# jimmc414/onefilellm

Specify a github or local repo, github pull request,  arXiv or Sci-Hub paper, Youtube transcript or documentation URL on the web and scrape into a text file and clipboard  for easier LLM ingestion

Repository: https://github.com/jimmc414/onefilellm
Canonical: https://ross.abutalabs.com/products/onefilellm
Language: Python
License: MIT
License Family: permissive
Topics: arxiv, github, llm, tiktoken, youtube-transcript-api, doi, ipynb, pdf, pmid, sci-hub, text, papers, repository, pull-request
Last push: 2026-06-12T19:40:26+00:00

## Health v2 (maintenance only)
Score: 69/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 87, release rhythm 35, longevity 90
- inputs: {"age_days": 1266, "days_push": 82, "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 2011, forks 177 (observed 2026-08-28T04:06:05.099597+00:00)

## What it is
OneFileLLM is a Python command-line tool and library that aggregates content from sources like GitHub repos, pull requests, arXiv/Sci-Hub papers, YouTube transcripts, web pages, PDFs, and local files into a single structured XML text file. The output is automatically copied to the clipboard for easy pasting into Large Language Model prompts.

## Use cases
- scrape a github repo into a single text file for llm context
- convert an arxiv paper to text for chatgpt
- extract youtube transcript for llm ingestion
- combine documentation urls into one file for a prompt
- pull a github pull request diff into llm context
- aggregate local pdfs and notebooks into one xml file
- crawl a docs site and feed it to an llm

## When to choose
- you need to quickly assemble multi-source context for an LLM prompt
- you want a CLI or Python API to flatten repos, papers, and web pages into one file
- you want automatic clipboard copying of aggregated text

## When to avoid
- you need a persistent RAG pipeline with embeddings and retrieval
- you need a GUI or web interface
- you only need to scrape a single page with no LLM-focused formatting

## Facets
- artifact type: cli-tool
- maturity: active
- function: web-scraping, pdf, developer-tools, cli, data-science
- domain: developer-tools, large-language-models
- platform: python, cli, cross-platform
- tags: llm-ingestion, context-aggregation, youtube-transcripts, arxiv, github-repos, clipboard, xml-output, tiktoken, command-line, natural-language-processing

## Member repositories
- jimmc414/onefilellm (main) score 69

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:05.099597+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 2026-08-30T03:01:06.736469+00:00, confidence not recorded.
  - readme: https://github.com/jimmc414/onefilellm (fetched 2026-08-28T04:06:05.099597+00:00, sha b3c2001ddec5)
- Data as of 2026-08-30T08:39:29.467469+00:00.