print(res)

Error Handling

AgentMemoryError is the base class for all HTTP error responses. It has the following properties:

Property	Type	Description
err.message	str	Error message
err.status_code	int	HTTP response status code eg 404
err.headers	httpx.Headers	HTTP response headers
err.body	str	HTTP body. Can be empty string if no body is returned.
err.raw_response	httpx.Response	Raw HTTP response
err.data		Optional. Some errors may contain structured data. See Error Classes.

Example

from redis_agent_memory import AgentMemory, errors


with AgentMemory(
    "https://api.example.com",
    store_id="<id>",
    api_key="<AGENT_MEMORY_API_KEY>",
) as agent_memory:
    res = None
    try:

        res = agent_memory.store_health()

        # Handle response
        print(res)


    except errors.AgentMemoryError as e:
        # The base class for HTTP error responses
        print(e.message)
        print(e.status_code)
        print(e.body)
        print(e.headers)
        print(e.raw_response)

        # Depending on the method different errors may be thrown
        if isinstance(e, errors.BadRequestErrorResponseContent):
            print(e.data.title)  # str
            print(e.data.status)  # Optional[int]
            print(e.data.detail)  # Optional[str]
            print(e.data.instance)  # Optional[str]
            print(e.data.type)  # models.BadRequestErrorType

Error Classes

Primary errors:

• AgentMemoryError: The base class for HTTP error responses.
  • BadRequestErrorResponseContent: Request validation or input decoding failed. Status code 400. *
  • AuthenticationErrorResponseContent: Authentication credentials are missing, malformed, or invalid. Status code 401. *
  • ForbiddenErrorResponseContent: The caller is authenticated but not allowed to access the requested resource. Status code 403. *
  • NotFoundErrorResponseContent: The requested resource does not exist. Status code 404. *
  • TimeoutErrorResponseContent: The request timed out before the service could complete it. Status code 408. *
  • ResourceSuspendedErrorResponseContent: The requested resource exists but is suspended by an administrator. Status code 423. *
  • TooManyRequestsErrorResponseContent: The service rejected the request because rate limits were exceeded. Status code 429. *
  • UnexpectedErrorResponseContent: The service failed with an unexpected internal error. Status code 500. *
  • PayloadTooLargeErrorResponseContent: The request payload exceeds the maximum supported size. Status code 413. *

Less common errors (8)

Network errors:

• httpx.RequestError: Base class for request errors.
  • httpx.ConnectError: HTTP client was unable to make a request to a server.
  • httpx.TimeoutException: HTTP request timed out.

Inherit from AgentMemoryError:

• FailedDependencyErrorResponseContent: A dependent resource required to process the request is unavailable or unhealthy. Status code 424. Applicable to 15 of 20 methods.*
• ConflictErrorResponseContent: The request conflicts with the current state of the resource. Status code 409. Applicable to 4 of 20 methods.*
• MemoryFailedDependencyErrorResponseContent: A resource or model-provider dependency required by Agent Memory could not complete the request. Status code 424. Applicable to 4 of 20 methods.*
• ResponseValidationError: Type mismatch between the response data and the expected Pydantic model. Provides access to the Pydantic validation error via the cause attribute.

* Check the method documentation to see if the error is applicable.

Custom HTTP Client

The Python SDK makes API calls using the httpx HTTP library. In order to provide a convenient way to configure timeouts, cookies, proxies, custom headers, and other low-level configuration, you can initialize the SDK client with your own HTTP client instance. Depending on whether you are using the sync or async version of the SDK, you can pass an instance of HttpClient or AsyncHttpClient respectively, which are Protocol's ensuring that the client has the necessary methods to make API calls. This allows you to wrap the client with your own custom logic, such as adding custom headers, logging, or error handling, or you can just pass an instance of httpx.Client or httpx.AsyncClient directly.

For example, you could specify a header for every request that this sdk makes as follows:

from redis_agent_memory import AgentMemory
import httpx

http_client = httpx.Client(headers={"x-custom-header": "someValue"})
s = AgentMemory(client=http_client)

or you could wrap the client with your own custom logic:

from redis_agent_memory import AgentMemory
from redis_agent_memory.httpclient import AsyncHttpClient
import httpx

class CustomClient(AsyncHttpClient):
    client: AsyncHttpClient

    def __init__(self, client: AsyncHttpClient):
        self.client = client

    async def send(
        self,
        request: httpx.Request,
        *,
        stream: bool = False,
        auth: Union[
            httpx._types.AuthTypes, httpx._client.UseClientDefault, None
        ] = httpx.USE_CLIENT_DEFAULT,
        follow_redirects: Union[
            bool, httpx._client.UseClientDefault
        ] = httpx.USE_CLIENT_DEFAULT,
    ) -> httpx.Response:
        request.headers["Client-Level-Header"] = "added by client"

        return await self.client.send(
            request, stream=stream, auth=auth, follow_redirects=follow_redirects
        )

    def build_request(
        self,
        method: str,
        url: httpx._types.URLTypes,
        *,
        content: Optional[httpx._types.RequestContent] = None,
        data: Optional[httpx._types.RequestData] = None,
        files: Optional[httpx._types.RequestFiles] = None,
        json: Optional[Any] = None,
        params: Optional[httpx._types.QueryParamTypes] = None,
        headers: Optional[httpx._types.HeaderTypes] = None,
        cookies: Optional[httpx._types.CookieTypes] = None,
        timeout: Union[
            httpx._types.TimeoutTypes, httpx._client.UseClientDefault
        ] = httpx.USE_CLIENT_DEFAULT,
        extensions: Optional[httpx._types.RequestExtensions] = None,
    ) -> httpx.Request:
        return self.client.build_request(
            method,
            url,
            content=content,
            data=data,
            files=files,
            json=json,
            params=params,
            headers=headers,
            cookies=cookies,
            timeout=timeout,
            extensions=extensions,
        )

s = AgentMemory(async_client=CustomClient(httpx.AsyncClient()))

httpx2 (Pydantic's httpx fork)

httpx2 is Pydantic's maintained fork of httpx. To run this SDK on httpx2, call alias_httpx() at your program's entry point, before importing the SDK, so every import httpx — including the ones inside the SDK — resolves to httpx2:

import httpx2

httpx2.alias_httpx()

from redis_agent_memory import AgentMemory

s = AgentMemory()

An SDK can also be generated against httpx2 directly, so it depends on the fork instead of httpx, by setting python.httpClientLibrary: httpx2 in gen.yaml.

Resource Management

The AgentMemory class implements the context manager protocol and registers a finalizer function to close the underlying sync and async HTTPX clients it uses under the hood. This will close HTTP connections, release memory and free up other resources held by the SDK. In short-lived Python programs and notebooks that make a few SDK method calls, resource management may not be a concern. However, in longer-lived programs, it is beneficial to create a single SDK instance via a context manager and reuse it across the application.

from redis_agent_memory import AgentMemory
def main():

    with AgentMemory(
        "https://api.example.com",
        store_id="<id>",
        api_key="<AGENT_MEMORY_API_KEY>",
    ) as agent_memory:
        # Rest of application here...


# Or when using async:
async def amain():

    async with AgentMemory(
        "https://api.example.com",
        store_id="<id>",
        api_key="<AGENT_MEMORY_API_KEY>",
    ) as agent_memory:
        # Rest of application here...

Debugging

You can setup your SDK to emit debug logs for SDK requests and responses.

You can pass your own logger class directly into your SDK.

from redis_agent_memory import AgentMemory
import logging

logging.basicConfig(level=logging.DEBUG)
s = AgentMemory(server_url="https://example.com", debug_logger=logging.getLogger("redis_agent_memory"))

You can also enable a default debug logger by setting an environment variable AGENT_MEMORY_DEBUG to true.

Development

Maturity

This SDK is in beta, and there may be breaking changes between versions without a major version update. Therefore, we recommend pinning usage to a specific package version. This way, you can install the same version each time without breaking changes unless you are intentionally looking for the latest version.

Contributions

While we value open-source contributions to this SDK, this library is generated programmatically. Any manual changes added to internal files will be overwritten on the next generation. We look forward to hearing your feedback. Feel free to open a PR or an issue with a proof of concept and we'll do our best to include it in a future release.