This repository is a production-grade application for building real-time voice agents, primarily designed as an educational course but structured for actual deployment. It implements a complete voice call center system capable of receiving and making phone calls via Twilio, transcribing speech using various STT models (Moonshine, Whisper, Faster Whisper), reasoning with LLMs (Groq), searching property data using Superlinked and Qdrant, and generating speech using TTS models (Kokoro, Orpheus). The architecture is a modular monolith built with FastAPI, utilizing Docker for containerization and RunPod for GPU-accelerated model inference. While the repository includes Jupyter notebooks for educational purposes (Lesson 1-4), the core value lies in the `src/realtime_phone_agents` package, which encapsulates the agent logic, avatar system, and infrastructure integrations. The code demonstrates high craftsmanship in handling async audio streaming, managing external API dependencies, and implementing a flexible avatar registry system. It is suitable for engineers looking to build voice AI applications or understand the integration of LLMs with real-time audio pipelines.
Alumnet is a full-stack, AI-powered alumni exhibition and management system designed for school history museums. It consists of three workspaces: a touch-screen kiosk frontend (client) built with Vue 3, Three.js, and Tailwind CSS; an admin dashboard (admin) using Vue 3 and Element Plus; and a backend server (server) built with Express, TypeScript, PostgreSQL (with pgvector), and Qdrant for vector search. The system provides alumni CRUD, AI-powered natural language search via RAG, 3D galaxy visualization, timeline corridor, interactive message boards, video greetings, donation management, and comprehensive admin controls including content audit, backup/restore, and data import. It features JWT authentication with role-based access, privacy data masking, rate limiting, and a layered architecture (routes → services → repositories). The codebase includes extensive testing (unit, integration, property-based with fast-check) and is deployable via Docker Compose or PM2. While primarily an application, it incorporates data engineering patterns through its RAG pipeline and knowledge base management.
KEA Research is a full-stack multi-provider AI research chat application. The backend is a FastAPI service backed by SQLite/SQLAlchemy, exposing chat, admin, health, user, and TTS endpoints. The frontend is an Astro + TypeScript single-page app that stores chat history and pipeline data in IndexedDB, with a Bootstrap-based UI. Deployment is containerized via Docker Compose with nginx handling TLS and SSE-friendly proxying. The core product logic is a four-step research pipeline: initial multi-provider responses, Mixture-of-Agents refinement, peer evaluation, and a final KEA synthesis with facts, consensus, flagged claims, rankings, and confidence scores. A web admin panel manages providers, models, provider sets, users, and app settings, while the frontend supports research layers, bookmarks, notes, drafts, export, attachment ingestion, and text-to-speech via a Kokoro ONNX model.