add README.md

README.md

@@ -1,17 +1,39 @@
-# DeepAgent Search
+# DeepAgent from Scratch
 
-This repository contains a simple deep agent that can search the web and create virtual files. The agent is built using the `deepagents` library and follows the "deep agents from scratch" pattern.
+## Overview
+This repository contains a minimal implementation of a **DeepAgent** inspired by the *Deep Agents from Scratch* course. The agent can:
 
-## Features
+1. Search the web using DuckDuckGo.
+2. Create virtual files in an in‑memory file system.
+3. Persist those virtual files to the real file system when the task is finished.
 
-- Web search using DuckDuckGo.
+The implementation uses:
-- Virtual file creation in an in‑memory filesystem.
+- **LangChain OpenAI** (`ChatOpenAI`) for LLM interactions.
-- Export virtual files to the real filesystem at the end of the run.
+- **DuckDuckGo Search** for web queries.
+- A simple `VirtualFileSystem` class to hold files in memory.
 
-## Usage
+## Requirements
-
+```
-```bash
+langchain-openai>=0.3.0
-python main.py "search query"
+langchain>=1.2.10
+langgraph>=0.2.0
+duckduckgo-search
 ```
 
-The agent will perform the search, create virtual files, and write them to the current directory.
+## Running the Agent
+```bash
+# Install dependencies
+pip install -r requirements.txt
+
+# Run the agent
+python main.py
+```
+
+The script will perform a sample search for *"LangChain deep agent"* and create a file named `summary.txt` with the first search result. All virtual files are written to the current directory.
+
+## Extending the Agent
+- Add more tools by decorating functions with `@tool` and passing them to `DeepAgent`.
+- Modify the `run` method to change the interaction loop or add more sophisticated prompting.
+
+## License
+MIT