I wanted to experiment with LLM tutoring for my kids, but ChatGPT etc. doesn't have a good enough memory or ability to add long-term learning goals. So I made a LLM wrapper that runs locally with a web interface and uses memory files in the background to manage a dynamic lesson plan and details about the student's preferences and learning style. Screenshots at https://github.com/MGensheimer/seneca-tutor?tab=readme-ov-fi... The memory is stored as text files and it's fun to see the lesson plan get updated over time. It's a quick install on Mac or Linux. Uses Python and Flask, and you'll need an Anthropic API key. Would love to hear any feedback or how you used it! |
No comments yet