Skip to main content
📢 Announcing our research paper: Zentry achieves 26% higher accuracy than OpenAI Memory, 91% lower latency, and 90% token savings! Read the paper to learn how we're revolutionizing AI agent memory.
Integrate Zentry’s memory capabilities with OpenAI’s Agents SDK to create AI agents with persistent memory. You can create agents that remember past conversations and use that context to provide better responses.

​
Installation

First, install the required packages: 
pip install Zentryai pydantic openai-agents
You’ll also need a custom agents framework for this implementation.

​
Setting Up Environment Variables

Store your Zentry API key as an environment variable: 
export Zentry_API_KEY="your_Zentry_api_key"
Or in your Python script: 
import os
os.environ["Zentry_API_KEY"] = "your_Zentry_api_key"

​
Code Structure

The integration consists of three main components:
  1. Context Manager: Defines user context for memory operations
  2. Memory Tools: Functions to add, search, and retrieve memories
  3. Memory Agent: An agent configured to use these memory tools

​
Step-by-Step Implementation

​
1. Import Dependencies

from __future__ import annotations
import os
import asyncio
from pydantic import BaseModel
try:
    from Zentry import AsyncMemoryClient
except ImportError:
    raise ImportError("Zentry is not installed. Please install it using 'pip install Zentryai'.")
from agents import (
    Agent,
    ItemHelpers,
    MessageOutputItem,
    RunContextWrapper,
    Runner,
    ToolCallItem,
    ToolCallOutputItem,
    TResponseInputItem,
    function_tool,
)

​
2. Define Memory Context

class ZentryContext(BaseModel):
    user_id: str | None = None

​
3. Initialize the Zentry Client

client = AsyncMemoryClient(api_key=os.getenv("Zentry_API_KEY"))

​
4. Create Memory Tools

​
Add to Memory

@function_tool
async def add_to_memory(
    context: RunContextWrapper[ZentryContext],
    content: str,
) -> str:
    """
    Add a message to Zentry
    Args:
        content: The content to store in memory.
    """
    messages = [{"role": "user", "content": content}]
    user_id = context.context.user_id or "default_user"
    await client.add(messages, user_id=user_id)
    return f"Stored message: {content}"

​
Search Memory

@function_tool
async def search_memory(
    context: RunContextWrapper[ZentryContext],
    query: str,
) -> str:
    """
    Search for memories in Zentry
    Args:
        query: The search query.
    """
    user_id = context.context.user_id or "default_user"
    memories = await client.search(query, user_id=user_id, output_format="v1.1")
    results = '\n'.join([result["memory"] for result in memories["results"]])
    return str(results)

​
Get All Memories

@function_tool
async def get_all_memory(
    context: RunContextWrapper[ZentryContext],
) -> str:
    """Retrieve all memories from Zentry"""
    user_id = context.context.user_id or "default_user"
    memories = await client.get_all(user_id=user_id, output_format="v1.1")
    results = '\n'.join([result["memory"] for result in memories["results"]])
    return str(results)

​
5. Configure the Memory Agent

memory_agent = Agent[ZentryContext](
    name="Memory Assistant",
    instructions="""You are a helpful assistant with memory capabilities. You can:
    1. Store new information using add_to_memory
    2. Search existing information using search_memory
    3. Retrieve all stored information using get_all_memory
    When users ask questions:
    - If they want to store information, use add_to_memory
    - If they're searching for specific information, use search_memory
    - If they want to see everything stored, use get_all_memory""",
    tools=[add_to_memory, search_memory, get_all_memory],
)

​
6. Implement the Main Runtime Loop

async def main():
    current_agent: Agent[ZentryContext] = memory_agent
    input_items: list[TResponseInputItem] = []
    context = ZentryContext()
    while True:
        user_input = input("Enter your message (or 'quit' to exit): ")
        if user_input.lower() == 'quit':
            break
        input_items.append({"content": user_input, "role": "user"})
        result = await Runner.run(current_agent, input_items, context=context)
        for new_item in result.new_items:
            agent_name = new_item.agent.name
            if isinstance(new_item, MessageOutputItem):
                print(f"{agent_name}: {ItemHelpers.text_message_output(new_item)}")
            elif isinstance(new_item, ToolCallItem):
                print(f"{agent_name}: Calling a tool")
            elif isinstance(new_item, ToolCallOutputItem):
                print(f"{agent_name}: Tool call output: {new_item.output}")
            else:
                print(f"{agent_name}: Skipping item: {new_item.__class__.__name__}")
        input_items = result.to_input_list()

if __name__ == "__main__":
    asyncio.run(main())

​
Usage Examples

​
Storing Information

User: Remember that my favorite color is blue
Agent: Calling a tool
Agent: Tool call output: Stored message: my favorite color is blue
Agent: I've stored that your favorite color is blue in my memory. I'll remember that for future conversations.

​
Searching Memory

User: What's my favorite color?
Agent: Calling a tool
Agent: Tool call output: my favorite color is blue
Agent: Your favorite color is blue, based on what you've told me earlier.

​
Retrieving All Memories

User: What do you know about me?
Agent: Calling a tool
Agent: Tool call output: favorite color is blue
my birthday is on March 15
Agent: Based on our previous conversations, I know that:
1. Your favorite color is blue
2. Your birthday is on March 15

​
Advanced Configuration

​
Custom User IDs

You can specify different user IDs to maintain separate memory stores for multiple users: 
context = ZentryContext(user_id="user123")

​
Resources