AI Receptionist
- 17
- Stars
- 8
- Forks
- Voice
- Real-time agent
Interface illustration — [ADD REAL PROJECT SCREENSHOT]
Project details
- Type
- Open source
- Category
- AI / Voice
- Status
- Live
Technology
- Python
- Claude SDK
- Speech-to-text
- Telephony APIs
Services involved
Overview
An open source AI-powered appointment-booking voice agent built with the Claude SDK. It answers an inbound call, holds a real conversation, and books the appointment.
Published openly because voice agents are widely demoed and rarely shown working end to end — including the parts that break, like interruption handling and structured booking.
The challenge
Voice agent demos are easy; voice agents that book a real appointment are not. The gap is in turning free-form speech into a structured booking and handling the moments where the caller cuts across the agent.
Most published examples handle the happy path and nothing else.
The solution
Real-time speech handling wired to a conversational agent with a defined booking flow, so the conversation produces structured data rather than a transcript.
Appointment logic separated from the conversation layer, which makes the agent testable and the booking rules changeable without touching the voice pipeline.
Key features
- Real-time inbound voice conversation
- Structured appointment booking from natural speech
- Built on the Claude SDK
- Open source and forkable
Outcome
- 17 stars and 8 forks on GitHub.
- Published as a working reference for production voice agents.
Other projects
- E-commerce / AIClient engagementLive
Yoon Lab
369 Korean skincare products across 30+ brands, sold online and in physical stores across Mexico — filtered by skin concern, with a shoppable video feed and AI skin analysis.
Case study - ERP / OperationsClient engagementLive
Logistika Urbana ERP
The full back office behind the storefront — inventory, purchasing, orders, finance and a custom POS, all running off one synced system.
Case study - AI / AgTechClient engagementLive
SYBAL
Turning agricultural AI models into production APIs — the engineering layer between a research notebook and a product customers use.
Case study
Have a project in mind?
Let's build something useful. Tell us what you're trying to achieve and we'll come back with an honest view of what it takes.
Within 1–2 business days · Working with clients in the United States and internationally