This project provides a no-code platform for creating and embedding custom GPTs on websites using the OpenAI Assistants API. It targets users who want to quickly deploy personalized AI assistants for their sites, offering features like fast setup, self-hosting for data security, embeddability, and monetization options.

How It Works

The platform leverages the OpenAI Assistants API to build custom GPTs. Users can configure instructions, enable features like Code Interpreter, DALL-E, or file retrieval, and integrate custom functions. The application is built with Next.js, OpenAI libraries, and Tailwind CSS, allowing for local hosting and direct embedding of the GPT onto a user's site.

Quick Start & Requirements

• Install: npm install
• Run: npm run build then npm run dev
• Prerequisites: Node.js v18, OpenAI API Key.
• Demo: https://customgpt.thesamur.ai/

Highlighted Details

• Enables embedding custom GPTs directly onto websites.
• Supports monetization by gating GPT access behind a paywall.
• Offers a hosted version for users who prefer not to self-host.
• Includes streaming support in the hosted version.

Maintenance & Community

• Community support is available via Discord: https://discord.gg/3sbpBxVZyH

Licensing & Compatibility

• Licensed under the MIT License.
• Permissive for commercial use and integration with closed-source applications.

Limitations & Caveats

The project requires an OpenAI API key, and local setup necessitates Node.js v18. While a hosted version is available, specific details on its features and limitations compared to the self-hosted option are not elaborated.