PaperBanana is an open-source agentic framework designed to automatically generate publication-quality academic diagrams and statistical plots directly from text descriptions. The project focuses on helping researchers, educators, and data scientists transform conceptual descriptions of figures into structured visual outputs suitable for research papers, presentations, and technical reports. Instead of manually designing charts or diagrams using traditional visualization tools, users can describe the desired figure in natural language and allow the system to generate the visual representation automatically. PaperBanana integrates modern multimodal AI models capable of interpreting instructions and producing graphics that follow academic conventions. The framework supports multiple AI providers including OpenAI, Azure OpenAI services, and Google Gemini, allowing users to run the system with different model backends.
Features
- Agentic framework for generating academic diagrams from text prompts
- Automatic creation of publication-quality statistical plots and figures
- Support for multiple AI providers including OpenAI, Azure, and Gemini
- Natural language interface for describing research visuals
- Tools for generating figures suitable for academic papers and slides
- Extensible pipeline for building automated research visualization workflows