Show HN: Feedback Wanted: Gemini-Engineer Tool

An interactive, AI-driven terminal application that acts as a software engineering assistant, leveraging Google's Gemini API with function calling capabilities to perform file system operations and provide intelligent coding assistance.

• AI-Powered Coding Assistant: Uses Google's Gemini Pro model for intelligent code analysis and suggestions
• File System Operations: Read, create, edit, and manage files through AI function calls
• Interactive Terminal Interface: Beautiful, feature-rich terminal UI with Rich and prompt_toolkit
• Function Calling: Seamless integration between AI reasoning and local file operations
• Context Management: Add files and directories to conversation context for better assistance
• Streaming Responses: Real-time AI responses with visual feedback
• Safety Features: Built-in security checks to prevent directory traversal and handle binary files

• Python 3.11 or higher
• Google Gemini API key

1. Clone or download the project:

2. Install dependencies:

   pip install -r requirements.txt

3. Set up your Gemini API key: Create a .env file in the project directory:

   # Copy the example file and edit it cp env.example .env # Then edit .env and add your actual API key

   Or create it manually:

   echo "GEMINI_API_KEY=your_actual_api_key_here" > .env

   Optional: You can also specify which Gemini model to use:

   echo "GEMINI_MODEL=gemini-2.5-flash-preview" >> .env

   Available models: gemini-2.0-flash (default), gemini-2.5-flash-preview, gemini-2.5-pro-preview, gemini-1.5-flash, gemini-1.5-pro

   Get your API key from: https://aistudio.google.com/app/apikey

4. Run the application:

• Chat with AI: Simply type your questions or requests
• /add <file_path>: Add a file to conversation context
• /add <folder_path>: Add all files in a folder to context
• /help: Show help message
• /clear: Clear conversation history
• /exit or /quit: Exit the application

The AI assistant has access to the following file system tools:

Read the content of a single file.

Read the contents of multiple files at once.

Create a new file or overwrite an existing one.

Create multiple files simultaneously.

Replace specific text snippets in files.

List the contents of a directory.

• Path Validation: Prevents directory traversal attacks (../)
• File Size Limits: Maximum file size of 1MB for reads/writes
• Binary File Detection: Automatically skips binary files
• Working Directory Restriction: Operations are confined to the current directory and subdirectories

• GeminiEngineer: Main application class managing the interactive loop
• Tool Functions: File system operations (read_local_file, create_file, etc.)
• Tool Schemas: JSON schemas defining available tools for Gemini
• Safety Utilities: Path normalization and file type validation
• Rich UI: Terminal interface with panels, tables, and syntax highlighting

• google-generativeai: Gemini API integration
• rich: Terminal UI and formatting
• prompt_toolkit: Interactive command-line interface
• pydantic: Data validation
• python-dotenv: Environment variable management

The AI will:

1. Create the main Flask app file
2. Set up requirements.txt
3. Create a README with instructions
4. Provide run instructions

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

This project is open source and available under the MIT License.

API Key Error: Make sure your .env file contains a valid Gemini API key.

Permission Errors: Ensure you have write permissions in the current directory.

Import Errors: Install all dependencies with pip install -r requirements.txt.

Binary File Warnings: The tool automatically skips binary files for safety.

• Support for more AI models (Claude, GPT-4, etc.)
• Git integration for version control operations
• Project templates and scaffolding
• Code execution in sandboxed environments
• Plugin system for custom tools
• Web interface option
• Team collaboration features

If you encounter any issues or have questions:

1. Check the troubleshooting section above
2. Review the existing issues on GitHub
3. Create a new issue with detailed information about your problem

Happy coding with Gemini Engineer! 🚀