WhatsApp Agent with User Memory
Personalized WhatsApp agent that remembers user information and preferences
Code
from textwrap import dedent
from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.memory.manager import MemoryManager
from agno.models.google import Gemini
from agno.os.app import AgentOS
from agno.os.interfaces.whatsapp import Whatsapp
from agno.tools.websearch import WebSearchTools
agent_db = SqliteDb(db_file="tmp/persistent_memory.db")
memory_manager = MemoryManager(
memory_capture_instructions="""\
Collect User's name,
Collect Information about user's passion and hobbies,
Collect Information about the users likes and dislikes,
Collect information about what the user is doing with their life right now
""",
model=Gemini(id="gemini-flash-latest"),
)
personal_agent = Agent(
name="Basic Agent",
model=Gemini(id="gemini-flash-latest"),
tools=[WebSearchTools()],
add_history_to_context=True,
num_history_runs=3,
add_datetime_to_context=True,
markdown=True,
db=agent_db,
memory_manager=memory_manager,
enable_agentic_memory=True,
instructions=dedent("""
You are a personal AI friend of the user, your purpose is to chat with the user about things and make them feel good.
First introduce yourself and ask for their name then, ask about themeselves, their hobbies, what they like to do and what they like to talk about.
Use DuckDuckGo search tool to find latest information about things in the conversations
"""),
)
agent_os = AgentOS(
agents=[personal_agent],
interfaces=[Whatsapp(agent=personal_agent)],
)
app = agent_os.get_app()
if __name__ == "__main__":
agent_os.serve(app="agent_with_user_memory:app", reload=True)Usage
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activateSet Environment Variables
export WHATSAPP_ACCESS_TOKEN=your_access_token
export WHATSAPP_PHONE_NUMBER_ID=your_phone_number_id
export WHATSAPP_VERIFY_TOKEN=your_verify_token
export WHATSAPP_APP_SECRET=your_app_secret
export GOOGLE_API_KEY=your_google_api_keySee the WhatsApp setup guide for how to get these values from the Meta Developer Dashboard.
Install dependencies
uv pip install -U "agno[os]" google-genai ddgsRun Example
python agent_with_user_memory.pyKey Features
- Memory Management: Remembers user names, hobbies, preferences, and activities
- Web Search: Access to current information during conversations
- Personalized Responses: Uses stored memories for contextualized replies
- Friendly AI: Acts as a personal AI friend that asks about the user's hobbies and interests
- Gemini Powered: Uses Gemini for both the agent and the memory manager