Roadmap

Our vision for DeepTutor's future development.

✅ Recently Completed (v0.4.0)

• [x] RAG Module Decoupling — Modular RAG architecture with provider-agnostic interface
  • Currently supports RAG-Anything (MinerU + LightRAG)
  • More backends coming soon
• [x] Multi-Provider Support — Expanded LLM and Embedding provider options
  • LLM: OpenAI, Anthropic, Azure, Ollama, Groq, OpenRouter, DeepSeek, Gemini
  • Embedding: OpenAI, Jina, Cohere, Ollama, LM Studio, HuggingFace
• [x] Dark Mode — System-wide dark/light theme support
• [x] Environment Configuration — Unified .env based configuration

🚀 Planned Features

• [ ] Deepcoding from Idea Generation — Transform research ideas into working prototypes
• [ ] Personalized Memory — Adapt tutoring style based on user learning history
• [ ] Additional RAG Backends — LlamaIndex, ChromaDB, Pinecone integration
• [ ] More Embedding Adapters — Voyage AI, Mixedbread, local transformers

💭 Under Consideration

• Multi-language support
• Mobile-friendly interface
• Collaborative learning features
• Voice interaction support
• Faster frontend framework

🤝 Community Requests

Have a feature idea? We'd love to hear it!

• Open a Feature Request
• Join the discussion on existing proposals
• Check our GitHub Discussions

---

⭐ Star the repo to follow our future updates!