# Agentic memory service

> Agentic memory service - Learn when to use DataRobot's built-in chat history and REST integration
> versus the mem0-compatible memory API.

This Markdown file sits beside the HTML page at the same path (with a `.md` suffix). It summarizes the topic and lists links for tools and LLM context.

Companion generated at `2026-05-06T05:15:47.431720+00:00` (UTC).

## Primary page

- [Agentic memory service](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-memory-service.html): Full documentation for this topic (HTML).

## Related documentation

- [Agentic AI](https://docs.datarobot.com/en/docs/agentic-ai/index.html): Linked from this page.
- [Build](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/index.html): Linked from this page.
- [REST API](https://docs.datarobot.com/en/docs/api/reference/public-api/index.html): Linked from this page.
- [Python API client](https://docs.datarobot.com/en/docs/api/reference/sdk/index.html): Linked from this page.

## Documentation content

# Agentic memory service

> [!NOTE] Premium
> DataRobot's Agentic AI capabilities are a premium feature; contact your DataRobot representative for enablement information. Try this functionality for yourself in a limited capacity in the DataRobot trial experience.

The agentic memory surface in DataRobot exposes two different APIs that address different use cases. Choose the path that matches your build, then follow the documentation for that path. You do not need to merge the two in a single application.

If you need to persist and retrieve chat-style history (sessions, turns) through DataRobot's REST API and Python API client with a DataRobot model, use the chat history API described in the [Chat history API](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-memory-service.html#chat-history-api) section. Read the [REST API](https://docs.datarobot.com/en/docs/api/reference/public-api/index.html) and [Python API client](https://docs.datarobot.com/en/docs/api/reference/sdk/index.html) reference documentation for complete details.

If you are working with long-term, mem0-style memory (including migrating from the open-source mem0 stack), or you want examples and request shapes that match the mem0 product, use the [mem0 API](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-memory-service.html#mem0-api). For that interface, the canonical resource is the [mem0 documentation](https://docs.mem0.ai/).

**Chat history API:**
The chat history API is the DataRobot-integrated path: the same [REST API](https://docs.datarobot.com/en/docs/api/reference/public-api/index.html) you use for other DataRobot resources, with matching coverage in the [DataRobot Python API client](https://docs.datarobot.com/sdk/index).

Python API client: The Python API client adds dedicated types to make build-out straightforward:

datarobot.models.memory.MemorySpace
offers a basic CRUD for
memory spaces
(containers for stored conversation data).
datarobot.models.memory.Session
and
datarobot.models.memory.Event
work with
sessions
and
events
(for example, turns or messages) when you build chat-style agentic applications.

REST API: Use the REST API for these resources alongside the same authentication and base URL patterns as the rest of DataRobot's v2 API. Details appear in the [REST API](https://docs.datarobot.com/en/docs/api/reference/public-api/index.html) reference for the relevant operations and schemas.

Choose this path when you want a DataRobot chat history and session model aligned with the platform's API and Python package.

The chat history API is the DataRobot-integrated path: the same [REST API](https://docs.datarobot.com/en/docs/api/reference/public-api/index.html) you use for other DataRobot resources, with matching coverage in the [DataRobot Python API client](https://docs.datarobot.com/sdk/index).

Python API client: The Python API client adds dedicated types to make build-out straightforward:

datarobot.models.memory.MemorySpace
offers a basic CRUD for
memory spaces
(containers for stored conversation data).
datarobot.models.memory.Session
and
datarobot.models.memory.Event
work with
sessions
and
events
(for example, turns or messages) when you build chat-style agentic applications.

REST API: Use the REST API for these resources alongside the same authentication and base URL patterns as the rest of DataRobot's v2 API. Details appear in the [REST API](https://docs.datarobot.com/en/docs/api/reference/public-api/index.html) reference for the relevant operations and schemas.

Choose this path when you want a DataRobot chat history and session model aligned with the platform's API and Python package.

**mem0 API:**
DataRobot also offers a mem0-compatible HTTP API that is intended as a one-to-one match to the [open-source mem0](https://github.com/mem0ai/mem0) product's interface.

For conceptual overviews, endpoint behavior, and especially examples (including language- and framework-specific snippets), use the official mem0 documentation, which is maintained for that product.

Access the primary mem0 documentation at [https://docs.mem0.ai](https://docs.mem0.ai/) to learn request and response shapes, how to add and search memory, and how to integrate with common agent frameworks. Because the DataRobot service is built to be compatible with the same API surface, those guides apply with your DataRobot endpoint and authentication. Choose this path when you are targeting mem0's semantics and ecosystem, or porting an integration that was written against the open-source service.