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.

Agentica

@autobe is also built using @agentica

GitHub: https://github.com/wrtnlabs/agentica 

Agentica is an agentic AI framework specialized in AI Function Calling.

It performs everything through function calling and brings functions from the following three protocols:

• TypeScript Class/Interface
• Swagger/OpenAPI Document
• MCP (Model Context Protocol) Server

When you provide the swagger.json file of a backend server generated by @autobe, it directly becomes an AI chatbot that interacts with that server.

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");

AutoView

GitHub: https://github.com/wrtnlabs/autoview 

AutoView is a frontend automation tool that generates React component code from type information from the following sources:

• TypeScript Type
• JSON Schema (OpenAPI Document)

When you provide the swagger.json file of a backend server generated by @autobe, it directly becomes a frontend application.

Usage Example

import { AutoViewAgent } from "@autoview/agent";
import fs from "fs";
import OpenAI from "openai";
import typia, { tags } from "typia";
 
// 1. Define your TypeScript interface to display
interface IMember {
  id: string & tags.Format<"uuid">;
  name: string;
  age: number & tags.Minimum<0> & tags.Maximum<100>;
  thumbnail: string & tags.Format<"uri"> & tags.ContentMediaType;
}
 
// 2. Set up the AutoView agent
const agent = new AutoViewAgent({
  model: "chatgpt",
  vendor: {
    api: new OpenAI({ apiKey: "********" }),
    model: "o3-mini",
    isThinkingEnabled: true,
  },
  input: {
    type: "json-schema",
    unit: typia.json.unit<IMember>(),
  },
  transformFunctionName: "transformMember",
  experimentalAllInOne: true, // recommended for faster and fewer errors
});
 
// 3. Generate the result!
const result = await agent.generate(); 
await fs.promises.writeFile(
  "./src/transformers/transformMember.ts",
  result.transformTsCode,
  "utf8",
);