# AutoFigure

Repository: https://github.com/ResearAI/AutoFigure
Canonical: https://ross.abutalabs.com/products/autofigure
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2026-06-26T10:50:54+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 89, release rhythm 35, longevity 18
- inputs: {"age_days": 259, "days_push": 68, "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 1845, forks 137 (observed 2026-08-28T04:05:43.382802+00:00)

## What it is
AutoFigure-Edit is a Python application that converts scientific paper method sections into fully editable SVG figures using large language models, with an embedded SVG editor for refinement. It is the successor to AutoFigure and includes a web interface and a FigureBench dataset.

## Use cases
- generate editable SVG figures from paper method text
- create scientific illustrations for research papers
- refine auto-generated paper figures in an SVG editor
- turn method descriptions into publication-ready diagrams
- benchmark figure generation models with FigureBench

## When to choose
- you need editable vector figures for academic papers rather than raster images
- you want to automate illustration creation from method section text
- you prefer an open-source, self-hosted figure generation tool

## When to avoid
- you need general-purpose image editing or photo manipulation
- you want non-scientific or artistic illustration generation
- you require offline use without access to LLM APIs

## Facets
- artifact type: application
- maturity: active
- function: image-processing, llm-inference, data-visualization, machine-learning
- domain: artificial-intelligence, large-language-models, documentation, education
- platform: python, cross-platform
- tags: scientific-illustration, svg-generation, figure-generation, text-to-svg, academic-writing, figure-editing, research-tools, natural-language-processing, web-server

## Member repositories
- ResearAI/AutoFigure (main) score 56
- ResearAI/AutoFigure-Edit (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:43.382802+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 2026-08-29T18:22:55.200161+00:00, confidence not recorded.
  - readme: https://github.com/ResearAI/AutoFigure (fetched 2026-08-28T04:05:43.382802+00:00, sha 3332a2015eed)
- Data as of 2026-08-30T08:39:29.467469+00:00.