AI Tamago is a 100% JavaScript-based virtual pet that simulates thoughts and feelings using local LLM inference. It aims to evoke nostalgia for Tamagotchi while offering a modern, AI-driven experience for users interested in local AI applications and interactive digital pets.

How It Works

The project leverages a full-stack JavaScript architecture, with Next.js handling app logic and UI. Local LLM inference is primarily managed by Ollama, with Langchain.js orchestrating LLM interactions. Game state is managed by Inngest, and Supabase with pgvector handles transactional and vector database needs. Embeddings are generated using Transformer.js and all-MiniLM-L6-v2.

Quick Start & Requirements

• Install: npm install
• Prerequisites: Docker, Ollama (or OpenAI/Replicate API keys), Supabase CLI, Node.js.
• Setup: Requires cloning the repo, installing dependencies, setting up local Supabase and Inngest, and configuring environment variables.
• Docs: Deployment Guide, Ollama, Supabase, Inngest.

Highlighted Details

• 100% local LLM inference with Ollama, OpenAI, or Replicate options.
• Full-stack JavaScript implementation using Next.js, Supabase, and Inngest.
• ASCII animations generated via ChatGPT prompts included in the repository.
• Multi-tenancy and rate limiting are supported for production deployments.

Maintenance & Community

• Active development with community support available via the #ai-tamago channel on AI Stack devs Discord.
• Links to relevant deployment guides for core technologies are provided.

Licensing & Compatibility

• The repository does not explicitly state a license in the provided README. Compatibility for commercial use or closed-source linking is not specified.

Limitations & Caveats

The project requires significant setup for local operation, including Docker, Supabase, and Ollama. Production deployment involves integrating with services like Fly.io, Clerk for authentication, and Upstash for rate limiting, which adds complexity. The lack of an explicit license may pose challenges for commercial adoption.