Enfiy Code

Enfiy Code

Your Universal AI Coding Agent

npm install -g @enfiy/enfiy-code

Screenshot

Quickstart

Ensure you have Node.js v18 or higher installed.

Option 1: Run without installing (Recommended for first-time users)

npx @enfiy/enfiy-code

Option 2: Install globally (Recommended for regular use)

npm install -g @enfiy/enfiy-code
enfiy

On first run, you'll be guided through selecting a theme, AI provider, and authentication method. Your settings persist automatically.

About

Enfiy Code is a command-line AI workflow tool that integrates with your development environment. It understands your code and helps you work more efficiently, whether you're working locally or in the cloud.

Key Features

• Query and edit large codebases using advanced AI models with extended context support
• Generate applications from PDFs or sketches using multimodal AI
• Automate tasks like querying pull requests or handling complex rebases
• Connect external tools through MCP (Model Context Protocol)
• Support for multiple AI providers - both cloud and local

AI Providers

Cloud AI (Powerful)

| Provider | Description | | ------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------- | | | Anthropic ClaudeIndustry-leading AI for coding tasks | | | OpenAI GPTPopular and versatile language models | | | Google GeminiMultimodal AI with strong reasoning capabilities | | | Mistral AIOpen-source focused AI models | | | OpenRouterUnified access to many AI models |

Local AI (Private)

| Provider | Description | | -------------------------------------------------------------------- | ------------------------------------------------------------------------- | | | OllamaRun models locally with full privacy |

Development

Prerequisites for Development

• Node.js v18 or higher
• npm or yarn package manager
• Git

Setting Up Development Environment

1. Clone the repository

git clone https://github.com/enfiy/enfiy-code.git
cd enfiy-code

1. Install dependencies

npm install

This will install all required packages listed in package.json.

1. Build the project

npm run build

This compiles TypeScript and prepares the application for execution.

1. Start the development version

npm start

This launches Enfiy Code in development mode.

Development Commands

• npm run start - Start in development mode
• npm run debug - Start with debugging enabled
• npm run build - Build for production
• npm run test - Run test suite
• npm run lint - Check code style and quality
• npm run format - Format code automatically
• npm run typecheck - TypeScript type checking
• npm run preflight - Complete CI pipeline check

Authentication

OAuth Configuration (Optional)

For production use, you may want to set up custom OAuth applications:

Google Gemini OAuth

# Set custom Google OAuth credentials (optional)
export ENFIY_GOOGLE_OAUTH_CLIENT_ID="your-client-id.apps.googleusercontent.com"
export ENFIY_GOOGLE_OAUTH_CLIENT_SECRET="your-client-secret"

To create your own Google OAuth client:

1. Visit Google Cloud Console
2. Create new OAuth 2.0 Client ID
3. Select "Desktop application"
4. Name it "Enfiy Code"
5. Use the credentials in environment variables above

HuggingFace OAuth

# Set custom HuggingFace OAuth client ID (optional)
export HF_CLIENT_ID="your-huggingface-app-id"

> Note: By default, Enfiy Code uses temporary OAuth clients for compatibility. Custom OAuth setup ensures proper branding in consent screens.

Command Line Options

Enfiy Code supports various command-line options to customize your experience:

Basic Options

• -m, --model - Specify AI model to use
• -p, --prompt - Start with an initial prompt

Workflow Options

• -y, --auto - Automatically approve all AI actions
• -a, --all-files - Include all project files in context
• -c, --checkpointing - Enable file edit checkpointing

Development Options

• -d, --debug - Enable debug mode with verbose logging
• --show-memory-usage - Display memory usage in status bar

Sandbox Options

• -s, --sandbox - Run in isolated sandbox environment
• --sandbox-image - Use custom sandbox container image

Examples

# Start interactive mode
enfiy

# Use specific model
enfiy -m "gpt-4"

# Start with a prompt
enfiy -p "Review my code for security issues"

# Auto-approve all actions
enfiy --auto

# Enable debug mode
enfiy --debug

Interactive Commands

Once Enfiy Code is running, use these commands to interact with the AI:

• /provider - Select AI provider and model
• /mcp - Connect to MCP servers for enhanced capabilities
• /tool - Access specialized tools and integrations
• /help - Show available commands and usage information
• /bug - Report bugs or issues to the development team
• Code with confidence, create without limits, command with ease

Usage Examples

Basic Usage

# Start Enfiy Code
enfiy

# Ask questions about your code
> What does this function do?
> How can I optimize this database query?

# Request code changes
> Add error handling to the user authentication
> Refactor this component to use React hooks

Project Development

# Start a new project
cd my-project/
enfiy
> Create a React app with TypeScript and authentication
> Add a responsive navigation component
> Set up Jest testing framework

Code Analysis

# Analyze existing codebase
enfiy
> Review this codebase for security vulnerabilities
> Identify performance bottlenecks
> Suggest architectural improvements

Automation Tasks

# Automate development workflows
enfiy
> Write comprehensive tests for the API endpoints
> Generate documentation for these functions
> Create deployment scripts for production

Documentation

Getting Started

• [Quick Start Guide](./docs/getting-started/README.md) – Get up and running in minutes
• [Installation](./docs/getting-started/installation.md) – Detailed installation instructions
• [First Steps](./docs/getting-started/first-steps.md) – Essential commands and workflows
• [API Configuration](./docs/getting-started/api-configuration.md) – Set up AI provider authentication

User Guides

• [All Guides](./docs/guides/README.md) – Complete guide collection
• [MCP Integration](./docs/guides/mcp-integration.md) – Connect external tools and services
• [Checkpointing](./docs/guides/checkpointing.md) – Save and restore conversation sessions

API Reference

• [API Documentation](./docs/api/README.md) – Technical reference
• [CLI Commands](./docs/api/cli/commands.md) – Complete command reference
• [Tools Reference](./docs/api/tools/README.md) – Built-in tools and capabilities

Development

• [Development Guide](./docs/development/README.md) – Contributing and development setup
• [Architecture](./docs/development/architecture.md) – System design and components
• [Extensions](./docs/development/extension.md) – Creating custom extensions

Security

• [Security Overview](./docs/security/README.md) – Security policies and best practices
• [Privacy Policy](./docs/security/privacy-policy.md) – Data handling and privacy rights
• [Telemetry](./docs/security/telemetry.md) – Data collection and opt-out options

Project Structure

enfiy-code/
├── packages/              # Monorepo packages
│   ├── cli/              # CLI application
│   └── core/             # Core library
├── docs/                 # Documentation
├── scripts/              # Build and development scripts
├── integration-tests/    # End-to-end tests
├── bundle/              # Built CLI bundle
├── build-artifacts/     # Build analysis files
└── tools/               # Development utilities

Contributing

We welcome contributions to Enfiy Code! Please see our [contributing guidelines](./CONTRIBUTING.md) for more information on how to get started.

License

Enfiy Code is licensed under the [Apache 2.0 License](./LICENSE).

---

Thank you for using Enfiy Code! 🧡

Built with care by the Enfiy Community

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: enfiy
• Source: enfiy/enfiy-code
• License: Apache-2.0

Install and usage instructions live in the source repository linked above.