CircleBack

A voice-powered networking platform that helps you manage professional relationships through a knowledge graph. Track contacts, events, and connections — then explore them via a 3D graph visualization or conversational voice agent.

Tech Stack

• Frontend: Next.js 16, React 19, Tailwind CSS, shadcn/ui, react-force-graph-3d
• Backend: FastAPI, Motor (async MongoDB driver), Pydantic
• Database: MongoDB 7
• Voice: ElevenLabs Conversational AI + TTS
• Infra: Docker Compose

Quick Start

Prerequisites

• Docker and Docker Compose

1. Clone and configure

git clone https://github.com/Alienware2000/CircleBack.git
cd CircleBack

Create a .env file in the project root:

ELEVENLABS_API_KEY=your_key_here
GOOGLE_API_KEY=your_key_here

These keys are optional — the app runs without them, but the voice agent and TTS features will be disabled.

2. Start everything

docker compose up --build

This launches three services:

Service	URL
Frontend	http://localhost:3000
Backend	http://localhost:8111
MongoDB	mongodb://localhost:27017

3. Seed sample data (optional)

curl -X POST http://localhost:8111/api/seed

To clear all data:

curl -X DELETE http://localhost:8111/api/seed

API

The backend serves REST endpoints under /api:

• /api/contacts — CRUD for contacts
• /api/relationships — manage connections between contacts
• /api/events — networking events
• /api/interactions — logged interactions
• /api/graph — knowledge graph queries
• /api/chat/signed-url — get a signed WebSocket URL for the ElevenLabs voice agent
• /api/tts — text-to-speech proxy

Interactive docs available at http://localhost:8111/docs once the backend is running.

Local Development (without Docker)

Backend

cd backend
python -m venv venv && source venv/bin/activate
pip install -r requirements.txt
cp .env.example .env   # edit with your values
uvicorn app.main:app --reload --port 8000

Frontend

cd frontend
pnpm install
NEXT_PUBLIC_API_URL=http://localhost:8000 pnpm dev

Requires a MongoDB instance running on localhost:27017.