> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Zep Integration

> Write user messages through ZepTools, wait for Zep to sync, then pass the retrieved Zep context block into an Agno agent as a dependency.

Demonstrates Zep-powered memory retrieval for an Agno agent.

```python zep_integration.py theme={null}
"""
Zep Integration
===============

Demonstrates Zep-powered memory retrieval for an Agno agent.
"""

import time

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.zep import ZepTools

# ---------------------------------------------------------------------------
# Setup
# ---------------------------------------------------------------------------
# Initialize the ZepTools
zep_tools = ZepTools(user_id="agno", session_id="agno-session")

zep_tools.add_zep_message(role="user", content="My name is John Billings")
zep_tools.add_zep_message(role="user", content="I live in NYC")
zep_tools.add_zep_message(role="user", content="I'm going to a concert tomorrow")

# Allow the memories to sync with Zep database
time.sleep(10)


# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
agent = Agent(
    model=OpenAIChat(),
    tools=[zep_tools],
    dependencies={"memory": zep_tools.get_zep_memory(memory_type="context")},
    add_dependencies_to_context=True,
)


# ---------------------------------------------------------------------------
# Run Example
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    # Ask the Agent about the user
    agent.print_response("What do you know about me?")
```

## Run the Example

<Snippet file="create-venv-step.mdx" />

**1. Install dependencies**

```bash theme={null}
uv pip install -U agno openai zep-cloud
```

**2. Export your API keys**

```bash Mac/Linux theme={null}
export OPENAI_API_KEY="your_openai_api_key_here"
export ZEP_API_KEY="your_zep_api_key_here"
```

```bash Windows theme={null}
$Env:OPENAI_API_KEY="your_openai_api_key_here"
$Env:ZEP_API_KEY="your_zep_api_key_here"
```

**3. Run the example**

Save the code above as `zep_integration.py`, then run:

```bash theme={null}
python zep_integration.py
```

Full source: [cookbook/11\_memory/integrations/zep\_integration.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/11_memory/integrations/zep_integration.py)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.