SuperAPI AI Directory

friday

Friday is an AI-powered application generation tool, positioned as a developer assistant that can help users quickly create complete Node.js projects through unlimited prompts. It provides one core prompt for setting up the application foundation and allows adding any number of sections, each corresponding to a prompt and representing a specific part of the application. Friday uses GPT-4 to provide AI assistance and has been tested and optimized for GPT-4-32k to achieve better speed and results. Generating the application foundation requires 2 small requests, and each user-provided section requires 1 request. Friday uses esbuild in the background to process each created application. The project uses the MIT license.

Open website

About this tool

Purpose

Friday is a developer assistant and also an AI-powered application generation tool, designed to help users quickly create applications with the help of AI. It can generate complete Node.js projects for users and supports an unlimited number of prompts.

Main capabilities

  • Provides a core prompt for building the application foundation.
  • Allows adding an unlimited number of sections, where each section is a prompt representing a specific part of the application.
  • Uses GPT-4 for AI assistance and has been tested and optimized for GPT-4-32k to improve speed and obtain better results.
  • Uses 2 small requests for the application foundation and 1 request for each provided section.
  • Uses esbuild in the background for each created application.
  • Currently mainly generates one index.js and one .env file for the entire application.

How to use

Using Friday requires access to a GPT-like chat completion API, such as GPT-4 or GPT-4-32k. The project's file structure is as follows:

  • core: Friday's core module.
  • web:
    • frontend: the application's frontend module.
    • backend: the application's backend module.
  • frontend: the application's frontend module.
  • backend: the application's backend module.

Setup and usage steps:

  1. Go to the web/backend directory and open the .env file, then fill in the AI API key and endpoint. You can use the official OpenAI endpoint:https://api.openai.com/v1/chat/completions
  2. Go to the core directory and run the corresponding command to build the core module.
  3. Go to the web/backend directory and run the corresponding command to start the backend server.
  4. Go to the web/frontend directory and run the corresponding command to run the frontend module.

Make sure to run npm install for the backend and frontend directories to install the necessary dependencies, especially when setting up the project for the first time.

After completing the above steps, you should be able to access and use Friday through the frontend interface at http://localhost:5173。

After receiving the "Done" message in the UI, the project will be created in the projects/last directory.

  • Check the .env file and modify it if needed.
  • Run npm i to install packages.
  • Run npm run start to start the project.

Sometimes Friday may not include the packages used in the packages.json file. If you encounter missing packages after running npm run start, please install them manually.

Use Cases

Friday is suitable for developers who need to quickly generate Node.js application prototypes with the help of AI, especially for scenarios where they want to gradually build the application foundation and specific parts using a core prompt plus multiple section prompts. The official materials mention that you can visit its Twitter homepage to view demos and examples, and you can join its Discord server to get support, participate in discussions, and share feedback, ideas, and applications created with Friday.

Limitations

  • Requires access to a GPT-type chat completion API (such as GPT-4 or GPT-4-32k).
  • Currently mainly generates one index.js and one .env file, and scalability for multi-file applications needs to be enhanced.
  • Occasionally may not list the packages used in packages.json, requiring manual installation of missing packages.

The improvement directions listed in the official materials include: enhancing Friday's scalability for multi-file applications through clearly defined structure; improving the panel's user interface for a more intuitive experience; implementing documentation functionality to attach API or package documentation to application prompts with just one click; introducing a code debugger to make troubleshooting easier.

License

This project uses the MIT license.