> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs-beta.getzep.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs-beta.getzep.com/_mcp/server.

# Get started with Zep

> Pick a Zep quickstart for enterprise context graphs, agent memory, or customer and account context.

Start with the information that the agent needs. Then identify who owns that context. Each row links to the solution overview and to a quickstart that builds the solution.

| Solution                                                  | Use it when                                                                               | Implementation path                                                                                                         | Quickstart                                                                                 |
| --------------------------------------------------------- | ----------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------ |
| [Enterprise context graphs](/enterprise-context-graphs)   | Agents need shared context about projects, products, operations, or a business domain.    | Create a Context Graph with `graph_id`, add business data and documents, then give an agent tools that search the graph.    | [Enterprise context graph quickstart](/give-your-agent-domain-knowledge)                   |
| [Agent memory](/agent-memory-solution)                    | An agent needs context from one user's previous conversations, activity, and changes.     | Create a user and threads, ingest messages and user business data, then retrieve with `thread.get_user_context`.            | [Agent memory quickstart](/quick-start-guide)                                              |
| [Customer and account context](/customer-account-context) | An agent needs personal context and shared customer or account records for the same task. | Keep personal data in a user graph, keep shared data in an account Context Graph, and combine authorized retrieval results. | [Customer and account context quickstart](/how-to-share-context-across-users-using-graphs) |

## Choose how the agent retrieves context

Each solution supports two retrieval models. Select the model from the task.

| Retrieval model         | User graph                                       | Shared Context Graph                                                   | Use it for                                                        |
| ----------------------- | ------------------------------------------------ | ---------------------------------------------------------------------- | ----------------------------------------------------------------- |
| One-call grounding      | [`thread.get_user_context`](/retrieving-context) | [`graph.search`](/searching-the-graph#auto-search) with `scope="auto"` | Low-latency grounding on each conversational turn                 |
| An agent with Zep tools | Tools that pin the `user_id`                     | Tools that pin the `graph_id`                                          | Complex questions and tasks that need several targeted retrievals |

To build an agent that plans its retrieval and uses Zep tools, see [Build an Agent with Zep](/build-an-agent-with-zep).

## Combine solutions when a task requires multiple scopes

An agent can retrieve from more than one authorized Context Graph. For example, a support agent can use:

* An account Context Graph for contracts, cases, and product history.
* A user graph for the current person's conversations and preferences.
* An enterprise Context Graph for support policies and runbooks.

Keep each data set in the graph that matches its subject and access boundary. Combine the retrieved context in the application.

## Next steps

* Use [Architecture patterns](/architecture-patterns) to select the graph, ingestion, and retrieval model.
* Use [Build an Agent with Zep](/build-an-agent-with-zep) to build an agent that plans its retrieval and uses Zep tools.
* Use [Working with Context](/working-with-context) to implement the ingest, shape, and retrieve lifecycle.
* Use [Governance](/governance) to control access and review activity.