Agentica

The simplest Agentic AI library, specialized in LLM Function Calling.

Don't compose complicate agent graph or workflow, but just deliver Swagger/OpenAPI documents or TypeScript class types linearly to the agentica. Then agentica will do everything with the function calling.

Look at the below demonstration, and feel how agentica is easy and powerful.

import { Agentica } from "@agentica/core";
import typia from "typia";

const agent = new Agentica({
  controllers: [
    await fetch(
      "https://shopping-be.wrtn.ai/editor/swagger.json",
    ).then(r => r.json()),
    typia.llm.application<ShoppingCounselor>(),
    typia.llm.application<ShoppingPolicy>(),
    typia.llm.application<ShoppingSearchRag>(),
  ],
});
await agent.conversate("I wanna buy MacBook Pro");

shopping-chat-summary.mp4

Demonstration video of Shopping AI Chatbot

Playground

You can experience how typia works by playground website:

💻 https://wrtnlabs.io/agentica/playground

Guide Documents

Check out the document in the website:

🏠 Home

• 🚀 Getting Started
• 📦 Setup
• 🔍 Concepts
  • Function Calling
  • Compiler Driven Development
  • Document Driven Development

📖 Features

• 📚 Core Library
  • Agentic AI
  • Facade Controller
  • Configurations
  • Event Handling
  • Prompt Histories
• 📡 WebSocket Protocol
  • Remote Procedure Call
  • NestJS Server
  • NodeJS Server
  • Client Application
• 🌉 Plugin Modules
  • Benchmark Program
  • OpenAI Vector Store
  • PG Vector Selector

🔗 Appendix

• 📅 Roadmap
• 📊 Related Projects
  • Agent OS
  • AutoView
• ⇲ API Documents

How to Contribute?

Please refer to the CONTRIBUTING.md file for more information.

Thank you for your interest in contributing to Agentica!