TIGER-AI-Lab/TheoremExplainAgent
An AI agent system that generates Manim animation videos to visually explain mathematical theorems using LLMs.

TheoremExplainAgent is a multimodal AI system that generates long-form Manim animation videos to explain mathematical theorems, demonstrating deep LLM understanding while uncovering reasoning gaps that text-only explanations miss. The system leverages retrieval-augmented generation (RAG) and LLM agent techniques to produce and evaluate video-based explanations. The codebase includes generation code, evaluation metrics, and a dataset of theorem-video pairs for benchmarking.
Frequently asked
- What is TIGER-AI-Lab/TheoremExplainAgent?
- An AI agent system that generates Manim animation videos to visually explain mathematical theorems using LLMs.
- Is TheoremExplainAgent open source?
- Yes — TIGER-AI-Lab/TheoremExplainAgent is open source, released under the MIT license.
- What language is TheoremExplainAgent written in?
- TIGER-AI-Lab/TheoremExplainAgent is primarily written in Python.
- How popular is TheoremExplainAgent?
- TIGER-AI-Lab/TheoremExplainAgent has 1.5k stars on GitHub.
- Where can I find TheoremExplainAgent?
- TIGER-AI-Lab/TheoremExplainAgent is on GitHub at https://github.com/TIGER-AI-Lab/TheoremExplainAgent.