Agno - supermemory | Memory API for the AI era

Agno agents are stateless by default. Each conversation starts fresh. Supermemory changes that - your agents can remember users, recall past conversations, and build on previous interactions.

What you can do

Give agents access to user profiles and conversation history
Store agent interactions for future sessions
Let agents search memories to answer questions with context

Setup

Install the packages:

pip install agno supermemory python-dotenv

Set up your environment:

# .env
SUPERMEMORY_API_KEY=your-supermemory-api-key
OPENAI_API_KEY=your-openai-api-key

Get your Supermemory API key from console.supermemory.ai.

Basic integration

Fetch user context before running an agent, then store the interaction after.

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from supermemory import Supermemory
from dotenv import load_dotenv

load_dotenv()

memory = Supermemory()

def get_user_context(user_id: str, query: str) -> str:
    """Pull user profile and relevant memories."""
    result = memory.profile(container_tag=user_id, q=query)

    static = result.profile.static or []
    dynamic = result.profile.dynamic or []
    memories = result.search_results.results if result.search_results else []

    return f"""
User background:
{chr(10).join(static) if static else 'No profile yet.'}

Recent activity:
{chr(10).join(dynamic) if dynamic else 'Nothing recent.'}

Related memories:
{chr(10).join([m.memory or m.chunk for m in memories[:5]]) if memories else 'None.'}
"""

def create_agent(user_id: str, task: str) -> Agent:
    """Create an agent with user context."""
    context = get_user_context(user_id, task)

    return Agent(
        name="assistant",
        model=OpenAIChat(id="gpt-4o"),
        description=f"""You are a helpful assistant.

Here's what you know about this user:
{context}

Use this to personalize your responses.""",
        markdown=True
    )

def chat(user_id: str, message: str) -> str:
    """Run the agent and store the interaction."""
    agent = create_agent(user_id, message)
    response = agent.run(message)

    # Save for next time
    memory.add(
        content=f"User: {message}\nAssistant: {response.content}",
        container_tag=user_id
    )

    return response.content

Core concepts

User profiles

Supermemory keeps two buckets of user info:

Static facts: Things that stay consistent (name, preferences, expertise)
Dynamic context: What they’re focused on lately

result = memory.profile(
    container_tag="user_123",
    q="cooking help"  # Also returns relevant memories
)

print(result.profile.static)   # ["Vegetarian", "Allergic to nuts"]
print(result.profile.dynamic)  # ["Learning Italian cuisine", "Meal prepping"]

Storing memories

Save interactions so future sessions have context:

def store_chat(user_id: str, user_msg: str, agent_response: str):
    memory.add(
        content=f"User asked: {user_msg}\nAgent said: {agent_response}",
        container_tag=user_id,
        metadata={"type": "conversation"}
    )

Searching memories

Look up past interactions:

results = memory.search.memories(
    q="pasta recipes we discussed",
    container_tag="user_123",
    search_mode="hybrid",
    limit=5
)

for r in results.results:
    print(r.memory or r.chunk)

Example: personal assistant with memory

An assistant that actually knows who it’s talking to. Preferences stick around. Past conversations inform new ones.

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from supermemory import Supermemory
from dotenv import load_dotenv

load_dotenv()

class PersonalAssistant:
    def __init__(self):
        self.memory = Supermemory()

    def get_context(self, user_id: str, query: str) -> dict:
        """Fetch user profile and relevant history."""
        result = self.memory.profile(
            container_tag=user_id,
            q=query,
            threshold=0.5
        )

        return {
            "profile": result.profile.static or [],
            "recent": result.profile.dynamic or [],
            "history": [m.memory for m in (result.search_results.results or [])[:3]]
        }

    def build_description(self, context: dict) -> str:
        """Turn context into agent description."""
        parts = ["You are a helpful personal assistant."]

        if context["profile"]:
            parts.append(f"About this user: {', '.join(context['profile'])}")

        if context["recent"]:
            parts.append(f"They're currently: {', '.join(context['recent'])}")

        if context["history"]:
            parts.append(f"Past conversations: {'; '.join(context['history'])}")

        parts.append("Reference what you know about them when relevant.")

        return "\n\n".join(parts)

    def create_agent(self, context: dict) -> Agent:
        return Agent(
            name="assistant",
            model=OpenAIChat(id="gpt-4o"),
            description=self.build_description(context),
            markdown=True
        )

    def chat(self, user_id: str, message: str) -> str:
        """Handle a message and remember the interaction."""
        context = self.get_context(user_id, message)
        agent = self.create_agent(context)

        response = agent.run(message)

        # Store for future sessions
        self.memory.add(
            content=f"User: {message}\nAssistant: {response.content}",
            container_tag=user_id,
            metadata={"type": "chat"}
        )

        return response.content

    def teach(self, user_id: str, fact: str):
        """Store a preference or fact about the user."""
        self.memory.add(
            content=fact,
            container_tag=user_id,
            metadata={"type": "preference"}
        )


if __name__ == "__main__":
    assistant = PersonalAssistant()

    # Teach it some preferences
    assistant.teach("user_1", "Prefers concise answers")
    assistant.teach("user_1", "Works in software engineering")

    # Chat
    response = assistant.chat("user_1", "What's a good way to learn Rust?")
    print(response)

Using Agno tools with memory

Give your agent tools that can search and store memories directly.

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools import tool
from supermemory import Supermemory

memory = Supermemory()

@tool
def search_memory(query: str, user_id: str) -> str:
    """Search for information in the user's memory.

    Args:
        query: What to look for
        user_id: The user's ID
    """
    results = memory.search.memories(
        q=query,
        container_tag=user_id,
        limit=5
    )

    if not results.results:
        return "Nothing relevant found in memory."

    return "\n".join([r.memory or r.chunk for r in results.results])

@tool
def remember(content: str, user_id: str) -> str:
    """Store something important about the user.

    Args:
        content: What to remember
        user_id: The user's ID
    """
    memory.add(content=content, container_tag=user_id)
    return f"Remembered: {content}"

agent = Agent(
    name="memory_agent",
    model=OpenAIChat(id="gpt-4o"),
    tools=[search_memory, remember],
    description="""You are an assistant with memory.

When users share preferences or important info, use the remember tool.
When they ask about past conversations, search your memory first.""",
    markdown=True
)

Image context with memory

Agno handles images too. When users share photos, you can store what the agent saw for later.

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.media import Image
from pathlib import Path
from supermemory import Supermemory

memory = Supermemory()

def analyze_and_remember(user_id: str, image_path: str, question: str) -> str:
    """Analyze an image, answer a question, and store the context."""

    agent = Agent(
        name="vision_agent",
        model=OpenAIChat(id="gpt-4o"),
        description="You analyze images and answer questions about them.",
        markdown=True
    )

    # Get the agent's analysis
    response = agent.run(question, images=[Image(filepath=Path(image_path))])

    # Store the interaction with image context
    memory.add(
        content=f"User shared an image and asked: {question}\nAnalysis: {response.content}",
        container_tag=user_id,
        metadata={"type": "image_analysis", "image": image_path}
    )

    return response.content

Metadata for filtering

Tags let you narrow down searches:

# Store with metadata
memory.add(
    content="User prefers dark mode interfaces",
    container_tag="user_123",
    metadata={
        "type": "preference",
        "category": "ui",
        "source": "onboarding"
    }
)

# Search with filters
results = memory.search.memories(
    q="interface preferences",
    container_tag="user_123",
    filters={
        "AND": [
            {"key": "type", "value": "preference"},
            {"key": "category", "value": "ui"}
        ]
    }
)

User profiles

How automatic profiling works

Search

Filtering and search modes

LangChain

Memory for LangChain apps

CrewAI

Multi-agent systems with memory

​What you can do

​Setup

​Basic integration

​Core concepts

​User profiles

​Storing memories

​Searching memories

​Example: personal assistant with memory

​Using Agno tools with memory

​Image context with memory

​Metadata for filtering

​Related docs

User profiles

Search

LangChain

CrewAI

What you can do

Setup

Basic integration

Core concepts

User profiles

Storing memories

Searching memories

Example: personal assistant with memory

Using Agno tools with memory

Image context with memory

Metadata for filtering

Related docs