removed dead code from openai_cl, README updated

Author: abhishek-anand

README.md

@@ -1,79 +1,127 @@
 ![Demo](./demo.png)
 
-# ⚡ CodeRunner: A sandbox running on apple container for code execution
-
-CodeRunner provides a MCP server running inside a secure sandbox, powered by Apple's native [container](https://github.com/apple/container) technology, allowing you to safely execute code generated by local/remote AI models like Ollama.
-
-This guide is for **using** the pre-built CodeRunner sandbox.
+# ⚡ CodeRunner: Secure Code Execution Sandbox
 
+CodeRunner provides a secure MCP (Model Context Protocol) server that runs inside a sandboxed environment, powered by Apple's native [container](https://github.com/apple/container) technology. It allows you to safely execute code generated by AI models like Claude, OpenAI GPT, or Ollama.
 
+This guide shows you how to use the pre-built CodeRunner sandbox.
 
 ## 🚀 Quick Start
 
 ### Prerequisites
 
-*   A Mac with Apple Silicon (M1/M2/M3/M4 series).
-*   **[Apple `container` Tool](https://github.com/apple/container)** installed via **[Download](https://github.com/apple/container/releases/download/0.1.0/container-0.1.0-installer-signed.pkg)**
-*   **Python 3.10+**
+- Mac with Apple Silicon (M1/M2/M3/M4 series)
+- **[Apple `container` Tool](https://github.com/apple/container)** - [Download installer](https://github.com/apple/container/releases/download/0.1.0/container-0.1.0-installer-signed.pkg)
+- **Python 3.10+**
 
-### Step 1: Configure Local Network for Sandbox
+### Step 1: Set Up Local Network
 
-
-Run these commands once to set up the `.local` top-level domain:
+Run these commands once to configure the `.local` domain:
 
 ```bash
 sudo container system dns create local
 container system dns default set local
 ```
 
-### Step 2: Run the Pre-Built Sandbox Container
+### Step 2: Start the Sandbox Container
 
-This single command will download the CodeRunner sandbox image from Docker Hub (if not already present) and run it.
+This command downloads and runs the CodeRunner sandbox from Docker Hub:
 
 ```bash
-# This will run the container named 'coderunner' and make it
-# available at http://coderunner.local:8222
+# Run the container and make it available at http://coderunner.local:8222
 container run \
   --name coderunner \
   --detach --rm \
   instavm/coderunner
 ```
 
-
-### Step 3: Run an AI Task
-
-Finally, run the script from your terminal:
+### Step 3: Clone the Repository
 
 ```bash
 git clone https://github.com/BandarLabs/coderunner.git
 cd coderunner
-
-# Configure Claude Desktop MCP integration (optional)
-cp claude_mcp_proxy/claude_desktop_config.example.json claude_mcp_proxy/claude_desktop_config.json
-# Edit the config file with your local paths
 ```
 
-Now you can give it prompts like `write python code to generate 100 primes` and watch it execute the code safely in the sandbox!
+## 🔌 Integration Options
 
-### Use with Ollama3.1 with MCPHOST
+### Option 1: Claude Desktop Integration
 
-Download `mcphost` from [releases](https://github.com/mark3labs/mcphost/releases/tag/v0.14.0)
+Configure Claude Desktop to use CodeRunner as an MCP server:
 
-```bash
-cp examples/.mcp.json ~/.mcp.json
-~/Downloads/mcphost_Darwin_arm64/mcphost  -m ollama:llama3.1:8b
-```
+1. **Copy the example configuration:**
+   ```bash
+   cp claude_mcp_proxy/claude_desktop_config.example.json claude_mcp_proxy/claude_desktop_config.json
+   ```
 
-### Can also run via python openai agents
+2. **Edit the configuration file** and replace the placeholder paths:
+   - Replace `/path/to/your/python` with your actual Python path (e.g., `/usr/bin/python3` or `/opt/homebrew/bin/python3`)
+   - Replace `/path/to/coderunner` with the actual path to your cloned repository
+   
+   Example after editing:
+   ```json
+   {
+     "mcpServers": {
+       "coderunner": {
+         "command": "/opt/homebrew/bin/python3",
+         "args": ["/Users/yourname/coderunner/claude_mcp_proxy/mcp.py"]
+       }
+     }
+   }
+   ```
 
-```bash
-python examples/openai_client.py
-```
+3. **Update Claude Desktop configuration:**
+   - Open Claude Desktop
+   - Go to Settings → Developer
+   - Add the MCP server configuration
+   - Restart Claude Desktop
 
-### Use via Curl
+4. **Start using CodeRunner in Claude:**
+   You can now ask Claude to execute code, and it will run safely in the sandbox!
 
-```
-curl -X POST "http://coderunner.local:8222/execute/"  -H "Content-Type: application/json" -d '{"command": "print(100**100)"}'
+### Option 2: Python OpenAI Agents
 
-{"result":"100000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000\n"}
-```
+Use CodeRunner with OpenAI's Python agents library:
+
+1. **Set your OpenAI API key:**
+   ```bash
+   export OPENAI_API_KEY="your-openai-api-key-here"
+   ```
+
+2. **Install required dependencies:**
+   ```bash
+   pip install openai-agents
+   ```
+
+3. **Run the client:**
+   ```bash
+   python examples/openai_client.py
+   ```
+
+4. **Start coding:**
+   Enter prompts like "write python code to generate 100 prime numbers" and watch it execute safely in the sandbox!
+
+## 🛡️ Security Features
+
+### Sandboxed Execution
+All code runs in an isolated container environment, ensuring your host system remains secure.
+
+## 🏗️ Architecture
+
+CodeRunner consists of:
+- **Sandbox Container:** Isolated execution environment with Jupyter kernel
+- **MCP Server:** Handles communication between AI models and the sandbox
+- **Proxy Layer:** Manages connections and security
+
+## 📚 Examples
+
+The `examples/` directory contains:
+- `openai_client.py` - Example OpenAI agents integration
+- `systemprompt.txt` - Sample system prompt for AI models
+
+## 🤝 Contributing
+
+We welcome contributions! Please see [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
+
+## 📄 License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.

examples/.mcp.json

@@ -11,32 +11,6 @@
 from agents.model_settings import ModelSettings
 
 
-# async def run(mcp_server: MCPServer):
-#     agent = Agent(
-#         name="Assistant",
-#         instructions="Use the tools to answer the questions.",
-#         mcp_servers=[mcp_server],
-#         model_settings=ModelSettings(tool_choice="required"),
-#     )
-
-#     # Use the `add` tool to add two numbers
-#     message = "list files in current directory using python"
-#     print(f"Running: {message}")
-#     result = await Runner.run(starting_agent=agent, input=message)
-#     print(result.final_output)
-
-#     # Run the `get_weather` tool
-#     message = "Fetch ETH price on 15th June 2025. First pip install libraries needed like yfinance, then write the code and fetch data."
-#     print(f"\n\nRunning: {message}")
-#     result = await Runner.run(starting_agent=agent, input=message)
-#     print(result.final_output)
-
-#     # Run the `get_secret_word` tool
-#     message = "What's the secret word?"
-#     print(f"\n\nRunning: {message}")
-#     result = await Runner.run(starting_agent=agent, input=message)
-#     print(result.final_output)
-
 
 async def run(mcp_server: MCPServer):
     agent = Agent(