We're building an AI Agent with human-like memory which integrates Zep's long-term memory backend with Microsoft's AutoGen framework, enabling agents to retain, recall, and manage contextual memory across conversations—paving the way for more intelligent, personalized, and persistent multi-agent interactions.

We use:

Zep for the memory layer to AI agent
Autogen (Agent Orchestration)
Ollama as Model Provider
Qwen 3 (LLM)
Streamlit to wrap the logic in an interactive UI

Set Up

Run these commands in project root

Setting up Ollama

# Setting up Ollama on linux
curl -fsSL https://ollama.com/install.sh | sh

# Pull the Qwen 3 4B model
ollama pull qwen3:4b

Install Dependencies

uv sync

Run the Application

Run the application with:

streamlit run app.py

Get your Zep API keys here

Get a FREE Data Science eBook 📖 with 150+ essential lessons in Data Science when you subscribe to our newsletter! Stay in the loop with the latest tutorials, insights, and exclusive resources. Subscribe now!

Contribution

Contributions are welcome! Feel free to fork this repository and submit pull requests with your improvements.

README.md

Zep Memory Assistant

Set Up

Setting up Ollama

Install Dependencies

Run the Application

📬 Stay Updated with Our Newsletter!

Contribution