AI-Ready React Native + TypeScript Boilerplate

This repository provides a production-grade React Native boilerplate pre-configured for seamless integration with AI services like OpenAI, Anthropic, and Google Gemini. It targets developers seeking a robust foundation for AI-powered mobile applications, offering a provider-agnostic AI service layer, modern React Native features, and enhanced developer experience tools to accelerate development.

How It Works

The core innovation is a provider-agnostic AI service layer that abstracts interactions with various Large Language Models (LLMs). Developers can integrate OpenAI, Anthropic, Gemini, or custom LLM APIs using consistent hooks (useAIChat for multi-turn conversations and useAICompletion for single-shot tasks) and direct service calls (sendAIMessage, streamAIMessage). This approach minimizes integration time and allows for easy switching between AI providers. The boilerplate also leverages React Native's New Architecture for improved performance and includes a typed theme system and path aliases for better code organization and maintainability.

Quick Start & Requirements

1. Clone the repository: git clone https://github.com/kuraydev/react-native-typescript-boilerplate.git my-app
2. Navigate into the directory: cd my-app
3. Install dependencies: npm install
4. Install iOS pods: cd ios && pod install && cd ..
5. Configure Android SDK path by creating android/local.properties with your SDK location.
6. Run the app: npm run ios or npm run android.

Prerequisites include Node.js, npm, and a standard React Native development environment.

Highlighted Details

• AI Guidance Files: Includes configuration files (CLAUDE.md, AGENTS.md, .cursor/rules/, .github/copilot-instructions.md) for AI coding assistants like Cursor, Claude Code, GitHub Copilot, and Gemini CLI to understand project conventions.
• New Architecture: Enabled by default (newArchEnabled=true) for enhanced performance.
• Developer Experience: Features strict TypeScript, path aliases (@screens, @services, etc.), ESLint, Prettier, and Husky v9 pre-commit hooks enforcing linting, formatting, and Conventional Commits.
• AI Service Layer: Provider-agnostic hooks (useAIChat, useAICompletion) and functions (sendAIMessage, streamAIMessage) supporting streaming responses and customizable configurations.
• Navigation: A Stack navigator wrapping a Bottom Tab navigator, with all screen names managed via a SCREENS constant for type safety.

Maintenance & Community

No specific details on maintainers, sponsorships, or community channels (like Discord/Slack) are provided in the README.

Licensing & Compatibility

The project is licensed under the MIT License, permitting commercial use and modification.

Limitations & Caveats

The screens, components, and mock data included in the boilerplate are solely for demonstration purposes to showcase architecture and features; they are intended to be replaced with custom implementations.