https://github.com/clerk/agent-toolkit-example

An example repo using the Clerk Agent Toolkit to build a simple chatbot
https://github.com/clerk/agent-toolkit-example

Last synced: 3 months ago
JSON representation

An example repo using the Clerk Agent Toolkit to build a simple chatbot

• Host: GitHub
• URL: https://github.com/clerk/agent-toolkit-example
• Owner: clerk
• Created: 2025-02-11T10:03:31.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2025-03-12T10:47:58.000Z (over 1 year ago)
• Last Synced: 2025-03-12T11:27:55.437Z (over 1 year ago)
• Language: TypeScript
• Size: 85.9 KB
• Stars: 0
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          


  

    

      

      

    

  

  


  
Clerk Agent Toolkit Example




[![Chat on Discord](https://img.shields.io/discord/856971667393609759.svg?logo=discord)](https://clerk.com/discord)

[![Clerk documentation](https://img.shields.io/badge/documentation-clerk-green.svg)](https://clerk.com/docs?utm_source=github&utm_medium=clerk_agent_toolkit)

[![Follow on Twitter](https://img.shields.io/twitter/follow/ClerkDev?style=social)](https://twitter.com/intent/follow?screen_name=ClerkDev)

[Changelog](https://github.com/clerk/javascript/blob/main/packages/agent-toolkit/CHANGELOG.md)

·

[Report a Bug](https://github.com/clerk/javascript/issues/new?assignees=&labels=needs-triage&projects=&template=BUG_REPORT.yml)

·

[Request a Feature](https://feedback.clerk.com/roadmap)

·

[Get Help](https://clerk.com/contact/support?utm_source=github&utm_medium=clerk_agent_toolkit)



# Important - Work in progress

This repository and the @clerk/agent-toolkit package are still in development and the public API is subject to change.

## Introduction

In this project, you will build a simple chatbot that updates the signed-in user's metadata with knowledge from the discussion, similar to the ChatGPT "Memory" feature. When asked, the chatbot will only respond with the information it knows about the current user. The chatbot will be able to both store and retrieve information.

## Getting Started

1. Clone this repository.

2. Copy `.env.example` to `.env.local` and fill in the required environment variables.

3. Run `pnpm install` to install the dependencies.

4. Run `pnpm dev` to start the development server.

## Navigating the app

The app was kept as simple as possible to focus on the agent toolkit integration. The main components are:

- `app/api/ai-sdk/route.ts` and `app/ai-sdk/page.tsx`: The Vercel AI SDK integration.

- `app/api/agent-toolkit/route.ts` and `app/agent-toolkit/page.tsx`: The Clerk Agent Toolkit integration.

## Vercel AI SDK RAG Guide Starter Project

This repo is a simplified version of the [Vercel AI SDK RAG Guide Starter Project](https://sdk.vercel.ai/docs/guides/rag-chatbot). For more details, visit the [Vercel AI SDK documentation](https://sdk.vercel.ai/docs/introduction).