# gavrielc/Nano-PDF

Edit PDF files with Nano Banana

Repository: https://github.com/gavrielc/Nano-PDF
Canonical: https://ross.abutalabs.com/products/nano-pdf
Language: Python
License: MIT
License Family: permissive
Last push: 2025-12-03T10:27:32+00:00

## Health v2 (maintenance only)
Score: 41/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 55, release rhythm 35, longevity 19
- inputs: {"age_days": 278, "days_push": 273, "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 1321, forks 86 (observed 2026-08-28T04:04:21.859358+00:00)

## What it is
A Python CLI tool that edits PDF slides using natural language prompts, powered by Google's Gemini 3 Pro Image model. It renders pages to images, applies AI-generated edits, and preserves the searchable text layer via OCR re-hydration.

## Use cases
- edit pdf slides with natural language
- change text in a pdf deck without losing selectable text
- generate new slides matching an existing deck's style
- batch edit multiple pdf pages in parallel
- update charts and taglines in pitch decks

## When to choose
- you need quick AI-driven edits to presentation PDFs
- you want to preserve searchable/selectable text in edited PDFs
- you prefer a simple pip-installable CLI workflow

## When to avoid
- you need precise, deterministic PDF layout editing
- you cannot use a paid Google Gemini API key
- you need to edit scanned PDFs without a text layer or non-slide documents

## Facets
- artifact type: cli-tool
- maturity: active
- function: pdf, ocr, image-processing, cli, llm-inference
- domain: pdf, artificial-intelligence, developer-tools
- platform: cli, python, cross-platform
- tags: pdf-editing, gemini, nano-banana, slides, presentations, natural-language-editing, ocr-rehydration, command-line

## Member repositories
- gavrielc/Nano-PDF (main) score 41

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:21.859358+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 2026-08-30T04:47:17.473536+00:00, confidence not recorded.
  - readme: https://github.com/gavrielc/Nano-PDF (fetched 2026-08-28T04:04:21.859358+00:00, sha a91f768f0110)
  - registry_pypi: https://pypi.org/pypi/nano-pdf/json (fetched 2026-08-29T12:06:10.403797+00:00, sha 884e9494647c)
- Data as of 2026-08-30T08:39:29.467469+00:00.