# Deep Agent from Scratch

This repository contains a minimal implementation of a deep agent that can:

1. Search the web using DuckDuckGo.
2. Create virtual files in memory.
3. Export the virtual files to the real file system.

The agent is built using the new LangChain 1.x and LangGraph 1.x APIs.

## Prerequisites

- Python 3.11 or newer
- Ollama running locally with a model such as `llama3.1`
- `pip install -r requirements.txt`

## Running the Agent

```bash
python agent.py
```

The script will run the agent with a sample prompt, create a virtual file `report.txt`, and export it to the `exported_files` directory.

## File Structure

- `agent.py` – Main implementation.
- `requirements.txt` – Python dependencies.
- `README.md` – This file.