paperbanana
A framework for generating academic and statistical charts from text descriptions.
- Type
- MCP
- Transport
- stdio
- Open source
- Yes
- GitHub Stars
- ★ 2.0k
- Source
- mcp-github
- Repository
- github.com/llmsresearch/paperbanana
Overview
PaperBanana is an open-source project designed to generate high-quality academic and statistical charts from text descriptions. It supports multiple image generation providers, including OpenAI, Azure OpenAI, Google Gemini, and Atlas Cloud. The tool offers CLI, Python API, and MCP server interfaces for easy integration into IDEs. Additional features include batch generation, PDF input support, and a local Gradio Web UI for visual interaction.
Capabilities
- ▪Multi-agent pipeline iterative optimization
- ▪Support for multiple image generation providers
- ▪Input optimization layer to improve generation quality
- ▪Auto-refinement mode with user feedback for continued execution
- ▪Batch generation of multiple charts
- ▪Batch generation of statistical charts
Use cases
Setup
pip install paperbanana
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How do I get started with PaperBanana?
After installation, run `paperbanana --help` to view help information and configure your API Key.
Which image generation providers are supported?
Supports OpenAI, Azure OpenAI, Google Gemini, and Atlas Cloud.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
sast-skills
Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.
antivibe
Transform AI-generated code into deep learning materials to help developers understand the code.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.