# Zep Documentation

> Zep is the unified context layer for enterprise data. It combines business data, documents, and conversations into shared, governed context for agents.

Documentation

# Zep Documentation

Zep is the unified context layer for enterprise data. It combines business data, documents, and conversations into shared, governed context that agents can retrieve.

Zep organizes this context in temporal Context Graphs. The [Context Lake](/context-lake) manages and serves millions of these graphs as one system on Konig, Zep's graph database service.

New

Build with Zep in Claude Code and Codex

A skill plus the Zep docs MCP server, in one plugin.

[Get the plugin →](/implement-zep-with-agents)

## Get started

#### [Quickstarts](/use-cases)

Pick the quickstart for your agent's task: domain knowledge, agent memory, or customer and account context.

#### [Agent frameworks](/memory-for-agent-frameworks)

Add Zep context and agent memory to supported orchestration frameworks.

#### [Cookbooks](/advanced-context-block-construction)

Practical recipes and patterns for common use cases with Zep.

#### [SDK Reference](/sdk-reference)

API reference for Zep's Python, TypeScript, and Go SDKs.

#### [Governance](/governance)

Control access to context, trace graph data to its sources, and review dashboard and API activity.

#### [Graphiti](/graphiti/getting-started/overview)

Graphiti is Zep's open-source framework for temporal knowledge graphs.

> Build agents with unified, governed enterprise context

## Instructions for AI Agents

- For clean Markdown of any page, append `.md` to the page URL
- For section-specific indexes, append `/llms.txt` to any section URL
- For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs-beta.getzep.com/_mcp/server

## Versions

- [v3](https://docs-beta.getzep.com/v3/llms.txt) (default)
- [v2](https://docs-beta.getzep.com/v2/llms.txt)