AutoGPT/autogpt_platform/frontend

This is the frontend for AutoGPT's next generation

🧢 Getting Started

This project uses pnpm as the package manager via corepack. Corepack is a Node.js tool that automatically manages package managers without requiring global installations.

Prerequisites

Make sure you have Node.js 16.10+ installed. Corepack is included with Node.js by default.

⚠️ Migrating from yarn

This project was previously using yarn1, make sure to clean up the old files if you set it up previously with yarn:

rm -f yarn.lock && rm -rf node_modules

Then follow the setup steps below.

Setup

1. Enable corepack (run this once on your system):

   corepack enable
   

   This enables corepack to automatically manage pnpm based on the packageManager field in package.json.

2. Install dependencies:

   pnpm i
   

3. Start the development server:

   pnpm dev
   

Open http://localhost:3000 with your browser to see the result.

You can start editing the page by modifying app/page.tsx. The page auto-updates as you edit the file.

Subsequent Runs

For subsequent development sessions, you only need to run:

pnpm dev

Every time a new Front-end dependency is added by you or others, you will need to run pnpm i to install the new dependencies.

Available Scripts

• pnpm dev - Start development server
• pnpm build - Build for production
• pnpm start - Start production server
• pnpm lint - Run ESLint and Prettier checks
• pnpm format - Format code with Prettier
• pnpm type-check - Run TypeScript type checking
• pnpm test - Run Playwright tests
• pnpm test-ui - Run Playwright tests with UI
• pnpm fetch:openapi - Fetch OpenAPI spec from backend
• pnpm generate:api-client - Generate API client from OpenAPI spec
• pnpm generate:api-all - Fetch OpenAPI spec and generate API client

This project uses next/font to automatically optimize and load Inter, a custom Google Font.

🔄 Data Fetching Strategy

Note

You don't need to run the OpenAPI commands below to run the Front-end. You will only need to run them when adding or modifying endpoints on the Backend API and wanting to use those on the Frontend.

This project uses an auto-generated API client powered by Orval, which creates type-safe API clients from OpenAPI specifications.

How It Works

1. Backend Requirements: Each API endpoint needs a summary and tag in the OpenAPI spec
2. Operation ID Generation: FastAPI generates operation IDs using the pattern {method}{tag}{summary}
3. Spec Fetching: The OpenAPI spec is fetched from http://localhost:8006/openapi.json and saved to the frontend
4. Spec Transformation: The OpenAPI spec is cleaned up using a custom transformer (see autogpt_platform/frontend/src/app/api/transformers)
5. Client Generation: Auto-generated client includes TypeScript types, API endpoints, and Zod schemas, organized by tags

API Client Commands

# Fetch OpenAPI spec from backend and generate client
pnpm generate:api-all

# Only fetch the OpenAPI spec
pnpm fetch:openapi

# Only generate the client (after spec is fetched)
pnpm generate:api-client

Using the Generated Client

The generated client provides React Query hooks for both queries and mutations:

Queries (GET requests)

import { useGetV1GetNotificationPreferences } from "@/app/api/__generated__/endpoints/auth/auth";

const { data, isLoading, isError } = useGetV1GetNotificationPreferences({
  query: {
    select: (res) => res.data,
    // Other React Query options
  },
});

Mutations (POST, PUT, DELETE requests)

import { useDeleteV2DeleteStoreSubmission } from "@/app/api/__generated__/endpoints/store/store";
import { getGetV2ListMySubmissionsQueryKey } from "@/app/api/__generated__/endpoints/store/store";
import { useQueryClient } from "@tanstack/react-query";

const queryClient = useQueryClient();

const { mutateAsync: deleteSubmission } = useDeleteV2DeleteStoreSubmission({
  mutation: {
    onSuccess: () => {
      // Invalidate related queries to refresh data
      queryClient.invalidateQueries({
        queryKey: getGetV2ListMySubmissionsQueryKey(),
      });
    },
  },
});

// Usage
await deleteSubmission({
  submissionId: submission_id,
});

Server Actions

For server-side operations, you can also use the generated client functions directly:

import { postV1UpdateNotificationPreferences } from "@/app/api/__generated__/endpoints/auth/auth";

// In a server action
const preferences = {
  email: "user@example.com",
  preferences: {
    AGENT_RUN: true,
    ZERO_BALANCE: false,
    // ... other preferences
  },
  daily_limit: 0,
};

await postV1UpdateNotificationPreferences(preferences);

Server-Side Prefetching

For server-side components, you can prefetch data on the server and hydrate it in the client cache. This allows immediate access to cached data when queries are called:

import { getQueryClient } from "@/lib/tanstack-query/getQueryClient";
import {
  prefetchGetV2ListStoreAgentsQuery,
  prefetchGetV2ListStoreCreatorsQuery
} from "@/app/api/__generated__/endpoints/store/store";
import { HydrationBoundary, dehydrate } from "@tanstack/react-query";

// In your server component
const queryClient = getQueryClient();

await Promise.all([
  prefetchGetV2ListStoreAgentsQuery(queryClient, {
    featured: true,
  }),
  prefetchGetV2ListStoreAgentsQuery(queryClient, {
    sorted_by: "runs",
  }),
  prefetchGetV2ListStoreCreatorsQuery(queryClient, {
    featured: true,
    sorted_by: "num_agents",
  }),
]);

return (
  <HydrationBoundary state={dehydrate(queryClient)}>
    <MainMarkeplacePage />
  </HydrationBoundary>
);

This pattern improves performance by serving pre-fetched data from the server while maintaining the benefits of client-side React Query features.

Configuration

The Orval configuration is located in autogpt_platform/frontend/orval.config.ts. It generates two separate clients:

1. autogpt_api_client: React Query hooks for client-side data fetching
2. autogpt_zod_schema: Zod schemas for validation

For more details, see the Orval documentation or check the configuration file.

🚚 Deploy

TODO

📙 Storybook

Storybook is a powerful development environment for UI components. It allows you to build UI components in isolation, making it easier to develop, test, and document your components independently from your main application.

Purpose in the Development Process

1. Component Development: Develop and test UI components in isolation.
2. Visual Testing: Easily spot visual regressions.
3. Documentation: Automatically document components and their props.
4. Collaboration: Share components with your team or stakeholders for feedback.

How to Use Storybook

1. Start Storybook: Run the following command to start the Storybook development server:

   pnpm storybook
   

   This will start Storybook on port 6006. Open http://localhost:6006 in your browser to view your component library.

2. Build Storybook: To build a static version of Storybook for deployment, use:

   pnpm build-storybook
   

3. Running Storybook Tests: Storybook tests can be run using:

   pnpm test-storybook
   

4. Writing Stories: Create .stories.tsx files alongside your components to define different states and variations of your components.

By integrating Storybook into our development workflow, we can streamline UI development, improve component reusability, and maintain a consistent design system across the project.

🔭 Tech Stack

Core Framework & Language

• Next.js - React framework with App Router
• React - UI library for building user interfaces
• TypeScript - Typed JavaScript for better developer experience

Styling & UI Components

• Tailwind CSS - Utility-first CSS framework
• shadcn/ui - Re-usable components built with Radix UI and Tailwind CSS
• Radix UI - Headless UI components for accessibility
• Lucide React - Beautiful & consistent icons
• Framer Motion - Animation library for React

Development & Testing

• Storybook - Component development environment
• Playwright - End-to-end testing framework
• ESLint - JavaScript/TypeScript linting
• Prettier - Code formatting

Backend & Services

• Supabase - Backend-as-a-Service (database, auth, storage)
• Sentry - Error monitoring and performance tracking

Package Management

• pnpm - Fast, disk space efficient package manager
• Corepack - Node.js package manager management

Additional Libraries

• React Hook Form - Forms with easy validation
• Zod - TypeScript-first schema validation
• React Table - Headless table library
• React Flow - Interactive node-based diagrams
• React Query - Data fetching and caching
• React Query DevTools - Debugging tool for React Query

Development Tools

• NEXT_PUBLIC_REACT_QUERY_DEVTOOL - Enable React Query DevTools. Set to true to enable.