# dwzhu-pku/PaperBanana

PaperBanana: Automating Academic Illustration For AI Scientists

Repository: https://github.com/dwzhu-pku/PaperBanana
Canonical: https://ross.abutalabs.com/products/paperbanana
Homepage: https://dwzhu-pku.github.io/PaperBanana/
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-06-25T12:48:17+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 89, release rhythm 35, longevity 15
- inputs: {"age_days": 215, "days_push": 69, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7000, forks 528 (observed 2026-08-28T04:09:52.737051+00:00)

## What it is
PaperBanana is a reference-driven multi-agent framework that automatically generates publication-ready academic illustrations such as methodology diagrams and statistical plots. It orchestrates Retriever, Planner, Stylist, Visualizer, and Critic agents powered by VLMs and image generation models, with iterative self-critique refinement.

## Use cases
- generate methodology diagrams for research papers automatically
- create statistical plots from scientific content
- automate figure creation for academic publications
- find reference illustrations to guide diagram style
- refine AI-generated paper figures via critique loops
- benchmark academic illustration generation with PaperBananaBench

## When to choose
- you need publication-quality diagrams or plots for papers without manual drawing
- you want an open-source, reference-driven agentic pipeline for scientific illustration
- you work with VLMs and image generation models and want an orchestrated multi-agent workflow

## When to avoid
- you need fully reliable, complex illustrations beyond computer science domains
- you require commercial licensing or guaranteed support
- you need offline generation without access to VLM and image generation APIs

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, image-processing, llm-inference, rag, data-visualization
- domain: artificial-intelligence, large-language-models, data-visualization, education
- platform: python, cross-platform
- tags: academic-illustration, scientific-figures, multi-agent, vlm, image-generation, diagram-generation, paper-writing, streamlit-ui, ai-agents, natural-language-processing, web-server

## Member repositories
- dwzhu-pku/PaperBanana (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:52.737051+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:40:48.507466+00:00, confidence not recorded.
  - readme: https://github.com/dwzhu-pku/PaperBanana (fetched 2026-08-28T04:09:52.737051+00:00, sha 4f776b56ea27)
  - homepage: https://dwzhu-pku.github.io/PaperBanana/ (fetched 2026-08-29T08:36:41.443295+00:00, sha dcb6a6c1d128)
- Data as of 2026-08-30T08:39:29.467469+00:00.