OneFileLLM is a command-line tool that automates aggregation from multiple sources (local files, GitHub repos, web pages, PDFs, YouTube transcripts, etc.) and outputs a single structured XML payload copied to your clipboard for use with large language models.
Key features
- Multi-source ingestion: supports local files, web pages, GitHub repos, issues/PRs, PDFs and transcripts.
- Unified output: packages collected content into structured XML for direct LLM consumption.
- CLI and Python API: usable as a command-line utility or integrated programmatically.
Use cases
- Quickly package research papers, codebases or docs into LLM-ready context to improve prompts.
- Consolidate scattered information into a single request to reduce retrieval overhead.
Technical notes
- Configurable crawl depth and concurrency, with options for content cleaning and filtering.
- Alias system and multiple output formats (markdown/json/html) for flexible pipelines.
- Supports GitHub API usage via environment token to enhance repository crawling.