THU-MAIC/OpenMAIC
OpenMAIC
OpenMAIC is an LLM multi-agent education platform designed to create immersive, interactive classroom simulations. It functions as a learning environment where multiple AI agents collaborate through a state-machine orchestration framework to coordinate conversational turns and interactions.
The platform features an AI-driven interactive lesson generator that transforms documents and topics into educational experiences including slides, quizzes, and project activities. It integrates a speech-enabled interface that combines speech-to-text and text-to-speech for voice-based interaction, alongside an in-browser 3D simulation environment for rendering interactive scenes and real-time whiteboard concepts.
The system includes capabilities for educational content generation, voice learning through voice cloning, and virtual instructional tooling for managing digital whiteboards and diagrams. Additional functionality covers OCR-based document parsing for extracting data from PDFs and access control mechanisms using passwords and authentication codes.
Features
- Interactive 3D Simulators - Builds responsive, in-browser 3D simulations that allow for hands-on exploration of complex educational processes.
- Multi-Agent Education Platforms - Provides a learning environment where multiple AI agents collaborate to provide immersive, interactive classroom simulations.
- Multi-Agent Collaboration Systems - Creates immersive educational environments where multiple AI agents collaborate to teach and guide students.
- Multi-Agent Session Facilitators - Coordinates and manages interactive group dialogues between multiple AI characters within a simulated classroom session.
- LLM Provider Adapters - Implements a modular adapter layer to flexibly source intelligence from various LLM providers and search tools.
- LLM Provider Integrations - Provides configurable adapters and authentication for connecting the platform to various external large language model providers.
- Multi-Agent Orchestration Frameworks - Implements a state-machine based manager that coordinates conversational turns and interactions between multiple AI agents.
- Speech-to-Text Conversions - Transforms live microphone input into machine-processable text to enable communication with the AI agents.
- Text-to-Speech Synthesis - Synthesizes natural-sounding spoken audio from text using automated voice providers and voice cloning.
- Educational Content Generation - Transforms documents and topics into structured course outlines, interactive slides, and quizzes using LLMs.
- Lesson Plan Generators - Transforms documents and topics into educational experiences containing slides, quizzes, and project activities.
- Virtual Classroom Software - Manages AI agent interactions, speech-to-text conversion, and 3D visualizations to build a responsive digital learning space.
- Autonomous AI Agent Simulations - Creates learning environments where multiple AI agents collaborate to provide an immersive educational experience.
- Educational Classroom Simulations - Provides immersive learning environments using AI agent simulations and 3D visualizations for hands-on education.
- Educational 3D Environments - Provides an in-browser visualization tool for rendering interactive 3D scenes and real-time whiteboard concepts.
- 3D Simulation Rendering - Renders interactive browser-based 3D environments to visualize educational concepts and AI agent activities.
- Conversational Voice Pipelines - Facilitates verbal interaction with AI agents by processing spoken audio through integrated speech-to-text and text-to-speech services.
- Conversation State Machines - Uses a deterministic state machine to coordinate conversational turns and dialogue flow between multiple AI agents.
- Content Generators - Transforms raw information into structured course outlines and slides via an AI-driven generation process.
- Generative Content Pipelines - Employs a generative pipeline that builds high-level outlines before populating detailed educational content and slides.
- Educational Voice Interfaces - Integrates text-to-speech and voice cloning to provide narrated, spoken educational experiences within a virtual environment.
- Speech-to-Speech Frameworks - Combines speech-to-text and text-to-speech for voice-based interaction with large language models.
- Voice Cloning - Supports replicating specific human vocal characteristics to provide personalized narration for educational content.
- Educational Scene Generators - Produces immersive educational scenes by generating structured outlines and corresponding detailed instructional content.
- Concept Visualization Techniques - Renders real-time diagrams, formulas, and flowcharts on a digital whiteboard to visually illustrate complex ideas.
- Virtual Instructional Actions - Performs instructional tasks such as drawing on whiteboards, creating charts, and using visual spotlights to guide students.
- Virtual Instructional Tooling - Uses AI to control digital whiteboards, generate real-time diagrams, and create visual spotlights for remote teaching.
