DeepTutor

DeepTutor is an agent-native platform designed to provide personalized, intelligent tutoring through a unified chat workspace and multi-agent architecture. It features advanced capabilities like a Book Engine for interactive learning, an AI Co-Writer, and persistent memory to tailor the experience to individual user profiles. Users can deploy the system easily via a guided CLI setup or Docker, supporting a wide range of LLM and embedding providers.

DeepTutor is an agent-native, personalized tutoring platform designed to transform static learning materials into interactive, autonomous educational experiences. By utilizing a unified architecture that integrates chat, research, visualization, and document management, the project solves the fragmentation common in AI-assisted learning tools. Its design philosophy centers on persistent memory and multi-agent collaboration, allowing users to build a living profile that evolves with their educational journey. The project makes significant technical trade-offs by prioritizing a plugin-based capability model and schema-driven agents, which enables high extensibility while maintaining a cohesive user experience across diverse LLM providers.