PandoraAI is a web-based chat client designed for interacting with multiple AI models, including various GPT versions and Bing Chat. It targets users seeking a convenient, account-free interface for AI conversations, offering custom preset management and local data storage for easy import/export across devices.

How It Works

The client is built with Nuxt 3, a Vue 3 framework, leveraging node-chatgpt-api for backend AI model integration. It supports multiple AI endpoints, provided they are compatible with the node-chatgpt-api interface. All user data, including presets and conversation history, is stored locally in the browser's local storage, eliminating the need for user accounts.

Quick Start & Requirements

• Install dependencies: yarn install, npm install, or pnpm install.
• Start development server: npm run dev.
• Build for production: npm run build.
• Preview production build: npm run preview.
• Requires a running node-chatgpt-api server with API_BASE_URL configured in .env.
• Nuxt 3 documentation: https://nuxt.com/docs/getting-started/introduction
• Deployment documentation: https://nuxt.com/docs/getting-started/deployment

Highlighted Details

• Supports multiple AI models via node-chatgpt-api (e.g., gpt-3.5-turbo, text-davinci-003, ChatGPT, Bing).
• Allows creation of multiple custom presets for different AI interactions.
• Local storage for data persistence, enabling account-free usage and data portability.
• Built on Nuxt 3 and Vue 3.

Maintenance & Community

No specific information on contributors, sponsorships, or community channels (Discord/Slack) is provided in the README.

Licensing & Compatibility

Licensed under the MIT License. This license is permissive and generally compatible with commercial use and closed-source linking.

Limitations & Caveats

The project relies on a separate node-chatgpt-api server, which must be set up and configured independently. Users may need to run nuxi upgrade --force if encountering issues with blank pages after updates.