{"adoption": {"forks": 177, "observed_at": "2026-08-28T04:06:05.099597+00:00", "stars": 2011}, "canonical_url": "https://ross.abutalabs.com/products/onefilellm", "card": {"archived": false, "artifact_type": "cli-tool", "description": "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", "domain": ["developer-tools", "large-language-models"], "enriched": true, "function": ["web-scraping", "pdf", "developer-tools", "cli", "data-science"], "health_score": 72, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["jimmc414/onefilellm"], "name": "jimmc414/onefilellm", "platform": ["python", "cli", "cross-platform"], "pushed_at": "2026-06-12T19:40:26+00:00", "repo": "jimmc414/onefilellm", "stars": 2011, "tags": ["llm-ingestion", "context-aggregation", "youtube-transcripts", "arxiv", "github-repos", "clipboard", "xml-output", "tiktoken", "command-line", "natural-language-processing"], "topics": ["arxiv", "github", "llm", "tiktoken", "youtube-transcript-api", "doi", "ipynb", "pdf", "pmid", "sci-hub", "text", "papers", "repository", "pull-request"], "urls": [], "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"], "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.", "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"], "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"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/onefilellm", "repo": "jimmc414/onefilellm", "role": "main", "score": 69}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.099597+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:01:06.736469+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b3c2001ddec561f879fafd2c961055e59b6d29f338ae3fcad9dd22694b09d4b1", "fetched_at": "2026-08-28T04:06:05.099597+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jimmc414/onefilellm"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.099597+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:01:06.736469+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b3c2001ddec561f879fafd2c961055e59b6d29f338ae3fcad9dd22694b09d4b1", "fetched_at": "2026-08-28T04:06:05.099597+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jimmc414/onefilellm"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:01:06.736469+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b3c2001ddec561f879fafd2c961055e59b6d29f338ae3fcad9dd22694b09d4b1", "fetched_at": "2026-08-28T04:06:05.099597+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jimmc414/onefilellm"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.099597+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.099597+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.099597+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:01:06.736469+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b3c2001ddec561f879fafd2c961055e59b6d29f338ae3fcad9dd22694b09d4b1", "fetched_at": "2026-08-28T04:06:05.099597+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jimmc414/onefilellm"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.099597+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.099597+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:01:06.736469+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b3c2001ddec561f879fafd2c961055e59b6d29f338ae3fcad9dd22694b09d4b1", "fetched_at": "2026-08-28T04:06:05.099597+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jimmc414/onefilellm"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.099597+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.099597+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.099597+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:01:06.736469+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b3c2001ddec561f879fafd2c961055e59b6d29f338ae3fcad9dd22694b09d4b1", "fetched_at": "2026-08-28T04:06:05.099597+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jimmc414/onefilellm"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.099597+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.099597+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:01:06.736469+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b3c2001ddec561f879fafd2c961055e59b6d29f338ae3fcad9dd22694b09d4b1", "fetched_at": "2026-08-28T04:06:05.099597+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jimmc414/onefilellm"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:01:06.736469+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b3c2001ddec561f879fafd2c961055e59b6d29f338ae3fcad9dd22694b09d4b1", "fetched_at": "2026-08-28T04:06:05.099597+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jimmc414/onefilellm"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:01:06.736469+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b3c2001ddec561f879fafd2c961055e59b6d29f338ae3fcad9dd22694b09d4b1", "fetched_at": "2026-08-28T04:06:05.099597+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jimmc414/onefilellm"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:01:06.736469+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b3c2001ddec561f879fafd2c961055e59b6d29f338ae3fcad9dd22694b09d4b1", "fetched_at": "2026-08-28T04:06:05.099597+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jimmc414/onefilellm"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 87, "longevity": 90, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1266, "days_push": 82, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 69, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}