AI CLI Agent

A powerful AI-powered command-line interface agent that integrates with OpenRouter API to perform automated software development tasks. Built with Rust for performance and reliability.

Features

🤖 AI-Powered: Leverages OpenRouter API to access various AI models
📁 File Operations: Read, write, edit, and delete files and directories
💻 Terminal Integration: Execute shell commands and manage processes
🎯 Multi-Step Tasks: Execute complex development workflows
🔄 Interactive Mode: Chat with the AI for iterative development
⚡ Fast & Efficient: Built with Rust for optimal performance
🔧 Configurable: Customizable settings and model selection

Installation

Prerequisites

Rust (latest stable version)
OpenRouter API key
Git

Setup

Clone the repository:

git clone https://github.com/your-username/ai-cli-agent.git
cd ai-cli-agent

Set up your OpenRouter API key:

export OPENROUTER_API_KEY="your_api_key_here"

Build the project:

cargo build --release

Run the test script to verify everything works:

chmod +x test_ai_agent.sh
./test_ai_agent.sh

Usage

Basic Commands

Execute a Task

cargo run -- execute "write a hello world program in python"

File Operations

# Read a file
cargo run -- read path/to/file.txt

# Write a file
cargo run -- write path/to/file.txt "Hello, World!"

# Edit a file
cargo run -- edit path/to/file.txt "change hello to hi"

# Delete a file
cargo run -- delete path/to/file.txt

# List directory
cargo run -- list path/to/directory

Terminal Commands

# Run a command
cargo run -- run "ls -la"

Interactive Mode

cargo run -- interactive

Advanced Usage

Custom Model Selection

cargo run -- execute --model "anthropic/claude-2" "write a rust program"

Custom Working Directory

cargo run -- execute --work-dir "/path/to/project" "analyze this codebase"

Custom System Prompt

cargo run -- execute --prompt "You are an expert Rust developer" "write a web server"

Configuration

The AI CLI Agent uses a configuration file located at ~/.config/ai-cli-agent/config.toml. You can customize various settings:

openrouter_api_key = "your_api_key_here"
model = "openai/gpt-4"
work_dir = "/path/to/your/project"
max_tokens = 4000
temperature = 0.7
timeout_seconds = 120
auto_save = true
backup_enabled = true
backup_dir = ".ai_cli_backups"

Available Models

The agent supports various models through OpenRouter:

openai/gpt-4
openai/gpt-4-turbo
openai/gpt-3.5-turbo
anthropic/claude-2
anthropic/claude-instant-1
google/palm-2-chat-bison
google/palm-2-codechat-bison
meta-llama/llama-2-70b-chat
meta-llama/llama-2-13b-chat
mistralai/mistral-7b-instruct
mistralai/mixtral-8x7b-instruct

Examples

Example 1: Create a Snake Game

cargo run -- execute "write a complete HTML snake game with CSS and JavaScript"

Example 2: Modify the Game

cargo run -- edit snake.html "change the background to a gradient from blue to purple"

Example 3: Build a Rust Project

cargo run -- execute "create a new Rust project with a simple web server using tokio"

Example 4: Code Analysis

cargo run -- execute "analyze this codebase and suggest improvements"

API Response Format

The AI agent understands structured responses in the following format:

WRITE_FILE: filename.html
<!DOCTYPE html>
<html>
<head>
    <title>My Page</title>
</head>
<body>
    <h1>Hello World</h1>
</body>
</html>

RUN_COMMAND: npm install
npm install

EDIT_FILE: style.css
Change the background color to blue

Development

Project Structure

ai-cli-agent/
├── src/
│   ├── main.rs          # Main entry point
│   ├── ai.rs            # OpenRouter API integration
│   ├── file_ops.rs      # File operations
│   ├── terminal.rs      # Terminal operations
│   ├── config.rs        # Configuration management
│   └── utils.rs         # Utility functions
├── Cargo.toml           # Rust dependencies
├── test_ai_agent.sh     # Test script
└── README.md           # This file

Adding New Features

Add new dependencies to Cargo.toml
Implement the feature in the appropriate module
Add CLI commands in main.rs
Update the configuration if needed
Add tests

Testing

Run the test script:

./test_ai_agent.sh

Run unit tests:

cargo test

Troubleshooting

Common Issues

API Key Not Found
- Make sure you've set the OPENROUTER_API_KEY environment variable
- Check your configuration file
Permission Denied
- Ensure you have write permissions in the target directory
- Check file system permissions
Network Issues
- Verify your internet connection
- Check if OpenRouter API is accessible
Build Errors
- Ensure you have the latest Rust version
- Run cargo clean and try building again

Debug Mode

Enable debug logging:

RUST_LOG=debug cargo run -- execute "your task"

Contributing

Fork the repository
Create a feature branch
Make your changes
Add tests
Submit a pull request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Support

For support, please open an issue on GitHub or contact the maintainers.

Acknowledgments

OpenRouter for providing AI model access
Rust community for excellent tools and libraries
All contributors who have helped improve this project

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
src		src
.dockerignore		.dockerignore
.gitignore		.gitignore
Cargo.toml		Cargo.toml
PROJECT_SUMMARY.md		PROJECT_SUMMARY.md
README.md		README.md
config.example.toml		config.example.toml
demo_ai_agent.py		demo_ai_agent.py
snake_game.html		snake_game.html
test_ai_agent.sh		test_ai_agent.sh

prprojectbase/aiagentcli

Folders and files

Latest commit

History

Repository files navigation