ForkFree

Images and design

paperbanana

by llmsresearch

PaperBanana is an unofficial open-source Python tool that turns a text description of a method into publication-style academic diagrams and statistical plots. It uses a multi-agent pipeline with image-generating AI models and can be run from the command line, a Python API, a local web interface or an MCP server.

Proof level: ReadWorth a lookMIT

Get it on GitHubCompare

No demo yet

Proof level: Read. We read its README and licence and ran our automatic checks. We have not run it yet. So this page is based on its README and our automatic checks.

The catch

Worth a lookEstablished, with a few things to check (listed below).

Check this first: Needs a paid or quota-limited API key from an AI provider, and costs rise with iterative refinement.

Things to check

  • Needs a paid or quota-limited API key from an AI provider, and costs rise with iterative refinement
  • Unofficial implementation, not affiliated with the original authors, so results may differ from the paper
  • AI-generated figures need careful checking for accuracy before publication

Can you use paperbanana commercially?

Free to use, change and sell, including in paid products. Keep the copyright notice.

Not legal advice. Read the project's licence file before building a product on it.

What can you do with paperbanana?

  • Generate a methodology diagram from a text description and a caption
  • Create statistical plots in bulk from CSV or JSON data using a manifest file
  • Refine and compare figures through the local Studio web interface or Claude Code slash commands

How do you get paperbanana running?

Install with pip install paperbanana (or build the Docker image), then add an OpenAI, Azure, Gemini or Atlas Cloud API key to a .env file.

Follow the official instructions in the project README.

Make money with it

A freelancer could offer fast figure and diagram preparation to academics and students, using the tool for first drafts and polishing the results by hand.

An idea, not financial advice. Check the licence before charging for anything built on it.

Ways a business could use it

  • Produce figures and diagrams for reports, white papers and grant applications without paying a designer
  • Offer figure preparation for papers, theses and slide decks as a freelance service

Who's talking about it

Checked 11 Nov 2026. Summary drafted by AI from the project's README. Proof level 1 of 4, Read: we read its readme and licence and ran our automatic checks. we have not run it yet.

Similar tools in Images and design

photocraft storytold
New and promising

PhotoCraft is an open-source photo editor written in Rust, offering a clean-room reimplementation of Adobe Photoshop's features, including layers, masks, and adjustment layers, all in a native app.

Instead of Adobe PhotoshopUp to £264 a year

Proof level: Read 80.6k stars +293 a day Apache-2.0
anatomy wheresryan22
New and promising

Anatomy is a tool that generates detailed, interactive isometric illustrations of real-world machines and complex systems, creating polished SVGs with optional WebGL shaders and 3D effects.

Instead of Claude Code, Antigravity

Proof level: Read 28.3k stars +292 a day MIT
solidcraft tangency-labs
New and promising

SolidCraft is an open-source parametric 3D CAD application built in Rust, allowing users to sketch, constrain, and build 3D models with a parametric feature timeline.

Instead of FreeCAD, Onshape

Proof level: Read 17.4k stars +263 a day Apache-2.0