AutoBE - No-Code Agent for Backend Applications

flowchart
subgraph "Backend Coding Agent"
  coder("Facade Controller")
end
subgraph "Functional Agents"
  coder --"Requirements Analysis"--> analyze("Analyze")
  coder --"ERD"--> prisma("Prisma")
  coder --"API Design"--> interface("Interface")
  coder --"Test Codes" --> test("Test")
  coder --"Main Program" --> realize("Realize")
end
subgraph "Compiler Feedback"
  prisma --"validates" --> prismaCompiler("Prisma Compiler")
  interface --"validates" --> openapiValidator("OpenAPI Validator")
  interface --"generates" --> tsCompiler("TypeScript Compiler")
  test --"validates" --> tsCompiler("TypeScript Compiler")
  realize --"validates" --> tsCompiler("TypeScript Compiler")
end

Loading

An AI-powered no-code agent that builds backend applications, enhanced by compiler feedback.

@autobe is a no-code AI agent that analyzes user requirements and automatically generates backend applications using the stack below, following a waterfall development model. Since @autobe-generated code is validated by review agents and OpenAPI/TypeScript/Prisma compilers, it delivers 100% working code.

• TypeScript
• NestJS
• Prisma (Postgres / SQLite)

Playground

autobe-palyground-demo.mp4

https://stackblitz.com/github/wrtnlabs/autobe-playground-stackblitz

Experience the @autobe agent through our interactive playground above.

The current alpha version of @autobe supports up to the Interface step, with full features planned for the beta release. In the official release, you'll be able to experience full-stack development by integrating with @agentica and @autoview.

To see examples of backend applications generated by @autobe, explore these interactive demos. These showcase @autobe's ability to generate production-ready backend code with proper structure, API documentation, and TypeScript interfaces. If you're unsure what to try, start with the BBS example script below.

• BBS (Bulletin Board System)
  1. I want to create a political/economic discussion board. Since I'm not familiar with programming, please write a requirements analysis report as you see fit.
  2. Design the database schema.
  3. Create the API interface specification.
• E-Commerce

Documentation Resources

Find comprehensive resources at our official website.

🏠 Home

• 🙋🏻‍♂️ Introduction
• 📦 Setup
• 🔍 Concepts
  • Waterfall Model
  • Compiler Strategy
  • AI Function Calling

📖 Features

• 🤖 Agent Library
  • No-Code Agent
  • Configuration
  • Event Handling
  • Prompt Histories
• 📡 WebSocket Protocol
  • Remote Procedure Call
  • NestJS Server
  • NodeJS Server
  • Client Application
• 🛠️ Backend Stack
  • TypeScript
  • Prisma ORM
  • NestJS Framework

🔗 Appendix

• 🌐 No-Code Ecosystem
• 📅 Roadmap
  • Alpha Release (completed)
  • Beta Release (in progress)
  • v1.0 Official Release (planned)
• 🔧 API Documentation

No-Code Ecosystem

A 70-year-old grandmother who grows tomatoes in the countryside created an online debate website in just 10 minutes. Despite being unfamiliar with coding or computers, she built this current affairs and economics discussion community simply by talking with Wrtn's AI. What's remarkable is that users can write posts and comments entirely through voice commands and even engage in current affairs debates with AI.

The next day, the grandmother spent another 20 minutes launching an agricultural products shopping mall. Customers can simply say "I'd like to order 2kg of tomatoes" to complete their purchase, while the grandmother manages everything from orders and shipping to inventory through simple chat conversations.

This is the vision that we, the WrtnLabs team, are pursuing. We aim to create a world where anyone can build backend servers, AI chatbots, and frontend applications without any coding knowledge—simply by conversing with AI.

To realize this vision, the WrtnLabs team is developing two additional projects: @agentica and @autoview.

• @agentica: Automatically creates AI chatbots when you provide a swagger.json file
• @autoview: Automatically generates frontend applications when you provide a swagger.json file

You're not limited to just creating backends with @autobe. Once you've built a no-code backend application through @autobe, you can immediately create an AI chatbot and frontend applications alongside it.

Can you converse? Then you're a full-stack developer.

import { Agentica, assertHttpController } from "@agentica/core";
import OpenAI from "openai";
import typia from "typia";

import { MobileFileSystem } from "./services/MobileFileSystem";

const agent = new Agentica({
  vendor: {
    api: new OpenAI({ apiKey: "********" }),
    model: "gpt-4o-mini",
  },
  controllers: [
    // functions from TypeScript class
    typia.llm.controller<MobileFileSystem, "chatgpt">(
      "filesystem",
      MobileFileSystem(),
    ),
    // functions from Swagger/OpenAPI
    assertHttpController({
      name: "shopping",
      model: "chatgpt",
      document: await fetch(
        "https://shopping-be.wrtn.ai/editor/swagger.json",
      ).then(r => r.json()),
      connection: {
        host: "https://shopping-be.wrtn.ai",
        headers: { Authorization: "Bearer ********" },
      },
    }),
  ],
});
await agent.conversate("I wanna buy MacBook Pro");

Roadmap Schedule

gantt
  dateFormat YYYY-MM-DD
  title Three-Month Roadmap for Production

  section Analyze Agent
  Debate Enhancement: done,    2025-06-01,  7d
  Prefix Rule:          active,  2025-06-12,  7d
  Multimodal:           planned, 2025-07-02, 31d

  section Prisma Agent
  Compiler Development: done,    2025-06-01, 14d
  Prohibition Rule:     done,    2025-06-08,  7d
  SQLite Support:       planned, 2025-06-16,  7d

  section Interface Agent
  Keyworded SDK:  done,    2025-06-01, 10d
  Authorization:  planned, 2025-06-19, 18d
  Snapshot Logic: planned, 2025-06-23, 14d
  Review Agent:   planned, 2025-07-02, 30d

  section Test Agent
  Scenario Agent:       active, 2025-06-01, 10d        
  Coding Agent:         done,   2025-06-12, 14d
  Compiler Feedback:    done,   2025-06-12, 14d
  Function Calling:     done,   2025-06-18, 14d
  Compiler Development: crit,   2025-07-02, 60d

  section Realize Agent
  Planner Agent:      planned, 2025-07-02, 30d
  Coding Agent:       planned, 2025-07-02, 30d
  Compiler Feedback:  planned, 2025-07-17, 15d
  Function Calling:   planned, 2025-07-17, 31d
  Runtime Validation: planned, 2025-08-01, 30d

  section Complementation
  Benchmark:     planned, 2025-06-12, 50d
  Demonstration: active,  2025-06-16, 14d
  Documentation: done,    2025-06-16, 45d
  Articles:      active,  2025-07-02, 61d
  Review Agent:  planned, 2025-07-02, 45d
  Maintenance:   planned, 2025-08-01, 30d

  section Ecosystem
  Agentica Prerequisite:  planned, 2025-06-18, 13d
  WebSocket Streaming:    planned, 2025-07-02, 14d
  History Manipulation:   planned, 2025-07-16, 30d
  AI Chatbot Development: planned, 2025-07-16, 30d
  Data Seeder Agent:      planned, 2025-08-01, 30d

Loading

@autobe's comprehensive three-month beta development roadmap spans from 2025-06-01 through 2025-08-31, marking a critical phase in our journey toward production readiness.

Following the successful completion of our alpha release on 2025-05-31, we have established a robust foundation with fully developed Analysis, Prisma, and Interface Agents. These core components have successfully automated the most complex challenges in backend development: comprehensive requirements analysis, intelligent database architecture, and seamless API design. This achievement represents a significant milestone in our mission to completely automate backend application design.

The upcoming beta phase strategically focuses on delivering and refining the Test Agent and Realization Agent while ensuring system-wide stability and performance optimization across the entire @autobe ecosystem. Our ambitious target for 2025-08-31 is to achieve a breakthrough: a 100% reliable No-Code Agent platform that can autonomously handle any backend application development challenge without human intervention.