Compass

Realtime Voice AI Recruiter Built With Tanstack Start, Convex and OpenAI.

This project uses the OpenAI Agents SDK, a toolkit for building, managing, and deploying advanced AI agents.

• Comprehensive candidate and jobs management with AI-powered workflows
• Multi-stage real-time AI voice interview system with seamless agent handoffs
• Public interview sharing with candidate onboarding flow and progress tracking
• AI-powered talent sourcing and matching with verified profiles
• Smart job creation with optimized descriptions and automated hiring pipelines
• Real-time transcript analysis and interview performance insights

NOTE: ❗ This project is in very early development and lots of things will change.

Features · Model Provider · Deploy Your Own · Running locally

Features

• Tanstack Start
  • File-based routing, type-safe from server to client
  • Built on Vite for a lightning-fast HMR development experience
• OpenAI
  • Leverages OpenAI's powerful models for generation.
  • Direct API calls for text generation and other AI features.
• Shadcn/UI
  • Styling with Tailwind CSS
  • Component primitives from Radix UI for accessibility and flexibility
• Convex
  • Real-time database for storing user profiles, job listings, and application data
  • Optimized file storage with automatic caching and CDN distribution
• Convex Auth
  • Simple and secure authentication without external services
  • Built-in support for magic links, OTPs, OAuth, and password authentication

Model Provider

This app utilizes the OpenAI API for its AI capabilities. You will need to provide your own OpenAI API key in the environment variables.

Deploy Your Own

You can deploy your own version of the OpenChat to Vercel with one click:

Running locally

You will need to use environment variables to run Compass. It's recommended you use Vercel Environment Variables for this, but a local .env file is also sufficient.

Note: You should not commit your .env file as it may expose secrets that could compromise your accounts.

1. Install dependencies:

bun install

2. If using Vercel for environment variables: a. Install Vercel CLI: bun i -g vercel b. Link local instance: vercel link c. Download environment variables: vercel env pull

3. Start the development server:

bun dev

Your app should now be running on localhost:3000.