Open Tutorai: An Open-Source Platform For Personalized And Immersive Learning With Generative AI

Mohamed EL HAJJI, Université Ibn Zohr

Tarek AIT BAHA, Université Ibn Zohr

Aicha DAKIR, Université Ibn Zohr

Hammou FADILI

Youssef ES-SAADY

Date

02/2026

AI Overview

Why it matters

Conventional educational chatbots often lack contextual adaptability, real-time responsiveness, and pedagogical agility, which limits student engagement and learning. Open, integrative platforms combining artificial intelligence and immersive technologies are needed to provide personalized and scalable educational support.

Study at a glance

Question: How can an open-source platform integrate generative artificial intelligence, 3D avatars, and learning analytics for personalized tutoring?
Setting and data: Technical system verification and proof-of-concept testing conducted on Apple Silicon development hardware with 16 GB RAM.
Method: System development and technical performance verification.
AI tools: Open TutorAI, LLaMA 3, GPT-4

Key findings

Technical verification confirmed the system reliably orchestrated personalized tutoring dialogues, synchronized 3D avatar animations, and retrieved relevant curricular knowledge via retrieval-augmented generation.
On an Apple Silicon machine, 3D avatar animations maintained consistently smooth rendering at approximately 120 frames per second across both local and cloud-based setups.
Running LLaMA 3 locally via Ollama required about 4 to 5 GB of RAM and 505% CPU utilization, while cloud-based GPT-4 consumed 84 MB of RAM and 94% CPU.

Summary drafted with AI from the full paper and may contain errors. See the full paper for details.

Recent advances in artificial intelligence have created new possibilities for making education more scalable, adaptive, and learner-centered. However, existing educational chatbot systems often lack contextual adaptability, real-time responsiveness, and pedagogical agility. which can limit learner engagement and diminish instructional effectiveness. Thus, there is a growing need for open, integrative platforms that combine AI and immersive technologies to support personalized, meaningful learning experiences. This paper presents Open TutorAI, an open-source educational platform based on LLMs and generative technologies that provides dynamic, personalized tutoring. The system integrates natural language processing with customizable 3D avatars to enable multimodal learner interaction. Through a structured onboarding process, it captures each learner's goals and preferences in order to configure a learner-specific AI assistant. This assistant is accessible via both text-based and avatar-driven interfaces. The platform includes tools for organizing content, providing embedded feedback, and offering dedicated interfaces for learners, educators, and parents. This work focuses on learner-facing components, delivering a tool for adaptive support that responds to individual learner profiles without requiring technical expertise. Its assistant-generation pipeline and avatar integration enhance engagement and emotional presence, creating a more humanized, immersive learning environment. Embedded learning analytics support self-regulated learning by tracking engagement patterns and generating actionable feedback. The result is Open TutorAI, which unites modular architecture, generative AI, and learner analytics within an open-source framework. It contributes to the development of next-generation intelligent tutoring systems.