#conversational-ai

An Agentic RAG-powered chatbot delivering intelligent, fact-grounded and context-aware answers for the DIEM Department at the University of Salerno.

The zero-friction, one-command pipeline for WhatsApp Voice AI

Give your AI agent a talking, lip-syncing face — 12-emotion particle face, in-browser Whisper (WebGPU), bring-your-own-agent bridge. MIT.

Open-source multilingual evaluation toolkit for conversational AI agents.

AI-powered multilingual chatbot for real-time text translation and conversational interaction across multiple languages.

Case study: live AI consultant — typed conversation graph, source-grounded knowledge, reviewer-gated utterances, in-process cost guardian.

Hub for AI engineering case studies: multi-agent orchestration, RAG, browser automation, observability + evaluation.

AI Automated Car Rental Booking via Telegram

AI-powered Voice & Text Chatbot built using Python, Streamlit, Hugging Face DialoGPT, and Deep Learning. Supports conversational memory, multiple chats, voice input, chat export, and real-time response generation.

An instruction-tuned conversational chatbot (Qwen2.5-0.5B-Instruct) with multi-turn memory, feedback-driven continuous learning, and a full MLOps pipeline (MLflow, FastAPI, GitHub Actions CI/CD) — DEPI Generative AI capstone project.

A full-stack web-based voice assistant built with Python and Flask. Integrates OpenAI's GPT for intelligent conversational responses and IBM Watson Speech Libraries for Embed for seamless speech-to-text (STT) and text-to-speech (TTS) processing.

Replace Claudesona emotion tags with flower-headed sprites in your Claude.ai chat interface using this Chrome extension.

Keep It Real — a schema-level deferral channel that makes LLM brevity safe. Code, data, and pre-registered protocols: a 400-conversation replication sweep, a placebo control, and a blinded human study (n=46).

AI-powered movie recommendation chatbot built using Landbot.

Multi-agent AI customer support system — Pinecone hybrid RAG, SLA-aware ticketing, and RAGAS evaluation on FastAPI + Streamlit

Open-source orchestration for AI conversation → AI coding agents → GitHub review, with recoverable handoffs, configurable automation, and privacy-conscious provenance.

Por donde entran tus datos. Ingesta conversacional sobre DuckDB: la IA diseña la carga, el SQL la ejecuta sola. / Conversational data ingestion on DuckDB. The AI designs the load; SQL runs it. Local-first, no cloud. Local, sin nube, sin servidor.