This project provides a personal AI assistant that integrates with Apple Shortcuts, eliminating the need for dedicated hardware. It's designed for users who want a customizable AI experience accessible via their iPhone or iPad, leveraging Cloudflare Workers for backend processing and supporting various LLM models.

How It Works

The assistant runs on Cloudflare Workers, enabling serverless execution and broad accessibility. It supports custom function calling for integrating external data sources, demonstrated with weather data retrieval. The architecture allows flexibility in choosing LLM providers, with Llama 3 and Groq being examples.

Quick Start & Requirements

• Install: Clone the repository, run npm install, npx wrangler login, npx wrangler kv:namespace create chats, npx wrangler kv:namespace create chats --preview, update wrangler.toml with KV namespace IDs, set secrets (GROQ_API_KEY, OPENWEATHERMAP_API_KEY) via npx wrangler secret put <SECRET_NAME>, and deploy with npx wrangler deploy.
• Prerequisites: Node.js, npm, Cloudflare account, Groq API key, OpenWeatherMap API key.
• Setup: Requires Cloudflare account setup and API key generation. Deployment involves configuring wrangler.toml and setting secrets.
• Links: Apple Shortcut

Highlighted Details

• Serverless backend on Cloudflare Workers.
• Supports custom function calling for LLMs.
• Integrates with Apple Shortcuts for mobile access.
• Example usage with Llama 3 and Groq.

Maintenance & Community

No specific details on contributors, sponsorships, or community channels are provided in the README.

Licensing & Compatibility

The README does not specify a license. Compatibility for commercial use or closed-source linking is not detailed.

Limitations & Caveats

The project is presented as a personal assistant, and its setup requires familiarity with Cloudflare Workers, Node.js, and API key management. The lack of a specified license may impact commercial adoption.