# Feather-2/Burner-X

Burner X - 浏览器即开即用，AI文献识别、文档批量翻译、阅读与智能分析工具 丨BYOK

Repository: https://github.com/Feather-2/Burner-X
Canonical: https://ross.abutalabs.com/products/burner-x
Homepage: https://www.paperburner.site/
Language: JavaScript
License: AGPL-3.0
License Family: copyleft
Last push: 2026-03-09T05:38:02+00:00

## Health v2 (maintenance only)
Score: 51/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 71, release rhythm 35, longevity 35
- inputs: {"age_days": 493, "days_push": 177, "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 1750, forks 750 (observed 2026-08-28T04:05:31.131729+00:00)

## What it is
Paper Burner X is a browser-based AI workstation for processing, translating, and analyzing academic documents like PDFs, DOCX, PPTX, and EPUBs. It runs entirely client-side with BYOK (bring your own key) model endpoints, offering OCR, format-preserving batch translation, terminology glossaries, and an agentic RAG system for long-document Q&A.

## Use cases
- translate academic pdfs preserving formulas and layout
- ocr scanned papers and extract text
- batch translate many documents at once
- ask questions about a long paper with an ai agent
- maintain a terminology glossary for consistent translation
- read papers side-by-side with aligned translations
- extract structured data from papers into a literature matrix
- import documents from github or urls for processing

## When to choose
- you need privacy-first, fully client-side document translation and analysis
- you want to bring your own AI API keys and model endpoints
- you regularly read foreign-language academic papers with formulas and figures
- you need batch OCR and translation with terminology consistency

## When to avoid
- you need a lightweight minimal pdf reader without AI features
- you require a mature backend/server deployment today (Docker backend still in development)
- you need offline operation right now rather than in the future
- you want multi-document synthesis, which is still a planned milestone

## Facets
- artifact type: application
- maturity: active
- function: ocr, nlp, rag, agent-framework, machine-learning, pdf, internationalization, file-upload
- domain: pdf, education, artificial-intelligence, developer-tools, self-hosted
- platform: browser, self-hosted
- tags: pdf-translation, academic-reading, byok, bring-your-own-key, document-processing, terminology-glossary, agentic-rag, client-side, literature-review, ocr-translation, natural-language-processing, web-server, docker, javascript

## Member repositories
- Feather-2/Burner-X (main) score 51

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:31.131729+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 2026-08-30T03:28:34.274538+00:00, confidence not recorded.
  - readme: https://github.com/Feather-2/Burner-X (fetched 2026-08-28T04:05:31.131729+00:00, sha 3bae7c725749)
  - homepage: https://www.paperburner.site/ (fetched 2026-08-29T11:06:48.055439+00:00, sha a834a685f407)
- Data as of 2026-08-30T08:39:29.467469+00:00.